From 64796ac3c0223c5bed1f3631584b47569efac992 Mon Sep 17 00:00:00 2001 From: "Marc A. Suchard" Date: Mon, 30 Oct 2023 18:02:26 -0700 Subject: [PATCH 1/6] v3.4.0 --- DESCRIPTION | 5 +++- cran-comments.md | 13 ++------- man/Multitype.Rd | 2 +- man/aconfint.Rd | 4 +-- man/convertToCyclopsData.Rd | 22 +++++++-------- man/convertToTimeVaryingCoef.Rd | 18 ++++++------ man/createControl.Rd | 2 +- man/createCyclopsData.Rd | 28 +++++++++--------- man/fitCyclopsModel.Rd | 6 ++-- man/oxford.Rd | 14 ++++----- man/readCyclopsData.Rd | 50 ++++++++++++++++----------------- man/splitTime.Rd | 6 ++-- 12 files changed, 84 insertions(+), 86 deletions(-) diff --git a/DESCRIPTION b/DESCRIPTION index f0525ba9..315e76ba 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,7 +1,7 @@ Package: Cyclops Type: Package Title: Cyclic Coordinate Descent for Logistic, Poisson and Survival Analysis -Version: 3.3.1.999 +Version: 3.4.0 Authors@R: c( person("Marc A.", "Suchard", email = "msuchard@ucla.edu", role = c("aut","cre")), person("Martijn J.", "Schuemie", role = "aut"), @@ -50,4 +50,7 @@ Suggests: ggplot2, microbenchmark, cmprsk +NeedsCompilation: yes RoxygenNote: 7.2.3 +Roxygen: list(markdown = TRUE) +Encoding: UTF-8 diff --git a/cran-comments.md b/cran-comments.md index ad72b40d..a4daffbb 100644 --- a/cran-comments.md +++ b/cran-comments.md @@ -1,16 +1,9 @@ -## Resubmission after VALGRIND feedback from Brian Ripley +## Submission of v3.4.0 -* fixed VALGRIND uninitialized value (UB) issue; variable 'priorType' was uninitialized, - specifically in: - - ==2293460== Conditional jump or move depends on uninitialised value(s) - ==2293460== at 0x22CE4848: bsccs::CyclicCoordinateDescent::computeAsymptoticPrecisionMatrix() (packages/tests-vg/Cyclops/src/cyclops/CyclicCoordinateDescent.cpp:1335) +* fixed use of deprecated `$` function in `dbplyr` using CRAN errors -* fixed VALGRIND memory leak issue; was caused by calls to '::Rf_error()' instead of - 'Rcpp::stop()' when handling some error edge-cases - ## Test environments -* local OS X install, R 4.1 +* local OS X install, R 4.3 * r-devel-valgrind docker container * ubuntu 20.04 (via gh-actions: devel and release) * win-builder (devel and release) diff --git a/man/Multitype.Rd b/man/Multitype.Rd index 4515482a..933eb4fa 100644 --- a/man/Multitype.Rd +++ b/man/Multitype.Rd @@ -15,7 +15,7 @@ Multitype(y, type) An object of class \code{Multitype} with length equal to the length of \code{y} and \code{type}. } \description{ -\code{Multitype} creates a multitype outcome object, usually used as a response variable in a +\code{Multitype} creates a multitype outcome object, usually used as a response variable in a hierarchical Cyclops model fit. } \examples{ diff --git a/man/aconfint.Rd b/man/aconfint.Rd index 7be57887..5750802b 100644 --- a/man/aconfint.Rd +++ b/man/aconfint.Rd @@ -29,8 +29,8 @@ either a vector of numbers of covariateId names} } \value{ A matrix with columns reporting lower and upper confidence limits for each parameter. -These columns are labelled as (1-level) / 2 and 1 - (1 - level) / 2 in % -(by default 2.5% and 97.5%) +These columns are labelled as (1-level) / 2 and 1 - (1 - level) / 2 in \% +(by default 2.5\% and 97.5\%) } \description{ \code{aconfinit} constructs confidence intervals of diff --git a/man/convertToCyclopsData.Rd b/man/convertToCyclopsData.Rd index 391ec1ec..5a947cb8 100644 --- a/man/convertToCyclopsData.Rd +++ b/man/convertToCyclopsData.Rd @@ -70,21 +70,21 @@ An object of type cyclopsData \details{ These columns are expected in the outcome object: \tabular{lll}{ - \verb{stratumId} \tab(integer) \tab (optional) Stratum ID for conditional regression models \cr - \verb{rowId} \tab(integer) \tab Row ID is used to link multiple covariates (x) to a single outcome (y) \cr - \verb{y} \tab(real) \tab The outcome variable \cr - \verb{time} \tab(real) \tab For models that use time (e.g. Poisson or Cox regression) this contains time \cr - \tab \tab(e.g. number of days) \cr - \verb{weights} \tab(real) \tab (optional) Non-negative weights to apply to outcome \cr - \verb{censorWeights} \tab(real) \tab (optional) Non-negative censoring weights for competing risk model; will be computed if not provided. +\verb{stratumId} \tab(integer) \tab (optional) Stratum ID for conditional regression models \cr +\verb{rowId} \tab(integer) \tab Row ID is used to link multiple covariates (x) to a single outcome (y) \cr +\verb{y} \tab(real) \tab The outcome variable \cr +\verb{time} \tab(real) \tab For models that use time (e.g. Poisson or Cox regression) this contains time \cr +\tab \tab(e.g. number of days) \cr +\verb{weights} \tab(real) \tab (optional) Non-negative weights to apply to outcome \cr +\verb{censorWeights} \tab(real) \tab (optional) Non-negative censoring weights for competing risk model; will be computed if not provided. } These columns are expected in the covariates object: \tabular{lll}{ - \verb{stratumId} \tab(integer) \tab (optional) Stratum ID for conditional regression models \cr - \verb{rowId} \tab(integer) \tab Row ID is used to link multiple covariates (x) to a single outcome (y) \cr - \verb{covariateId} \tab(integer) \tab A numeric identifier of a covariate \cr - \verb{covariateValue} \tab(real) \tab The value of the specified covariate \cr +\verb{stratumId} \tab(integer) \tab (optional) Stratum ID for conditional regression models \cr +\verb{rowId} \tab(integer) \tab Row ID is used to link multiple covariates (x) to a single outcome (y) \cr +\verb{covariateId} \tab(integer) \tab A numeric identifier of a covariate \cr +\verb{covariateValue} \tab(real) \tab The value of the specified covariate \cr } } \section{Methods (by class)}{ diff --git a/man/convertToTimeVaryingCoef.Rd b/man/convertToTimeVaryingCoef.Rd index b587f8f2..0902c226 100644 --- a/man/convertToTimeVaryingCoef.Rd +++ b/man/convertToTimeVaryingCoef.Rd @@ -22,18 +22,18 @@ A long sparse covariate table for time-varying coefficients. \details{ These columns are expected in the shortCov object: \tabular{lll}{ - \verb{rowId} \tab(integer) \tab Row ID is used to link multiple covariates (x) to a single outcome (y) \cr - \verb{covariateId} \tab(integer) \tab A numeric identifier of a covariate \cr - \verb{covariateValue} \tab(real) \tab The value of the specified covariate \cr +\verb{rowId} \tab(integer) \tab Row ID is used to link multiple covariates (x) to a single outcome (y) \cr +\verb{covariateId} \tab(integer) \tab A numeric identifier of a covariate \cr +\verb{covariateValue} \tab(real) \tab The value of the specified covariate \cr } These columns are expected in the longOut object: \tabular{lll}{ - \verb{stratumId} \tab(integer) \tab Stratum ID for time-varying models \cr - \verb{subjectId} \tab(integer) \tab Subject ID is used to link multiple covariates (x) at different time intervals to a single subject \cr - \verb{rowId} \tab(integer) \tab Row ID is used to link multiple covariates (x) to a single outcome (y) \cr - \verb{y} \tab(real) \tab The outcome variable \cr - \verb{time} \tab(real) \tab For models that use time (e.g. Poisson or Cox regression) this contains time \cr - \tab \tab(e.g. number of days) \cr +\verb{stratumId} \tab(integer) \tab Stratum ID for time-varying models \cr +\verb{subjectId} \tab(integer) \tab Subject ID is used to link multiple covariates (x) at different time intervals to a single subject \cr +\verb{rowId} \tab(integer) \tab Row ID is used to link multiple covariates (x) to a single outcome (y) \cr +\verb{y} \tab(real) \tab The outcome variable \cr +\verb{time} \tab(real) \tab For models that use time (e.g. Poisson or Cox regression) this contains time \cr +\tab \tab(e.g. number of days) \cr } } diff --git a/man/createControl.Rd b/man/createControl.Rd index 6da2461c..2dddced6 100644 --- a/man/createControl.Rd +++ b/man/createControl.Rd @@ -75,7 +75,7 @@ the average number of rows per stratum is smaller than the number of strata.} \item{maxBoundCount}{Numeric: Maximum number of tries to decrease initial trust-region size} -\item{algorithm}{String: name of fitting algorithm to employ; default is `ccd` +\item{algorithm}{String: name of fitting algorithm to employ; default is \code{ccd} Todo: Describe convegence types} } diff --git a/man/createCyclopsData.Rd b/man/createCyclopsData.Rd index 7a645b5a..8b4c43b4 100644 --- a/man/createCyclopsData.Rd +++ b/man/createCyclopsData.Rd @@ -83,24 +83,26 @@ Objects provided with \code{"sparseFormula"} and \code{"indicatorFormula"} must coersed into sparse and indicator representations for computational efficiency. Items to discuss: -* Only use formula or (y,dx,...) -* stratum() in formula -* offset() in formula -* when \code{"stratum"} (renamed from pid) are necessary -* when \code{"time"} are necessary +\itemize{ +\item Only use formula or (y,dx,...) +\item stratum() in formula +\item offset() in formula +\item when \code{"stratum"} (renamed from pid) are necessary +\item when \code{"time"} are necessary +} } \section{Models}{ Currently supported model types are: \tabular{ll}{ - \verb{ "ls"} \tab Least squares \cr - \verb{ "pr"} \tab Poisson regression \cr - \verb{ "lr"} \tab Logistic regression \cr - \verb{ "clr"} \tab Conditional logistic regression \cr - \verb{ "cpr"} \tab Conditional Poisson regression \cr - \verb{ "sccs"} \tab Self-controlled case series \cr - \verb{ "cox"} \tab Cox proportional hazards regression \cr - \verb{ "fgr"} \tab Fine-Gray proportional subdistribution hazards regression \cr +\verb{ "ls"} \tab Least squares \cr +\verb{ "pr"} \tab Poisson regression \cr +\verb{ "lr"} \tab Logistic regression \cr +\verb{ "clr"} \tab Conditional logistic regression \cr +\verb{ "cpr"} \tab Conditional Poisson regression \cr +\verb{ "sccs"} \tab Self-controlled case series \cr +\verb{ "cox"} \tab Cox proportional hazards regression \cr +\verb{ "fgr"} \tab Fine-Gray proportional subdistribution hazards regression \cr } } diff --git a/man/fitCyclopsModel.Rd b/man/fitCyclopsModel.Rd index 22381607..66f2495b 100644 --- a/man/fitCyclopsModel.Rd +++ b/man/fitCyclopsModel.Rd @@ -51,9 +51,9 @@ This function performs numerical optimization to fit a Cyclops model data object Currently supported prior types are: \tabular{ll}{ - \verb{ "none"} \tab Useful for finding MLE \cr - \verb{ "laplace"} \tab L_1 regularization \cr - \verb{ "normal"} \tab L_2 regularization \cr +\verb{ "none"} \tab Useful for finding MLE \cr +\verb{ "laplace"} \tab L_1 regularization \cr +\verb{ "normal"} \tab L_2 regularization \cr } } diff --git a/man/oxford.Rd b/man/oxford.Rd index 4fdf55d6..c5720893 100644 --- a/man/oxford.Rd +++ b/man/oxford.Rd @@ -7,13 +7,13 @@ \format{ A data frame with 38 rows and 6 variables: \describe{ - \item{indiv}{patient identifier} - \item{event}{number of events in interval} - \item{interval}{interval length in days} - \item{agegr}{age group} - \item{exgr}{exposure group} - \item{loginterval}{log interval length} - ... +\item{indiv}{patient identifier} +\item{event}{number of events in interval} +\item{interval}{interval length in days} +\item{agegr}{age group} +\item{exgr}{exposure group} +\item{loginterval}{log interval length} +... } } \usage{ diff --git a/man/readCyclopsData.Rd b/man/readCyclopsData.Rd index e9a3f23c..c9625522 100644 --- a/man/readCyclopsData.Rd +++ b/man/readCyclopsData.Rd @@ -21,19 +21,19 @@ A list that contains a Cyclops model data object pointer and an operation durati This function reads a Cyclops-formatted text file and returns a Cyclops data object. The first line of the file may start with '\samp{#}', indicating that it contains header options. Valid header options are: - \tabular{ll}{ - \verb{ row_label} \tab (assume file contains a numeric column of unique row identifiers) \cr - \verb{ stratum_label}\tab (assume file contains a numeric column of stratum identifiers) \cr - \verb{ weight} \tab (assume file contains a column of row-specific model weights, currently unused) \cr - \verb{ offset} \tab (assume file contains a dense column of linear predictor offsets) \cr - \verb{ bbr_outcome} \tab (assume logistic outcomes are encoded -1/+1 following BBR) \cr - \verb{ log_offset} \tab (assume file contains a dense column of values x_i for which log(x_i) is the offset) \cr - \verb{ add_intercept}\tab (automatically include an intercept column of all 1s for each entry) \cr - \verb{ indicator_only}\tab(assume all covariates 0/1-valued and only covariate name is given) \cr - \verb{ sparse} \tab (force all BBR formatted covariates to be represented as sparse, instead of \cr - \tab sparse-indicator, columns .. really only for debugging) \cr - \verb{ dense} \tab (force all BBR formatted covariates to be represented as dense columns.. really\cr - \tab only for debugging) \cr +\tabular{ll}{ +\verb{ row_label} \tab (assume file contains a numeric column of unique row identifiers) \cr +\verb{ stratum_label}\tab (assume file contains a numeric column of stratum identifiers) \cr +\verb{ weight} \tab (assume file contains a column of row-specific model weights, currently unused) \cr +\verb{ offset} \tab (assume file contains a dense column of linear predictor offsets) \cr +\verb{ bbr_outcome} \tab (assume logistic outcomes are encoded -1/+1 following BBR) \cr +\verb{ log_offset} \tab (assume file contains a dense column of values x_i for which log(x_i) is the offset) \cr +\verb{ add_intercept}\tab (automatically include an intercept column of all 1s for each entry) \cr +\verb{ indicator_only}\tab(assume all covariates 0/1-valued and only covariate name is given) \cr +\verb{ sparse} \tab (force all BBR formatted covariates to be represented as sparse, instead of \cr +\tab sparse-indicator, columns .. really only for debugging) \cr +\verb{ dense} \tab (force all BBR formatted covariates to be represented as dense columns.. really\cr +\tab only for debugging) \cr } Successive lines of the file are white-space delimited and follow the format: @@ -41,10 +41,10 @@ Successive lines of the file are white-space delimited and follow the format: \preformatted{ [Row ID] {Stratum ID} [Weight] {Censored} {Offset} } \itemize{ - \item \verb{[optional]} - \item \verb{} - \item \verb{{required or optional depending on model}} - } +\item \verb{[optional]} +\item \verb{} +\item \verb{{required or optional depending on model}} +} Bayesian binary regression (BBR) covariates are white-space delimited and generally in a sparse \samp{:} format, where \samp{name} must (currently) be numeric and \samp{value} is non-zero. @@ -59,14 +59,14 @@ are consecutive. Currently supported model types are: \tabular{ll}{ - \verb{ "ls"} \tab Least squares \cr - \verb{ "pr"} \tab Poisson regression \cr - \verb{ "lr"} \tab Logistic regression \cr - \verb{ "clr"} \tab Conditional logistic regression \cr - \verb{ "cpr"} \tab Conditional Poisson regression \cr - \verb{ "sccs"} \tab Self-controlled case series \cr - \verb{ "cox"} \tab Cox proportional hazards regression \cr - \verb{ "fgr"} \tab Fine-Gray proportional subdistribution hazards regression \cr +\verb{ "ls"} \tab Least squares \cr +\verb{ "pr"} \tab Poisson regression \cr +\verb{ "lr"} \tab Logistic regression \cr +\verb{ "clr"} \tab Conditional logistic regression \cr +\verb{ "cpr"} \tab Conditional Poisson regression \cr +\verb{ "sccs"} \tab Self-controlled case series \cr +\verb{ "cox"} \tab Cox proportional hazards regression \cr +\verb{ "fgr"} \tab Fine-Gray proportional subdistribution hazards regression \cr } } diff --git a/man/splitTime.Rd b/man/splitTime.Rd index fedc4a7e..955a7967 100644 --- a/man/splitTime.Rd +++ b/man/splitTime.Rd @@ -13,9 +13,9 @@ splitTime(shortOut, cut) These columns are expected in the shortOut object: \tabular{lll}{ - \verb{rowId} \tab(integer) \tab Row ID is used to link multiple covariates (x) to a single outcome (y) \cr - \verb{y} \tab(real) \tab Observed event status \cr - \verb{time} \tab(real) \tab Observed event time \cr +\verb{rowId} \tab(integer) \tab Row ID is used to link multiple covariates (x) to a single outcome (y) \cr +\verb{y} \tab(real) \tab Observed event status \cr +\verb{time} \tab(real) \tab Observed event time \cr }} } \value{ From 1c633d873686958d72c414480da15e01ca72d878 Mon Sep 17 00:00:00 2001 From: "Marc A. Suchard" Date: Mon, 30 Oct 2023 18:03:21 -0700 Subject: [PATCH 2/6] delete file --- CRAN-SUBMISSION | 3 --- 1 file changed, 3 deletions(-) delete mode 100644 CRAN-SUBMISSION diff --git a/CRAN-SUBMISSION b/CRAN-SUBMISSION deleted file mode 100644 index e91558cb..00000000 --- a/CRAN-SUBMISSION +++ /dev/null @@ -1,3 +0,0 @@ -Version: 3.3.1 -Date: 2023-04-09 20:06:33 UTC -SHA: d88c531efa06933c1007cb785343f1382c95ee0d From e99ed7b7524c641486d12d568fa2b3573a0bf994 Mon Sep 17 00:00:00 2001 From: Marc Suchard Date: Tue, 31 Oct 2023 06:13:46 -0700 Subject: [PATCH 3/6] update website --- README.md | 2 +- docs/404.html | 119 +-- docs/authors.html | 218 ++-- docs/index.html | 186 ++-- docs/news/index.html | 358 +++---- docs/pkgdown.css | 83 +- docs/pkgdown.js | 4 +- docs/pkgdown.yml | 6 +- docs/reference/Cyclops-package.html | 105 ++ docs/reference/Multitype.html | 185 ++-- docs/reference/aconfint.html | 204 ++-- docs/reference/appendSqlCyclopsData.html | 214 ++-- docs/reference/coef.cyclopsFit.html | 168 +--- docs/reference/confint.cyclopsFit.html | 936 ++++++++++++----- docs/reference/convertToCyclopsData.html | 358 +++---- docs/reference/convertToCyclopsVariance.html | 146 +-- docs/reference/convertToGlmnetLambda.html | 148 +-- docs/reference/convertToTimeVaryingCoef.html | 109 ++ docs/reference/coverage.html | 160 +-- .../createAutoGridCrossValidationControl.html | 204 ++-- docs/reference/createControl.html | 630 +++++------- docs/reference/createCyclopsData.html | 424 ++++---- docs/reference/createNonSeparablePrior.html | 156 +-- docs/reference/createParameterizedPrior.html | 194 ++-- docs/reference/createPrior.html | 941 +++--------------- .../createWeightBasedSearchControl.html | 113 +++ docs/reference/cyclops.html | 115 +-- docs/reference/finalizeSqlCyclopsData.html | 189 ++-- docs/reference/fitCyclopsModel.html | 288 +++--- docs/reference/fitCyclopsSimulation.html | 177 +--- docs/reference/getCovariateIds.html | 129 +-- docs/reference/getCovariateTypes.html | 137 +-- docs/reference/getCrossValidationInfo.html | 129 +-- .../getCyclopsPredictiveLogLikelihood.html | 144 +-- .../getCyclopsProfileLogLikelihood.html | 208 ++-- docs/reference/getFineGrayWeights.html | 191 ++-- docs/reference/getFloatingPointSize.html | 129 +-- docs/reference/getHyperParameter.html | 863 +++++++++++----- docs/reference/getNumberOfCovariates.html | 129 +-- docs/reference/getNumberOfRows.html | 129 +-- docs/reference/getNumberOfStrata.html | 129 +-- docs/reference/getNumberOfTypes.html | 129 +-- docs/reference/getSEs.html | 147 +-- docs/reference/getUnivariableCorrelation.html | 158 +-- .../reference/getUnivariableSeparability.html | 144 +-- docs/reference/index.html | 298 ++---- docs/reference/isInitialized.html | 131 +-- docs/reference/logLik.cyclopsFit.html | 325 +++--- docs/reference/meanLinearPredictor.html | 129 +-- docs/reference/mse.html | 144 +-- docs/reference/oxford.html | 147 +-- docs/reference/plotCyclopsSimulationFit.html | 149 +-- docs/reference/predict.cyclopsFit.html | 157 +-- docs/reference/print.cyclopsData.html | 149 +-- docs/reference/print.cyclopsFit.html | 149 +-- docs/reference/printMatrixMarket.html | 137 +-- docs/reference/readCyclopsData.html | 205 +--- docs/reference/reduce.html | 166 +-- docs/reference/simulateCyclopsData.html | 517 +++++----- docs/reference/splitTime.html | 103 ++ docs/reference/summary.cyclopsData.html | 146 +-- docs/reference/survfit.cyclopsFit.html | 150 +-- docs/reference/vcov.cyclopsFit.html | 168 +--- docs/sitemap.xml | 186 ++++ extras/Cyclops.pdf | Bin 208382 -> 148374 bytes 65 files changed, 5372 insertions(+), 8219 deletions(-) create mode 100644 docs/reference/Cyclops-package.html create mode 100644 docs/reference/convertToTimeVaryingCoef.html create mode 100644 docs/reference/createWeightBasedSearchControl.html create mode 100644 docs/reference/splitTime.html create mode 100644 docs/sitemap.xml diff --git a/README.md b/README.md index f7eded0b..3db57215 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ Cyclops ======= [![Build Status](https://github.com/ohdsi/Cyclops/workflows/R-CMD-check/badge.svg)](https://github.com/OHDSI/Cyclops/actions?query=workflow%3AR-CMD-check) -[![codecov.io](https://app.codecov.io/github/OHDSI/Cyclops/coverage.svg?branch=main)](https://app.codecov.io/github/OHDSI/Cyclops?branch=main) +[![codecov.io](https://codecov.io/github/OHDSI/Cyclops/coverage.svg?branch=main)](https://codecov.io/github/OHDSI/Cyclops?branch=main) [![CRAN_Status_Badge](https://www.r-pkg.org/badges/version/Cyclops)](https://CRAN.R-project.org/package=Cyclops) [![CRAN_Status_Badge](https://cranlogs.r-pkg.org/badges/Cyclops)](https://cran.r-project.org/package=Cyclops) diff --git a/docs/404.html b/docs/404.html index bd75ee9e..01baf29a 100644 --- a/docs/404.html +++ b/docs/404.html @@ -1,66 +1,27 @@ - - - - + + + + - Page not found (404) • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + - - - - -
-
- + +
+ + + - - -
+

Page not found (404)

@@ -121,31 +76,31 @@

Page not found (404)

+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

+

Site built with pkgdown 2.0.7.

-
+
+ + - - diff --git a/docs/authors.html b/docs/authors.html index 27d243a5..fffc6264 100644 --- a/docs/authors.html +++ b/docs/authors.html @@ -1,66 +1,12 @@ - - - - - - - -Citation and Authors • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Authors and Citation • Cyclops - - + + - - -
-
- -
- -
+
-
-

Citation

- Source: inst/CITATION +
+
+

Authors

+
+ + +
  • +

    Marc A. Suchard. Author, maintainer. +

    +
    • +
  • +

    Martijn J. Schuemie. Author. +

    +
    • +
  • +

    Trevor R. Shaddox. Author. +

    +
    • +
  • +

    Yuxi Tian. Author. +

    +
    • +
  • +

    Jianxiao Yang. Author. +

    +
    • +
  • +

    Eric Kawaguchi. Author. +

    +
    • +
  • +

    Sushil Mittal. Contributor. +

    +
    • +
  • +

    Observational Health Data Sciences and Informatics. Copyright holder. +

    +
    • +
  • +

    Marcus Geelnard. Copyright holder, contributor. +
    provided the TinyThread library

    +
    • +
  • +

    Rutgers University. Copyright holder, contributor. +
    provided the HParSearch routine

    +
    • +
  • +

    R Development Core Team. Copyright holder, contributor. +
    provided the ZeroIn routine

    +
    • +
+
+
+

Citation

+ Source: inst/CITATION
+
+

Suchard MA, Simpson SE, Zorych I, Ryan P, Madigan D (2013). -“Massive parallelization of serial inference algorithms for complex generalized linear models.” +“Massive parallelization of serial inference algorithms for complex generalized linear models.” ACM Transactions on Modeling and Computer Simulation, 23, 10. -https://dl.acm.org/doi/10.1145/2414416.2414791. +https://dl.acm.org/doi/10.1145/2414416.2414791. 

@Article{,
   author = {M. A. Suchard and S. E. Simpson and I. Zorych and P. Ryan and D. Madigan},
@@ -132,79 +119,26 @@ 
Citation

   url = {https://dl.acm.org/doi/10.1145/2414416.2414791},
 }
-
-

Authors

-
- -
    -
  • -

    Marc A. Suchard. Author, maintainer. -

    -
    • -
  • -

    Martijn J. Schuemie. Author. -

    -
    • -
  • -

    Trevor R. Shaddox. Author. -

    -
    • -
  • -

    Yuxi Tian. Author. -

    -
    • -
  • -

    Jianxiao Yang. Author. -

    -
    • -
  • -

    Eric Kawaguchi. Author. -

    -
    • -
  • -

    Sushil Mittal. Contributor. -

    -
    • -
  • -

    Observational Health Data Sciences and Informatics. Copyright holder. -

    -
    • -
  • -

    Marcus Geelnard. Copyright holder, contributor. -
    provided the TinyThread library

    -
    • -
  • -

    Rutgers University. Copyright holder, contributor. -
    provided the HParSearch routine

    -
    • -
  • -

    R Development Core Team. Copyright holder, contributor. -
    provided the ZeroIn routine

    -
    • -
-
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/index.html b/docs/index.html index fcfd38ef..660ec66e 100644 --- a/docs/index.html +++ b/docs/index.html @@ -24,6 +24,8 @@ + +
-
-

-Cyclops

- -

Cyclops is part of the HADES.

-
-
-

-Introduction

+
+

Cyclops +

+

Build Status codecov.io CRAN_Status_Badge CRAN_Status_Badge

+

Cyclops is part of the HADES.

+
+
+

Introduction +

Cyclops (Cyclic coordinate descent for logistic, Poisson and survival analysis) is an R package for performing large scale regularized regressions.

-
-

-Features

+
+

Features +

  • Regression of very large problems: up to millions of observations, millions of variables
  • Supports (conditional) logistic regression, (conditional) Poisson regression, as well as (conditional) Cox regression
    • @@ -101,78 +97,69 @@

  • Efficient estimation of confidence intervals for a single variable using a profile-likelihood for that variable

-
-

-Examples

+
+

Examples +

-  library(Cyclops)
-  cyclopsData <- createCyclopsDataFrame(formula)
-  cyclopsFit <- fitCyclopsModel(cyclopsData)
+ library(Cyclops) + cyclopsData <- createCyclopsDataFrame(formula) + cyclopsFit <- fitCyclopsModel(cyclopsData)
-
-

-Technology

+
+

Technology +

Cyclops in an R package, with most functionality implemented in C++. Cyclops uses cyclic coordinate descent to optimize the likelihood function, which makes use of the sparse nature of the data.

-
-

-System Requirements

-

Requires R (version 3.1.0 or higher). Compilation on Windows requires RTools >= 3.4.

+
+

System Requirements +

+

Requires R (version 3.1.0 or higher). Compilation on Windows requires RTools >= 3.4.

-
-

-Installation

+
+

Installation +

In R, to install the latest stable version, install from CRAN:

-install.packages("Cyclops")
+install.packages("Cyclops")

To install the latest development version, install from GitHub. Note that this will require RTools to be installed.

-install.packages("devtools")
-devtools::install_github("OHDSI/Cyclops")
-
-
-

-User Documentation

-

Documentation can be found on the package website.

-

PDF versions of the documentation are also available:

+install.packages("devtools") +devtools::install_github("OHDSI/Cyclops")
+
+
+

User Documentation +

+

Documentation can be found on the package website.

+

PDF versions of the documentation are also available: * Package manual: Cyclops manual

+
+
+

Support +

-
-

-Support

- +
+

Contributing +

+

Read here how you can contribute to this package.

-
-

-Contributing

-

Read here how you can contribute to this package.

-
-
-

-License

+
+

License +

Cyclops is licensed under Apache License 2.0. Cyclops contains the TinyThread libray.

-

The TinyThread library is licensed under the zlib/libpng license as described here.

+

The TinyThread library is licensed under the zlib/libpng license as described here.

-
-

-Development

+
+

Development +

Cyclops is being developed in R Studio.

-
-

-Development status

-

Beta

-
-
-

-Acknowledgements

+
+

Acknowledgements +

  • This project is supported in part through the National Science Foundation grants IIS 1251151 and DMS 1264153.
@@ -182,32 +169,32 @@

+ + +

-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+

+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

+

Site built with pkgdown 2.0.7.

@@ -246,5 +228,7 @@

Dev status

+ + diff --git a/docs/news/index.html b/docs/news/index.html index 3f0bc1cf..c6ee3bab 100644 --- a/docs/news/index.html +++ b/docs/news/index.html @@ -1,66 +1,12 @@ - - - - - - - -Changelog • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Changelog • Cyclops - + + - - - -
-
- -
- -
+

Changelog

- Source: NEWS.md + Source: NEWS.md
-
-

-Cyclops v3.1.2 2021-06-16 -

-

Changes:

-
    -
  1. adaptive likelihood profiling when objective function is concave.
    2. -
-
-
-

-Cyclops v3.1.1 2021-03-23 -

+
+

Cyclops v3.4.02023-10-30

Changes:

-
    -
  1. specify new option nocenter in survival package when testing predicted hazard function
    2. -
-
-
-

-Cyclops v3.1.0 2020-11-05 -

+
  1. remove dependence on BH +
    2. +
  2. improvements on adaptive likelihood profiling
    3. +
  3. add auto option to cvRepetitions +
    4. +
  4. bumped explicit C++11 requirement up to R v4.1
    5. +
  5. removed deprecated use of dbplyr:::$.tbl_lazy +
    1. breaking change in dbplyr v2.4.0 +
      2. +
    6. +
+
+

Cyclops v3.3.12023-04-11

Changes:

-
    -
  1. implement Fine-Gray competing risks regression
    2. +
    1. fix uninitialized value in detected in computeAsymptoticPrecisionMatrix(); value was priorType
      2. +
    2. fix memory leak caused by call to ::Rf_error() +
      3. +
    3. fix line-endings on Makevar on windows
      4. +
+
+

Cyclops v3.3.02023-04-05

+
  1. bump for R 4.2
    2. +
  2. fix CRAN warnings +
    1. used minValues +
      2. +
    3. +
  3. fix CRAN notes +
    1. remove explicit dependence on C++11 (except for R <= 4.0)
      2. +
    4. +
+
+

Cyclops v3.2.12022-08-10

+

Changes:

+
  1. fix small memory leak caused by direct call to ‘::Rf_error()’
    2. +
  2. disable JVM calls on CRAN due to uninitialized memory in Java JVM
    3. +
+
+

Cyclops v3.2.02022-06-30

+

Changes:

+
  1. fixed likelihood profiling when non-convex due to numerical instability
    2. +
  2. fixed parsing of 64-bit covariate IDs
    3. +
  3. fix BLR convergence criterion when there are 0 (survival) events
    4. +
  4. add Jeffrey’s prior for single regression coefficient
    5. +
+
+

Cyclops v3.1.22021-06-16

+

Changes:

+
  1. adaptive likelihood profiling when objective function is concave.
    2. +
+
+

Cyclops v3.1.12021-03-23

+

Changes:

+
  1. specify new option nocenter in survival package when testing predicted hazard function
    2. +
+
+

Cyclops v3.1.02020-11-05

+

Changes:

+
  1. implement Fine-Gray competing risks regression
  2. fixed getCyclopsProfileLogLikelihood when starting with extreme coefficients
    3. -
-
-
-

-Cyclops v3.0.0 2020-06-05 -

+
+
+

Cyclops v3.0.02020-06-05

Changes:

-
    -
  1. switch to Andromeda from ff to hold large datasets. This change breaks API
    2. -
-
-
-

-Cyclops v2.0.4 Unreleased -

+
  1. switch to Andromeda from ff to hold large datasets. This change breaks API
    2. +
+
+

Cyclops v2.0.4

Changes:

-
    -
  1. removed, unused variable imputation functions that contained a std::exit +
    1. removed, unused variable imputation functions that contained a std::exit
      2. -
    -
-
-

-Cyclops v2.0.3 2020-04-11 -

+
+
+

Cyclops v2.0.32020-04-11

Changes:

-
    -
  1. fix computation under conditional Poisson models by reverting to v1.3.4-style loop
    2. +
    1. fix computation under conditional Poisson models by reverting to v1.3.4-style loop
    2. fix several unit-tests for compatibility with R 4.0 factors
    3. add ability to profile likelihood function in parallel
    4. add initial infrastructure for competing risks models
      5. -
    -
-
-

-Cyclops v2.0.2 2019-03-17 -

+
+
+

Cyclops v2.0.22019-03-17

Changes:

-
    -
  1. use RNGversion("3.5.0") in unit-tests to reproduce old RNG behavior
    2. +
    1. use RNGversion("3.5.0") in unit-tests to reproduce old RNG behavior
    2. fix prior-type checks when specifying multiple types
      3. -
    -
-
-

-Cyclops 2.0.1 2018-09-23 -

+
+
+

Cyclops 2.0.12018-09-23

Changes:

-
    -
  1. patch two memory leaks in ModelData.cpp and ModelSpecifics.hpp +
    1. patch two memory leaks in ModelData.cpp and ModelSpecifics.hpp
      2. -
    -
-
-

-Cyclops 2.0.0 2018-09-18 -

+
+
+

Cyclops 2.0.02018-09-18

Changes:

-
    -
  1. simplify internal transformation-reductions loops
    2. +
    1. simplify internal transformation-reductions loops
    2. implemented non-negative weights
    3. allow for run-time selection of 32-/64-bit reals
    4. remove dependence on GNUmake
    5. temporarily remove dependence on RcppParallel (until TBB is again R-compliant)
      6. -
    -
-
-

-Cyclops 1.3.4 2018-06-15 -

+
+
+

Cyclops 1.3.42018-06-15

Changes:

-
    -
  1. fix undeclared dependencies in unit-tests: MASS and microbenchmarks +
    1. fix undeclared dependencies in unit-tests: MASS and microbenchmarks
    2. fix issues with ATLAS compilation
    3. add contexts to testthat files
    4. fix ASAN errors in AbstractModelSpecifics
      5. -
    -
-
-

-Cyclops 1.3.3 Unreleased -

+
+
+

Cyclops 1.3.3

Changes:

-
    -
  1. fix testthat expected error message
    2. -
-
-
-

-Cyclops 1.3.2 2018-05-04 -

+
  1. fix testthat expected error message
    2. +
+
+

Cyclops 1.3.22018-05-04

Changes:

-
    -
  1. explicitly includes <complex> header, needed for R 3.5 builds
    2. +
    1. explicitly includes <complex> header, needed for R 3.5 builds
    2. remove pragma statements used to quiet RcppEigen and RcppParallel
      3. -
    -
-
-

-Cyclops 1.3.1 Unreleased -

+
+
+

Cyclops 1.3.1

Changes:

-
    -
  1. fixes covariate indices returned from .checkCovariates when excluding covariates from regularization
    2. -
-
-
-

-Cyclops 1.3.0 2017-08-23 -

+
  1. fixes covariate indices returned from .checkCovariates when excluding covariates from regularization
    2. +
+
+

Cyclops 1.3.02017-08-23

Changes:

-
    -
  1. implements specialized priors through callbacks for use, for example, in the BrokenAdaptiveRidge package to provide L0-based model selection
    2. +
    1. implements specialized priors through callbacks for use, for example, in the BrokenAdaptiveRidge package to provide L0-based model selection
    2. implements specialized control through callbacks for use, for example, auto-and-grid-based cross-validation hyperparameter searches
    3. removes src/boost that clashes with BH 1.65.0
      4. -
    -
-
-

-Cyclops 1.2.3 Unreleased -

+
+
+

Cyclops 1.2.3

Changes:

-
    -
  1. fixed predict error with ff.data.frame with size == 0
    2. -
-
-
-

-Cyclops 1.2.2 2016-10-06 -

+
  1. fixed predict error with ff.data.frame with size == 0
    2. +
+
+

Cyclops 1.2.22016-10-06

Changes:

-
    -
  1. fixed solaris build errors
    2. +
    1. fixed solaris build errors
    2. added compatibility for C++14 (make_unique)
    3. fixed multiple ASan warnings
      4. -
    -
-
-

-Cyclops 1.2.0 2016-08-01 -

+
+
+

Cyclops 1.2.02016-08-01

Changes: initial submission to CRAN

+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/pkgdown.css b/docs/pkgdown.css index 1273238d..80ea5b83 100644 --- a/docs/pkgdown.css +++ b/docs/pkgdown.css @@ -56,8 +56,10 @@ img.icon { float: right; } -img { +/* Ensure in-page images don't run outside their container */ +.contents img { max-width: 100%; + height: auto; } /* Fix bug in bootstrap (only seen in firefox) */ @@ -78,11 +80,10 @@ dd { /* Section anchors ---------------------------------*/ a.anchor { - margin-left: -30px; - display:inline-block; - width: 30px; - height: 30px; - visibility: hidden; + display: none; + margin-left: 5px; + width: 20px; + height: 20px; background-image: url(./link.svg); background-repeat: no-repeat; @@ -90,17 +91,15 @@ a.anchor { background-position: center center; } -.hasAnchor:hover a.anchor { - visibility: visible; -} - -@media (max-width: 767px) { - .hasAnchor:hover a.anchor { - visibility: hidden; - } +h1:hover .anchor, +h2:hover .anchor, +h3:hover .anchor, +h4:hover .anchor, +h5:hover .anchor, +h6:hover .anchor { + display: inline-block; } - /* Fixes for fixed navbar --------------------------*/ .contents h1, .contents h2, .contents h3, .contents h4 { @@ -264,31 +263,26 @@ table { /* Syntax highlighting ---------------------------------------------------- */ -pre { - word-wrap: normal; - word-break: normal; - border: 1px solid #eee; -} - -pre, code { +pre, code, pre code { background-color: #f8f8f8; color: #333; } +pre, pre code { + white-space: pre-wrap; + word-break: break-all; + overflow-wrap: break-word; +} -pre code { - overflow: auto; - word-wrap: normal; - white-space: pre; +pre { + border: 1px solid #eee; } -pre .img { +pre .img, pre .r-plt { margin: 5px 0; } -pre .img img { +pre .img img, pre .r-plt img { background-color: #fff; - display: block; - height: auto; } code a, pre a { @@ -305,9 +299,8 @@ a.sourceLine:hover { .kw {color: #264D66;} /* keyword */ .co {color: #888888;} /* comment */ -.message { color: black; font-weight: bolder;} -.error { color: orange; font-weight: bolder;} -.warning { color: #6A0366; font-weight: bolder;} +.error {font-weight: bolder;} +.warning {font-weight: bolder;} /* Clipboard --------------------------*/ @@ -365,3 +358,27 @@ mark { content: ""; } } + +/* Section anchors --------------------------------- + Added in pandoc 2.11: https://github.com/jgm/pandoc-templates/commit/9904bf71 +*/ + +div.csl-bib-body { } +div.csl-entry { + clear: both; +} +.hanging-indent div.csl-entry { + margin-left:2em; + text-indent:-2em; +} +div.csl-left-margin { + min-width:2em; + float:left; +} +div.csl-right-inline { + margin-left:2em; + padding-left:1em; +} +div.csl-indent { + margin-left: 2em; +} diff --git a/docs/pkgdown.js b/docs/pkgdown.js index 7e7048fa..6f0eee40 100644 --- a/docs/pkgdown.js +++ b/docs/pkgdown.js @@ -80,7 +80,7 @@ $(document).ready(function() { var copyButton = ""; - $(".examples, div.sourceCode").addClass("hasCopyButton"); + $("div.sourceCode").addClass("hasCopyButton"); // Insert copy buttons: $(copyButton).prependTo(".hasCopyButton"); @@ -91,7 +91,7 @@ // Initialize clipboard: var clipboardBtnCopies = new ClipboardJS('[data-clipboard-copy]', { text: function(trigger) { - return trigger.parentNode.textContent; + return trigger.parentNode.textContent.replace(/\n#>[^\n]*/g, ""); } }); diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml index 59d17566..d55408be 100644 --- a/docs/pkgdown.yml +++ b/docs/pkgdown.yml @@ -1,6 +1,6 @@ -pandoc: 2.7.3 -pkgdown: 1.6.1 +pandoc: 3.1.2 +pkgdown: 2.0.7 pkgdown_sha: ~ articles: {} -last_built: 2021-06-17T13:30Z +last_built: 2023-10-31T13:12Z diff --git a/docs/reference/Cyclops-package.html b/docs/reference/Cyclops-package.html new file mode 100644 index 00000000..3b8af50b --- /dev/null +++ b/docs/reference/Cyclops-package.html @@ -0,0 +1,105 @@ + +Cyclops: Cyclic Coordinate Descent for Logistic, Poisson and Survival Analysis — Cyclops-package • Cyclops + + +
+
+ + + +
+
+
+

Cyclops: Cyclic Coordinate Descent for Logistic, Poisson and Survival Analysis

+ Source: R/Cyclops-package.R + +
+ +
+

This model fitting tool incorporates cyclic coordinate descent and majorization-minimization approaches to fit a variety of regression models found in large-scale observational healthcare data. Implementations focus on computational optimization and fine-scale parallelization to yield efficient inference in massive datasets. Please see: Suchard, Simpson, Zorych, Ryan and Madigan (2013) doi:10.1145/2414416.2414791 +.

+
+ + +
+

See also

+

Useful links:

+
+
+

Author

+

Maintainer: Marc A. Suchard msuchard@ucla.edu

+

Authors:

  • Martijn J. Schuemie

    • +

  • Trevor R. Shaddox

    • +

  • Yuxi Tian

    • +

  • Jianxiao Yang

    • +

  • Eric Kawaguchi

    • +

Other contributors:

  • Sushil Mittal [contributor]

    • +

  • Observational Health Data Sciences and Informatics [copyright holder]

    • +

  • Marcus Geelnard (provided the TinyThread library) [copyright holder, contributor]

    • +

  • Rutgers University (provided the HParSearch routine) [copyright holder, contributor]

    • +

  • R Development Core Team (provided the ZeroIn routine) [copyright holder, contributor]

    • +
+ +
+ +
+ + +
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+ +
+

Site built with pkgdown 2.0.7.

+
+ +
+ + + + + + + + diff --git a/docs/reference/Multitype.html b/docs/reference/Multitype.html index b8b4b67c..86d50ed9 100644 --- a/docs/reference/Multitype.html +++ b/docs/reference/Multitype.html @@ -1,68 +1,13 @@ - - - - - - - -Create a multitype outcome object — Multitype • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Create a multitype outcome object — Multitype • Cyclops - + + - - - -
-
- -
- -
+

Create a multitype outcome object

- Source: R/Multitype.R + Source: R/Multitype.R
-

Multitype creates a multitype outcome object, usually used as a response variable in a +

Multitype creates a multitype outcome object, usually used as a response variable in a hierarchical Cyclops model fit.

- 
Multitype(y, type)
- -

Arguments

- - - - - - - - - - -
y

Numeric: Response count(s)

type

Numeric or factor: Response type

- -

Value

- -

An object of class Multitype with length equal to the length of y and type.

- -

Examples

- 
Multitype(c(0,1,0), as.factor(c("A","A","B")))
-
#>      y type
-#> [1,] 0    1
-#> [2,] 1    1
-#> [3,] 0    2
-#> attr(,"contrasts")
-#>   B
-#> A 0
-#> B 1
-#> attr(,"class")
-#> [1] "Multitype"

-
+
+ 
Multitype(y, type)
+
+ +
+

Arguments

+
y
+

Numeric: Response count(s)

+ + +
type
+

Numeric or factor: Response type

+ +
+
+

Value

+ + +

An object of class Multitype with length equal to the length of y and type.

+
+ +
+

Examples

+ 
Multitype(c(0,1,0), as.factor(c("A","A","B")))
+#>      y type
+#> [1,] 0    1
+#> [2,] 1    1
+#> [3,] 0    2
+#> attr(,"contrasts")
+#>   B
+#> A 0
+#> B 1
+#> attr(,"class")
+#> [1] "Multitype"
+
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/aconfint.html b/docs/reference/aconfint.html index fbb958fd..7f543f57 100644 --- a/docs/reference/aconfint.html +++ b/docs/reference/aconfint.html @@ -1,68 +1,13 @@ - - - - - - - -Asymptotic confidence intervals for a fitted Cyclops model object — aconfint • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Asymptotic confidence intervals for a fitted Cyclops model object — aconfint • Cyclops - - + + - - -
-
- -
- -
+

Asymptotic confidence intervals for a fitted Cyclops model object

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -125,76 +57,74 @@

Asymptotic confidence intervals for a fitted Cyclops model object

arbitrary level using asymptotic standard error estimates.

- 
aconfint(
-  object,
-  parm,
-  level = 0.95,
-  control,
-  overrideNoRegularization = FALSE,
-  ...
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - -
object

A fitted Cyclops model object

parm

A specification of which parameters require confidence intervals, -either a vector of numbers of covariateId names

level

Numeric: confidence level required

control

A "cyclopsControl" object constructed by createControl

overrideNoRegularization

Logical: Enable confidence interval estimation for regularized parameters

...

Additional argument(s) for methods

- -

Value

- -

A matrix with columns reporting lower and upper confidence limits for each parameter. -These columns are labelled as (1-level) / 2 and 1 - (1 - level) / 2 in -(by default 2.5

+
+ 
aconfint(
+  object,
+  parm,
+  level = 0.95,
+  control,
+  overrideNoRegularization = FALSE,
+  ...
+)
+
+ +
+

Arguments

+
object
+

A fitted Cyclops model object

+ + +
parm
+

A specification of which parameters require confidence intervals, +either a vector of numbers of covariateId names

+ + +
level
+

Numeric: confidence level required

+ + +
control
+

A "cyclopsControl" object constructed by createControl

+ + +
overrideNoRegularization
+

Logical: Enable confidence interval estimation for regularized parameters

+ + +
...
+

Additional argument(s) for methods

+ +
+
+

Value

+ + +

A matrix with columns reporting lower and upper confidence limits for each parameter. +These columns are labelled as (1-level) / 2 and 1 - (1 - level) / 2 in % +(by default 2.5% and 97.5%)

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/appendSqlCyclopsData.html b/docs/reference/appendSqlCyclopsData.html index 6fd73d40..9d2087dc 100644 --- a/docs/reference/appendSqlCyclopsData.html +++ b/docs/reference/appendSqlCyclopsData.html @@ -1,67 +1,12 @@ - - - - - - - -appendSqlCyclopsData — appendSqlCyclopsData • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -appendSqlCyclopsData — appendSqlCyclopsData • Cyclops - - + + - - -
-
- -
- -
+

appendSqlCyclopsData

- Source: R/DataManagement.R + Source: R/DataManagement.R
@@ -123,85 +55,81 @@

appendSqlCyclopsData

appendSqlCyclopsData appends data to an OHDSI data object.

- 
appendSqlCyclopsData(
-  object,
-  oStratumId,
-  oRowId,
-  oY,
-  oTime,
-  cRowId,
-  cCovariateId,
-  cCovariateValue
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
object

OHDSI Cyclops data object to append entries

oStratumId

Integer vector (optional): non-unique stratum identifier for each row in outcomes table

oRowId

Integer vector: unique row identifier for each row in outcomes table

oY

Numeric vector: model outcome variable for each row in outcomes table

oTime

Numeric vector (optional): exposure interval or censoring time for each row in outcomes table

cRowId

Integer vector: non-unique row identifier for each row in covariates table that matches a single outcomes table entry

cCovariateId

Integer vector: covariate identifier

cCovariateValue

Numeric vector: covariate value

- -

Details

+
+ 
appendSqlCyclopsData(
+  object,
+  oStratumId,
+  oRowId,
+  oY,
+  oTime,
+  cRowId,
+  cCovariateId,
+  cCovariateValue
+)
+
+ +
+

Arguments

+
object
+

OHDSI Cyclops data object to append entries

+ + +
oStratumId
+

Integer vector (optional): non-unique stratum identifier for each row in outcomes table

+ + +
oRowId
+

Integer vector: unique row identifier for each row in outcomes table

+ + +
oY
+

Numeric vector: model outcome variable for each row in outcomes table

+ +
oTime
+

Numeric vector (optional): exposure interval or censoring time for each row in outcomes table

+ + +
cRowId
+

Integer vector: non-unique row identifier for each row in covariates table that matches a single outcomes table entry

+ + +
cCovariateId
+

Integer vector: covariate identifier

+ + +
cCovariateValue
+

Numeric vector: covariate value

+ +
+
+

Details

Append data using two tables. The outcomes table is dense and contains ... The covariates table is sparse and contains ... -All entries in the outcome table must be sorted in increasing order by oStratumId, oRowId. All entries in the covariate table -must be sorted in increasing order by cRowId. Each cRowId value must match exactly one oRowId value.

+All entries in the outcome table must be sorted in increasing order by (oStratumId, oRowId). All entries in the covariate table +must be sorted in increasing order by (cRowId). Each cRowId value must match exactly one oRowId value.

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/coef.cyclopsFit.html b/docs/reference/coef.cyclopsFit.html index db4428d2..4b2cabbe 100644 --- a/docs/reference/coef.cyclopsFit.html +++ b/docs/reference/coef.cyclopsFit.html @@ -1,67 +1,12 @@ - - - - - - - -Extract model coefficients — coef.cyclopsFit • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Extract model coefficients — coef.cyclopsFit • Cyclops - - + + - - -
-
- -
- -
+

Extract model coefficients

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -123,59 +55,57 @@

Extract model coefficients

coef.cyclopsFit extracts model coefficients from an Cyclops model fit object

- 
# S3 method for cyclopsFit
-coef(object, rescale = FALSE, ignoreConvergence = FALSE, ...)
- -

Arguments

- - - - - - - - - - - - - - - - - - -
object

Cyclops model fit object

rescale

Boolean: rescale coefficients for unnormalized covariate values

ignoreConvergence

Boolean: return coefficients even if fit object did not converge

...

Other arguments

- -

Value

- -

Named numeric vector of model coefficients.

+
+ 
# S3 method for cyclopsFit
+coef(object, rescale = FALSE, ignoreConvergence = FALSE, ...)
+
+ +
+

Arguments

+
object
+

Cyclops model fit object

+ + +
rescale
+

Boolean: rescale coefficients for unnormalized covariate values

+ + +
ignoreConvergence
+

Boolean: return coefficients even if fit object did not converge

+ + +
...
+

Other arguments

+ +
+
+

Value

+ + +

Named numeric vector of model coefficients.

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/confint.cyclopsFit.html b/docs/reference/confint.cyclopsFit.html index 03191154..9cccd20d 100644 --- a/docs/reference/confint.cyclopsFit.html +++ b/docs/reference/confint.cyclopsFit.html @@ -1,68 +1,13 @@ - - - - - - - -Confidence intervals for Cyclops model parameters — confint.cyclopsFit • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Confidence intervals for Cyclops model parameters — confint.cyclopsFit • Cyclops - - + + - - -
-
- -
- -
+

Confidence intervals for Cyclops model parameters

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -125,204 +57,688 @@

Confidence intervals for Cyclops model parameters

arbitrary level. Usually it only makes sense to do this for variables that have not been regularized.

- 
# S3 method for cyclopsFit
-confint(
-  object,
-  parm,
-  level = 0.95,
-  overrideNoRegularization = FALSE,
-  includePenalty = TRUE,
-  rescale = FALSE,
-  ...
-)
+
+ 
# S3 method for cyclopsFit
+confint(
+  object,
+  parm,
+  level = 0.95,
+  overrideNoRegularization = FALSE,
+  includePenalty = TRUE,
+  rescale = FALSE,
+  ...
+)
+
+ +
+

Arguments

+
object
+

A fitted Cyclops model object

+ + +
parm
+

A specification of which parameters require confidence intervals, +either a vector of numbers of covariateId names

+ + +
level
+

Numeric: confidence level required

+ -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
object

A fitted Cyclops model object

parm

A specification of which parameters require confidence intervals, -either a vector of numbers of covariateId names

level

Numeric: confidence level required

overrideNoRegularization

Logical: Enable confidence interval estimation for regularized parameters

includePenalty

Logical: Include regularized covariate penalty in profile

rescale

Boolean: rescale coefficients for unnormalized covariate values

...

Additional argument(s) for methods

+
overrideNoRegularization
+

Logical: Enable confidence interval estimation for regularized parameters

-

Value

-

A matrix with columns reporting lower and upper confidence limits for each parameter. +

includePenalty
+

Logical: Include regularized covariate penalty in profile

+ + +
rescale
+

Boolean: rescale coefficients for unnormalized covariate values

+ + +
...
+

Additional argument(s) for methods

+ +
+
+

Value

+ + +

A matrix with columns reporting lower and upper confidence limits for each parameter. These columns are labelled as (1-level) / 2 and 1 - (1 - level) / 2 in percent (by default 2.5 percent and 97.5 percent)

+
-

Examples

- 
#Generate some simulated data:
-sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
-                           model = "poisson")
-
#> Sparseness = 74.45 %
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
-                                    addIntercept = TRUE)
-
#> Sorting covariates by covariateId and rowId

-#Define the prior and control objects to use cross-validation for finding the 
-#optimal hyperparameter:
-prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
-control <- createControl(cvType = "auto", noiseLevel = "quiet")
-
-#Fit the model
-fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
-
#> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1623936644] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
-#> Using 1 thread(s)
-#> Starting var = 0.2555 (default)
-#> Running at Laplace(2.79782) None  Grid-point #1 at 0.2555 	Fold #1 Rep #1 pred log like = 375.98
-#> Running at Laplace(2.79782) None  Grid-point #1 at 0.2555 	Fold #2 Rep #1 pred log like = 358.921
-#> Running at Laplace(2.79782) None  Grid-point #1 at 0.2555 	Fold #3 Rep #1 pred log like = 402.461
-#> Running at Laplace(2.79782) None  Grid-point #1 at 0.2555 	Fold #4 Rep #1 pred log like = 224.91
-#> Running at Laplace(2.79782) None  Grid-point #1 at 0.2555 	Fold #5 Rep #1 pred log like = 416.062
-#> Running at Laplace(2.79782) None  Grid-point #1 at 0.2555 	Fold #6 Rep #1 pred log like = 381.177
-#> Running at Laplace(2.79782) None  Grid-point #1 at 0.2555 	Fold #7 Rep #1 pred log like = 410.934
-#> Running at Laplace(2.79782) None  Grid-point #1 at 0.2555 	Fold #8 Rep #1 pred log like = 363.449
-#> Running at Laplace(2.79782) None  Grid-point #1 at 0.2555 	Fold #9 Rep #1 pred log like = 380.333
-#> Running at Laplace(2.79782) None  Grid-point #1 at 0.2555 	Fold #10 Rep #1 pred log like = 355.956
-#> AvgPred = 367.018 with stdev = 51.4233
-#> Completed at 0.2555
-#> Next point at 2.555 with value 0 and continue = 1
-#> search[ 0.2555 ] = 367.018(51.4233)
-#> 
-#> Running at Laplace(0.884748) None  Grid-point #2 at 2.555 	Fold #1 Rep #1 pred log like = 375.99
-#> Running at Laplace(0.884748) None  Grid-point #2 at 2.555 	Fold #2 Rep #1 pred log like = 358.892
-#> Running at Laplace(0.884748) None  Grid-point #2 at 2.555 	Fold #3 Rep #1 pred log like = 402.439
-#> Running at Laplace(0.884748) None  Grid-point #2 at 2.555 	Fold #4 Rep #1 pred log like = 224.885
-#> Running at Laplace(0.884748) None  Grid-point #2 at 2.555 	Fold #5 Rep #1 pred log like = 416.043
-#> Running at Laplace(0.884748) None  Grid-point #2 at 2.555 	Fold #6 Rep #1 pred log like = 381.179
-#> Running at Laplace(0.884748) None  Grid-point #2 at 2.555 	Fold #7 Rep #1 pred log like = 410.904
-#> Running at Laplace(0.884748) None  Grid-point #2 at 2.555 	Fold #8 Rep #1 pred log like = 363.425
-#> Running at Laplace(0.884748) None  Grid-point #2 at 2.555 	Fold #9 Rep #1 pred log like = 380.301
-#> Running at Laplace(0.884748) None  Grid-point #2 at 2.555 	Fold #10 Rep #1 pred log like = 355.924
-#> AvgPred = 366.998 with stdev = 51.4251
-#> Completed at 2.555
-#> Next point at 0.02555 with value 0 and continue = 1
-#> search[ 0.2555 ] = 367.018(51.4233)
-#> search[ 2.555 ] = 366.998(51.4251)
-#> 
-#> Running at Laplace(8.84748) None  Grid-point #3 at 0.02555 	Fold #1 Rep #1 pred log like = 375.97
-#> Running at Laplace(8.84748) None  Grid-point #3 at 0.02555 	Fold #2 Rep #1 pred log like = 358.995
-#> Running at Laplace(8.84748) None  Grid-point #3 at 0.02555 	Fold #3 Rep #1 pred log like = 402.483
-#> Running at Laplace(8.84748) None  Grid-point #3 at 0.02555 	Fold #4 Rep #1 pred log like = 224.985
-#> Running at Laplace(8.84748) None  Grid-point #3 at 0.02555 	Fold #5 Rep #1 pred log like = 416.12
-#> Running at Laplace(8.84748) None  Grid-point #3 at 0.02555 	Fold #6 Rep #1 pred log like = 381.169
-#> Running at Laplace(8.84748) None  Grid-point #3 at 0.02555 	Fold #7 Rep #1 pred log like = 411.069
-#> Running at Laplace(8.84748) None  Grid-point #3 at 0.02555 	Fold #8 Rep #1 pred log like = 363.513
-#> Running at Laplace(8.84748) None  Grid-point #3 at 0.02555 	Fold #9 Rep #1 pred log like = 380.385
-#> Running at Laplace(8.84748) None  Grid-point #3 at 0.02555 	Fold #10 Rep #1 pred log like = 356.053
-#> AvgPred = 367.074 with stdev = 51.4186
-#> Completed at 0.02555
-#> Next point at 0.002555 with value 0 and continue = 1
-#> search[ 0.02555 ] = 367.074(51.4186)
-#> search[ 0.2555 ] = 367.018(51.4233)
-#> search[ 2.555 ] = 366.998(51.4251)
-#> 
-#> Running at Laplace(27.9782) None  Grid-point #4 at 0.002555 	Fold #1 Rep #1 pred log like = 375.97
-#> Running at Laplace(27.9782) None  Grid-point #4 at 0.002555 	Fold #2 Rep #1 pred log like = 359.05
-#> Running at Laplace(27.9782) None  Grid-point #4 at 0.002555 	Fold #3 Rep #1 pred log like = 402.485
-#> Running at Laplace(27.9782) None  Grid-point #4 at 0.002555 	Fold #4 Rep #1 pred log like = 225.084
-#> Running at Laplace(27.9782) None  Grid-point #4 at 0.002555 	Fold #5 Rep #1 pred log like = 416.178
-#> Running at Laplace(27.9782) None  Grid-point #4 at 0.002555 	Fold #6 Rep #1 pred log like = 381.169
-#> Running at Laplace(27.9782) None  Grid-point #4 at 0.002555 	Fold #7 Rep #1 pred log like = 411.373
-#> Running at Laplace(27.9782) None  Grid-point #4 at 0.002555 	Fold #8 Rep #1 pred log like = 363.543
-#> Running at Laplace(27.9782) None  Grid-point #4 at 0.002555 	Fold #9 Rep #1 pred log like = 380.399
-#> Running at Laplace(27.9782) None  Grid-point #4 at 0.002555 	Fold #10 Rep #1 pred log like = 356.206
-#> AvgPred = 367.146 with stdev = 51.4189
-#> Completed at 0.002555
-#> Next point at 0.0002555 with value 0 and continue = 1
-#> search[ 0.002555 ] = 367.146(51.4189)
-#> search[ 0.02555 ] = 367.074(51.4186)
-#> search[ 0.2555 ] = 367.018(51.4233)
-#> search[ 2.555 ] = 366.998(51.4251)
-#> 
-#> Running at Laplace(88.4748) None  Grid-point #5 at 0.0002555 	Fold #1 Rep #1 pred log like = 375.97
-#> Running at Laplace(88.4748) None  Grid-point #5 at 0.0002555 	Fold #2 Rep #1 pred log like = 359.05
-#> Running at Laplace(88.4748) None  Grid-point #5 at 0.0002555 	Fold #3 Rep #1 pred log like = 402.485
-#> Running at Laplace(88.4748) None  Grid-point #5 at 0.0002555 	Fold #4 Rep #1 pred log like = 225.084
-#> Running at Laplace(88.4748) None  Grid-point #5 at 0.0002555 	Fold #5 Rep #1 pred log like = 416.178
-#> Running at Laplace(88.4748) None  Grid-point #5 at 0.0002555 	Fold #6 Rep #1 pred log like = 381.169
-#> Running at Laplace(88.4748) None  Grid-point #5 at 0.0002555 	Fold #7 Rep #1 pred log like = 411.373
-#> Running at Laplace(88.4748) None  Grid-point #5 at 0.0002555 	Fold #8 Rep #1 pred log like = 363.543
-#> Running at Laplace(88.4748) None  Grid-point #5 at 0.0002555 	Fold #9 Rep #1 pred log like = 380.399
-#> Running at Laplace(88.4748) None  Grid-point #5 at 0.0002555 	Fold #10 Rep #1 pred log like = 356.206
-#> AvgPred = 367.146 with stdev = 51.4189
-#> Completed at 0.0002555
-#> Next point at 2.16648e-14 with value 367.335 and continue = 0
-#> search[ 0.0002555 ] = 367.146(51.4189)
-#> search[ 0.002555 ] = 367.146(51.4189)
-#> search[ 0.02555 ] = 367.074(51.4186)
-#> search[ 0.2555 ] = 367.018(51.4233)
-#> search[ 2.555 ] = 366.998(51.4251)
-#> 
-#> 
-#> Maximum predicted log likelihood (367.335) estimated at:
-#> 	2.16648e-14 (variance)
-#> 	9.6081e+06 (lambda)
-#> 
-#> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(9.6081e+06) None 

-#Find out what the optimal hyperparameter was:
-getHyperParameter(fit)
-
#> [1] 2.166483e-14

-#Extract the current log-likelihood, and coefficients
-logLik(fit)
-
#> 'log Lik.' -1973.343 (df=3)
coef(fit)
-
#> (Intercept)           1           2 
-#>   -3.937029    0.000000    0.000000 

-#We can only retrieve the confidence interval for unregularized coefficients:
-confint(fit, c(0))
-
#> Using 1 thread(s)
#>      covariate     2.5 %    97.5 % evaluations
-#> [1,]         0 -3.965463 -3.908849          24
+
+

Examples

+ 
#Generate some simulated data:
+sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
+                           model = "poisson")
+#> Sparseness = 77 %
+cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
+                                    addIntercept = TRUE)
+#> Sorting covariates by covariateId and rowId
+
+#Define the prior and control objects to use cross-validation for finding the 
+#optimal hyperparameter:
+prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
+control <- createControl(cvType = "auto", noiseLevel = "quiet")
+
+#Fit the model
+fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
+#> Using cross-validation selector type byRow
+#> Performing 10-fold cross-validation [seed = 1698757931] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Using 1 thread(s)
+#> Starting var = 0.23 (default)
+#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #1 Rep #1 pred log like = 267.858
+#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #2 Rep #1 pred log like = 210.218
+#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #3 Rep #1 pred log like = 247.642
+#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #4 Rep #1 pred log like = 268.625
+#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #5 Rep #1 pred log like = 234.92
+#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #6 Rep #1 pred log like = 256.935
+#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #7 Rep #1 pred log like = 237.206
+#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #8 Rep #1 pred log like = 203.575
+#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #9 Rep #1 pred log like = 268.979
+#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #10 Rep #1 pred log like = 313.499
+#> AvgPred = 250.946 with stdev = 30.3841
+#> Completed at 0.23
+#> Next point at 2.3 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> 
+#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #1 Rep #1 pred log like = 267.817
+#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #2 Rep #1 pred log like = 210.18
+#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #3 Rep #1 pred log like = 247.667
+#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #4 Rep #1 pred log like = 268.65
+#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #5 Rep #1 pred log like = 234.965
+#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #6 Rep #1 pred log like = 256.945
+#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #7 Rep #1 pred log like = 237.151
+#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #8 Rep #1 pred log like = 203.606
+#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #9 Rep #1 pred log like = 268.987
+#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #10 Rep #1 pred log like = 313.505
+#> AvgPred = 250.947 with stdev = 30.3849
+#> Completed at 2.3
+#> Next point at 23 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> 
+#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #1 Rep #1 pred log like = 267.803
+#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #2 Rep #1 pred log like = 210.168
+#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #3 Rep #1 pred log like = 247.674
+#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #4 Rep #1 pred log like = 268.657
+#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #5 Rep #1 pred log like = 234.98
+#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #6 Rep #1 pred log like = 256.948
+#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #7 Rep #1 pred log like = 237.134
+#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #8 Rep #1 pred log like = 203.616
+#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #9 Rep #1 pred log like = 268.988
+#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #10 Rep #1 pred log like = 313.506
+#> AvgPred = 250.947 with stdev = 30.3852
+#> Completed at 23
+#> Next point at 230 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> 
+#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #1 Rep #1 pred log like = 267.799
+#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #2 Rep #1 pred log like = 210.165
+#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #3 Rep #1 pred log like = 247.677
+#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #4 Rep #1 pred log like = 268.66
+#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #5 Rep #1 pred log like = 234.984
+#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #6 Rep #1 pred log like = 256.948
+#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #7 Rep #1 pred log like = 237.128
+#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #8 Rep #1 pred log like = 203.619
+#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 230
+#> Next point at 2300 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #1 Rep #1 pred log like = 267.798
+#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #4 Rep #1 pred log like = 268.66
+#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #5 Rep #1 pred log like = 234.985
+#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #7 Rep #1 pred log like = 237.126
+#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2300
+#> Next point at 23000 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #7 Rep #1 pred log like = 237.126
+#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 23000
+#> Next point at 230000 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #7 Rep #1 pred log like = 237.126
+#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 230000
+#> Next point at 2.3e+06 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+06
+#> Next point at 2.3e+07 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+07
+#> Next point at 2.3e+08 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+08
+#> Next point at 2.3e+09 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+09
+#> Next point at 2.3e+10 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+10
+#> Next point at 2.3e+11 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> search[ 2.3e+10 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+11
+#> Next point at 2.3e+12 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> search[ 2.3e+10 ] = 250.948(30.3853)
+#> search[ 2.3e+11 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+12
+#> Next point at 2.3e+13 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> search[ 2.3e+10 ] = 250.948(30.3853)
+#> search[ 2.3e+11 ] = 250.948(30.3853)
+#> search[ 2.3e+12 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+13
+#> Next point at 2.3e+14 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> search[ 2.3e+10 ] = 250.948(30.3853)
+#> search[ 2.3e+11 ] = 250.948(30.3853)
+#> search[ 2.3e+12 ] = 250.948(30.3853)
+#> search[ 2.3e+13 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+14
+#> Next point at 2.3e+15 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> search[ 2.3e+10 ] = 250.948(30.3853)
+#> search[ 2.3e+11 ] = 250.948(30.3853)
+#> search[ 2.3e+12 ] = 250.948(30.3853)
+#> search[ 2.3e+13 ] = 250.948(30.3853)
+#> search[ 2.3e+14 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+15
+#> Next point at 2.3e+16 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> search[ 2.3e+10 ] = 250.948(30.3853)
+#> search[ 2.3e+11 ] = 250.948(30.3853)
+#> search[ 2.3e+12 ] = 250.948(30.3853)
+#> search[ 2.3e+13 ] = 250.948(30.3853)
+#> search[ 2.3e+14 ] = 250.948(30.3853)
+#> search[ 2.3e+15 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+16
+#> Next point at 2.3e+17 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> search[ 2.3e+10 ] = 250.948(30.3853)
+#> search[ 2.3e+11 ] = 250.948(30.3853)
+#> search[ 2.3e+12 ] = 250.948(30.3853)
+#> search[ 2.3e+13 ] = 250.948(30.3853)
+#> search[ 2.3e+14 ] = 250.948(30.3853)
+#> search[ 2.3e+15 ] = 250.948(30.3853)
+#> search[ 2.3e+16 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+17
+#> Next point at 2.3e+18 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> search[ 2.3e+10 ] = 250.948(30.3853)
+#> search[ 2.3e+11 ] = 250.948(30.3853)
+#> search[ 2.3e+12 ] = 250.948(30.3853)
+#> search[ 2.3e+13 ] = 250.948(30.3853)
+#> search[ 2.3e+14 ] = 250.948(30.3853)
+#> search[ 2.3e+15 ] = 250.948(30.3853)
+#> search[ 2.3e+16 ] = 250.948(30.3853)
+#> search[ 2.3e+17 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+18
+#> Next point at 2.3e+19 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> search[ 2.3e+10 ] = 250.948(30.3853)
+#> search[ 2.3e+11 ] = 250.948(30.3853)
+#> search[ 2.3e+12 ] = 250.948(30.3853)
+#> search[ 2.3e+13 ] = 250.948(30.3853)
+#> search[ 2.3e+14 ] = 250.948(30.3853)
+#> search[ 2.3e+15 ] = 250.948(30.3853)
+#> search[ 2.3e+16 ] = 250.948(30.3853)
+#> search[ 2.3e+17 ] = 250.948(30.3853)
+#> search[ 2.3e+18 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+19
+#> Next point at 2.3e+20 with value 0 and continue = 1
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> search[ 2.3e+10 ] = 250.948(30.3853)
+#> search[ 2.3e+11 ] = 250.948(30.3853)
+#> search[ 2.3e+12 ] = 250.948(30.3853)
+#> search[ 2.3e+13 ] = 250.948(30.3853)
+#> search[ 2.3e+14 ] = 250.948(30.3853)
+#> search[ 2.3e+15 ] = 250.948(30.3853)
+#> search[ 2.3e+16 ] = 250.948(30.3853)
+#> search[ 2.3e+17 ] = 250.948(30.3853)
+#> search[ 2.3e+18 ] = 250.948(30.3853)
+#> search[ 2.3e+19 ] = 250.948(30.3853)
+#> 
+#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #1 Rep #1 pred log like = 267.797
+#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #2 Rep #1 pred log like = 210.163
+#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #3 Rep #1 pred log like = 247.678
+#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #4 Rep #1 pred log like = 268.661
+#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #5 Rep #1 pred log like = 234.986
+#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #6 Rep #1 pred log like = 256.949
+#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #7 Rep #1 pred log like = 237.125
+#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #8 Rep #1 pred log like = 203.62
+#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #9 Rep #1 pred log like = 268.989
+#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #10 Rep #1 pred log like = 313.507
+#> AvgPred = 250.948 with stdev = 30.3853
+#> Completed at 2.3e+20
+#> Next point at 2.41831e+12 with value 250.948 and continue = 0
+#> search[ 0.23 ] = 250.946(30.3841)
+#> search[ 2.3 ] = 250.947(30.3849)
+#> search[ 23 ] = 250.947(30.3852)
+#> search[ 230 ] = 250.948(30.3853)
+#> search[ 2300 ] = 250.948(30.3853)
+#> search[ 23000 ] = 250.948(30.3853)
+#> search[ 230000 ] = 250.948(30.3853)
+#> search[ 2.3e+06 ] = 250.948(30.3853)
+#> search[ 2.3e+07 ] = 250.948(30.3853)
+#> search[ 2.3e+08 ] = 250.948(30.3853)
+#> search[ 2.3e+09 ] = 250.948(30.3853)
+#> search[ 2.3e+10 ] = 250.948(30.3853)
+#> search[ 2.3e+11 ] = 250.948(30.3853)
+#> search[ 2.3e+12 ] = 250.948(30.3853)
+#> search[ 2.3e+13 ] = 250.948(30.3853)
+#> search[ 2.3e+14 ] = 250.948(30.3853)
+#> search[ 2.3e+15 ] = 250.948(30.3853)
+#> search[ 2.3e+16 ] = 250.948(30.3853)
+#> search[ 2.3e+17 ] = 250.948(30.3853)
+#> search[ 2.3e+18 ] = 250.948(30.3853)
+#> search[ 2.3e+19 ] = 250.948(30.3853)
+#> search[ 2.3e+20 ] = 250.948(30.3853)
+#> 
+#> 
+#> Maximum predicted log likelihood (250.948) estimated at:
+#> 	2.41831e+12 (variance)
+#> 	9.09409e-07 (lambda)
+#> 
+#> Fitting model at optimal hyperparameter
+#> Using prior: Laplace(9.09409e-07) None 
+
+#Find out what the optimal hyperparameter was:
+getHyperParameter(fit)
+#> [1] 2.418308e+12
+
+#Extract the current log-likelihood, and coefficients
+logLik(fit)
+#> 'log Lik.' -1953.765 (df=3)
+coef(fit)
+#> (Intercept)           1           2 
+#> -4.19783727  0.30746087  0.02797239 
+
+#We can only retrieve the confidence interval for unregularized coefficients:
+confint(fit, c(0))
+#> Using 1 thread(s)
+#>             covariate     2.5 %    97.5 % evaluations
+#> (Intercept)         0 -4.236526 -4.159602          22
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/convertToCyclopsData.html b/docs/reference/convertToCyclopsData.html index a9d7f04e..b74b9d80 100644 --- a/docs/reference/convertToCyclopsData.html +++ b/docs/reference/convertToCyclopsData.html @@ -1,67 +1,12 @@ - - - - - - - -Convert data from two data frames or ffdf objects into a CyclopsData object — convertToCyclopsData • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Convert data from two data frames or ffdf objects into a CyclopsData object — convertToCyclopsData • Cyclops - - - - + + -
-
- -
- -
+

Convert data from two data frames or ffdf objects into a CyclopsData object

- Source: R/NewDataConversion.R + Source: R/NewDataConversion.R
@@ -123,163 +55,145 @@

Convert data from two data frames or ffdf objects into a CyclopsData object<

convertToCyclopsData loads data from two data frames or ffdf objects, and inserts it into a Cyclops data object.

- 
convertToCyclopsData(
-  outcomes,
-  covariates,
-  modelType = "lr",
-  addIntercept = TRUE,
-  checkSorting = NULL,
-  checkRowIds = TRUE,
-  normalize = NULL,
-  quiet = FALSE,
-  floatingPoint = 64
-)
-
-# S3 method for data.frame
-convertToCyclopsData(
-  outcomes,
-  covariates,
-  modelType = "lr",
-  addIntercept = TRUE,
-  checkSorting = NULL,
-  checkRowIds = TRUE,
-  normalize = NULL,
-  quiet = FALSE,
-  floatingPoint = 64
-)
-
-# S3 method for tbl_dbi
-convertToCyclopsData(
-  outcomes,
-  covariates,
-  modelType = "lr",
-  addIntercept = TRUE,
-  checkSorting = NULL,
-  checkRowIds = TRUE,
-  normalize = NULL,
-  quiet = FALSE,
-  floatingPoint = 64
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
outcomes

A data frame or ffdf object containing the outcomes with predefined columns (see below).

covariates

A data frame or ffdf object containing the covariates with predefined columns (see below).

modelType

Cyclops model type. Current supported types are "pr", "cpr", lr", "clr", or "cox"

addIntercept

Add an intercept to the model?

checkSorting

(DEPRECATED) Check if the data are sorted appropriately, and if not, sort.

checkRowIds

Check if all rowIds in the covariates appear in the outcomes.

normalize

String: Name of normalization for all non-indicator covariates (possible values: stdev, max, median)

quiet

If true, (warning) messages are suppressed.

floatingPoint

Specified floating-point representation size (32 or 64)

- -

Value

- -

An object of type cyclopsData

-

Details

- -

These columns are expected in the outcome object:

- - - - - - - -
stratumId(integer)(optional) Stratum ID for conditional regression models
rowId(integer)Row ID is used to link multiple covariates (x) to a single outcome (y)
y(real)The outcome variable
time(real)For models that use time (e.g. Poisson or Cox regression) this contains time
(e.g. number of days)
weights(real)(optional) Non-negative weights to apply to outcome
censorWeights(real)(optional) Non-negative censoring weights for competing risk model; will be computed if not provided.
- - -

These columns are expected in the covariates object:

- - - - -
stratumId(integer)(optional) Stratum ID for conditional regression models
rowId(integer)Row ID is used to link multiple covariates (x) to a single outcome (y)
covariateId(integer)A numeric identifier of a covariate
covariateValue(real)The value of the specified covariate
- - -

Methods (by class)

+
+ 
convertToCyclopsData(
+  outcomes,
+  covariates,
+  modelType = "lr",
+  addIntercept = TRUE,
+  checkSorting = NULL,
+  checkRowIds = TRUE,
+  normalize = NULL,
+  quiet = FALSE,
+  floatingPoint = 64
+)
+
+# S3 method for data.frame
+convertToCyclopsData(
+  outcomes,
+  covariates,
+  modelType = "lr",
+  addIntercept = TRUE,
+  checkSorting = NULL,
+  checkRowIds = TRUE,
+  normalize = NULL,
+  quiet = FALSE,
+  floatingPoint = 64
+)
+
+# S3 method for tbl_dbi
+convertToCyclopsData(
+  outcomes,
+  covariates,
+  modelType = "lr",
+  addIntercept = TRUE,
+  checkSorting = NULL,
+  checkRowIds = TRUE,
+  normalize = NULL,
+  quiet = FALSE,
+  floatingPoint = 64
+)
+
+ +
+

Arguments

+
outcomes
+

A data frame or ffdf object containing the outcomes with predefined columns (see below).

+ + +
covariates
+

A data frame or ffdf object containing the covariates with predefined columns (see below).

+ + +
modelType
+

Cyclops model type. Current supported types are "pr", "cpr", lr", "clr", or "cox"

+ + +
addIntercept
+

Add an intercept to the model?

+ + +
checkSorting
+

(DEPRECATED) Check if the data are sorted appropriately, and if not, sort.

+ +
checkRowIds
+

Check if all rowIds in the covariates appear in the outcomes.

+ + +
normalize
+

String: Name of normalization for all non-indicator covariates (possible values: stdev, max, median)

+ + +
quiet
+

If true, (warning) messages are suppressed.

+ + +
floatingPoint
+

Specified floating-point representation size (32 or 64)

+ +
+
+

Value

-
    -

  • data.frame: Convert data from two data.frame

    • -

  • tbl_dbi: Convert data from two Andromeda tables

    • -
- -

Examples

- 
#Convert infert dataset to Cyclops format:
-covariates <- data.frame(stratumId = rep(infert$stratum, 2),
-                         rowId = rep(1:nrow(infert), 2),
-                         covariateId = rep(1:2, each = nrow(infert)),
-                         covariateValue = c(infert$spontaneous, infert$induced))
-outcomes <- data.frame(stratumId = infert$stratum,
-                       rowId = 1:nrow(infert),
-                       y = infert$case)
-#Make sparse:
-covariates <- covariates[covariates$covariateValue != 0, ]
-
-#Create Cyclops data object:
-cyclopsData <- convertToCyclopsData(outcomes, covariates, modelType = "clr",
-                                    addIntercept = FALSE)
-
#> Sorting outcomes by stratumId and rowId
-#> Sorting covariates by covariateId, stratumId, and rowId

-#Fit model:
-fit <- fitCyclopsModel(cyclopsData, prior = createPrior("none"))
-
-
+ +

An object of type cyclopsData

+
+
+

Details

+

These columns are expected in the outcome object:

stratumId(integer)(optional) Stratum ID for conditional regression models
rowId(integer)Row ID is used to link multiple covariates (x) to a single outcome (y)
y(real)The outcome variable
time(real)For models that use time (e.g. Poisson or Cox regression) this contains time
(e.g. number of days)
weights(real)(optional) Non-negative weights to apply to outcome
censorWeights(real)(optional) Non-negative censoring weights for competing risk model; will be computed if not provided.

These columns are expected in the covariates object:

stratumId(integer)(optional) Stratum ID for conditional regression models
rowId(integer)Row ID is used to link multiple covariates (x) to a single outcome (y)
covariateId(integer)A numeric identifier of a covariate
covariateValue(real)The value of the specified covariate
+
+

Methods (by class)

+ +

  • convertToCyclopsData(data.frame): Convert data from two data.frame

    • +

  • convertToCyclopsData(tbl_dbi): Convert data from two Andromeda tables

    • +
+ +
+

Examples

+ 
#Convert infert dataset to Cyclops format:
+covariates <- data.frame(stratumId = rep(infert$stratum, 2),
+                         rowId = rep(1:nrow(infert), 2),
+                         covariateId = rep(1:2, each = nrow(infert)),
+                         covariateValue = c(infert$spontaneous, infert$induced))
+outcomes <- data.frame(stratumId = infert$stratum,
+                       rowId = 1:nrow(infert),
+                       y = infert$case)
+#Make sparse:
+covariates <- covariates[covariates$covariateValue != 0, ]
+
+#Create Cyclops data object:
+cyclopsData <- convertToCyclopsData(outcomes, covariates, modelType = "clr",
+                                    addIntercept = FALSE)
+#> Sorting outcomes by stratumId and rowId
+#> Sorting covariates by covariateId, stratumId, and rowId
+
+#Fit model:
+fit <- fitCyclopsModel(cyclopsData, prior = createPrior("none"))
+
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/convertToCyclopsVariance.html b/docs/reference/convertToCyclopsVariance.html index d2e17bce..27798fa8 100644 --- a/docs/reference/convertToCyclopsVariance.html +++ b/docs/reference/convertToCyclopsVariance.html @@ -1,68 +1,13 @@ - - - - - - - -Convert to Cyclops Prior Variance — convertToCyclopsVariance • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Convert to Cyclops Prior Variance — convertToCyclopsVariance • Cyclops - - - - + + -
-
- -
- -
+

Convert to Cyclops Prior Variance

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -125,50 +57,48 @@

Convert to Cyclops Prior Variance

from glmnet into a prior variance.

- 
convertToCyclopsVariance(lambda, nobs)
+
+ 
convertToCyclopsVariance(lambda, nobs)
+
+ +
+

Arguments

+
lambda
+

Regularization parameter from glmnet

-

Arguments

- - - - - - - - - - -
lambda

Regularization parameter from glmnet

nobs

Number of observation rows in dataset

-

Value

+
nobs
+

Number of observation rows in dataset

-

Prior variance under a Laplace() prior

+
+
+

Value

+ + +

Prior variance under a Laplace() prior

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/convertToGlmnetLambda.html b/docs/reference/convertToGlmnetLambda.html index 3ec749d8..940dbdf7 100644 --- a/docs/reference/convertToGlmnetLambda.html +++ b/docs/reference/convertToGlmnetLambda.html @@ -1,68 +1,13 @@ - - - - - - - -Convert to glmnet regularization parameter — convertToGlmnetLambda • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Convert to glmnet regularization parameter — convertToGlmnetLambda • Cyclops - - + + - - -
-
- -
- -
+

Convert to glmnet regularization parameter

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -125,50 +57,50 @@

Convert to glmnet regularization parameter

from Cyclops into the regularization parameter lambda.

- 
convertToGlmnetLambda(variance, nobs)
+
+ 
convertToGlmnetLambda(variance, nobs)
+
+ +
+

Arguments

+
variance
+

Prior variance

+ + +
nobs
+

Number of observation rows in dataset

-

Arguments

- - - - - - - - - - -
variance

Prior variance

nobs

Number of observation rows in dataset

+
+
+

Value

+ -

Value

+

lambda

-

lambda

+ +
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/convertToTimeVaryingCoef.html b/docs/reference/convertToTimeVaryingCoef.html new file mode 100644 index 00000000..e6fb2b9e --- /dev/null +++ b/docs/reference/convertToTimeVaryingCoef.html @@ -0,0 +1,109 @@ + +Convert short sparse covariate table to long sparse covariate table for time-varying coefficients. — convertToTimeVaryingCoef • Cyclops + + +
+
+ + + +
+
+
+

Convert short sparse covariate table to long sparse covariate table for time-varying coefficients.

+ Source: R/TimeEffects.R + +
+ +
+

convertToTimeVaryingCoef convert short sparse covariate table to long sparse covariate table for time-varying coefficients.

+
+ +
+ 
convertToTimeVaryingCoef(shortCov, longOut, timeVaryCoefId)
+
+ +
+

Arguments

+
shortCov
+

A data frame containing the covariate with predefined columns (see below).

+ + +
longOut
+

A data frame containing the outcomes with predefined columns (see below), output of splitTime.

+ + +
timeVaryCoefId
+

Integer: A numeric identifier of a time-varying coefficient

+ +
+
+

Value

+ + +

A long sparse covariate table for time-varying coefficients.

+
+
+

Details

+

These columns are expected in the shortCov object:

rowId(integer)Row ID is used to link multiple covariates (x) to a single outcome (y)
covariateId(integer)A numeric identifier of a covariate
covariateValue(real)The value of the specified covariate

These columns are expected in the longOut object:

stratumId(integer)Stratum ID for time-varying models
subjectId(integer)Subject ID is used to link multiple covariates (x) at different time intervals to a single subject
rowId(integer)Row ID is used to link multiple covariates (x) to a single outcome (y)
y(real)The outcome variable
time(real)For models that use time (e.g. Poisson or Cox regression) this contains time
(e.g. number of days)
+ +
+ +
+ + +
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+ +
+

Site built with pkgdown 2.0.7.

+
+ +
+ + + + + + + + diff --git a/docs/reference/coverage.html b/docs/reference/coverage.html index 03373c59..97d8a4a3 100644 --- a/docs/reference/coverage.html +++ b/docs/reference/coverage.html @@ -1,67 +1,12 @@ - - - - - - - -Coverage — coverage • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Coverage — coverage • Cyclops - - + + - - -
-
- -
- -
+

Coverage

- Source: R/Simulation.R + Source: R/Simulation.R
@@ -123,54 +55,54 @@

Coverage

coverage computes the coverage on confidence intervals

- 
coverage(goldStandard, lowerBounds, upperBounds)
- -

Arguments

- - - - - - - - - - - - - - -
goldStandard

Numeric vector

lowerBounds

Numeric vector. Lower bound of the confidence intervals

upperBounds

Numeric vector. Upper bound of the confidence intervals

- -

Value

- -

The proportion of times goldStandard falls between lowerBound and upperBound

+
+ 
coverage(goldStandard, lowerBounds, upperBounds)
+
+ +
+

Arguments

+
goldStandard
+

Numeric vector

+ + +
lowerBounds
+

Numeric vector. Lower bound of the confidence intervals

+ + +
upperBounds
+

Numeric vector. Upper bound of the confidence intervals

+ +
+
+

Value

+ + +

The proportion of times goldStandard falls between lowerBound and upperBound

+ + +
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/createAutoGridCrossValidationControl.html b/docs/reference/createAutoGridCrossValidationControl.html index f95009f9..c5273416 100644 --- a/docs/reference/createAutoGridCrossValidationControl.html +++ b/docs/reference/createAutoGridCrossValidationControl.html @@ -1,69 +1,14 @@ - - - - - - - -Create a Cyclops control object that supports multiple hyperparameters — createAutoGridCrossValidationControl • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Create a Cyclops control object that supports multiple hyperparameters — createAutoGridCrossValidationControl • Cyclops - - - - - - - - - - - + + - - -
-
- -
- -
+

Create a Cyclops control object that supports multiple hyperparameters

- Source: R/CrossValidationControl.R + Source: R/CrossValidationControl.R
-

createCrossValidationControl creates a Cyclops control object for use with fitCyclopsModel +

createCrossValidationControl creates a Cyclops control object for use with fitCyclopsModel that supports multiple hyperparameters through an auto-search in one dimension and a grid-search over the remaining dimensions

- 
createAutoGridCrossValidationControl(
-  outerGrid,
-  autoPosition = 1,
-  refitAtMaximum = TRUE,
-  cvType = "auto",
-  initialValue = 1,
-  ...
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - -
outerGrid

List or data.frame of grid parameters to explore

autoPosition

Vector position for auto-search parameter (concatenated into outerGrid)

refitAtMaximum

Logical: re-fit Cyclops object at maximal cross-validation parameters

cvType

Must equal "auto"

initialValue

Initial value for auto-search parameter

...

Additional parameters passed through to createControl

- -

Value

- -

A Cyclops prior object of class inheriting from "cyclopsPrior" and "cyclopsFunctionalPrior" -for use with fitCyclopsModel.

+
+ 
createAutoGridCrossValidationControl(
+  outerGrid,
+  autoPosition = 1,
+  refitAtMaximum = TRUE,
+  cvType = "auto",
+  initialValue = 1,
+  ...
+)
+
+ +
+

Arguments

+
outerGrid
+

List or data.frame of grid parameters to explore

+ + +
autoPosition
+

Vector position for auto-search parameter (concatenated into outerGrid)

+ + +
refitAtMaximum
+

Logical: re-fit Cyclops object at maximal cross-validation parameters

+ + +
cvType
+

Must equal "auto"

+ + +
initialValue
+

Initial value for auto-search parameter

+ + +
...
+

Additional parameters passed through to createControl

+ +
+
+

Value

+ + +

A Cyclops prior object of class inheriting from "cyclopsPrior" and "cyclopsFunctionalPrior"

+ + +

for use with fitCyclopsModel.

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/createControl.html b/docs/reference/createControl.html index d01aaf31..6f9278ee 100644 --- a/docs/reference/createControl.html +++ b/docs/reference/createControl.html @@ -1,67 +1,12 @@ - - - - - - - -Create a Cyclops control object — createControl • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Create a Cyclops control object — createControl • Cyclops - + + - - - -
-
- -
- -
+

Create a Cyclops control object

- Source: R/ModelFit.R + Source: R/ModelFit.R
-

createControl creates a Cyclops control object for use with fitCyclopsModel.

+

createControl creates a Cyclops control object for use with fitCyclopsModel.

+
+ +
+ 
createControl(
+  maxIterations = 1000,
+  tolerance = 1e-06,
+  convergenceType = "gradient",
+  cvType = "auto",
+  fold = 10,
+  lowerLimit = 0.01,
+  upperLimit = 20,
+  gridSteps = 10,
+  cvRepetitions = 1,
+  minCVData = 100,
+  noiseLevel = "silent",
+  threads = 1,
+  seed = NULL,
+  resetCoefficients = FALSE,
+  startingVariance = -1,
+  useKKTSwindle = FALSE,
+  tuneSwindle = 10,
+  selectorType = "auto",
+  initialBound = 2,
+  maxBoundCount = 5,
+  algorithm = "ccd"
+)
- 
createControl(
-  maxIterations = 1000,
-  tolerance = 1e-06,
-  convergenceType = "gradient",
-  cvType = "auto",
-  fold = 10,
-  lowerLimit = 0.01,
-  upperLimit = 20,
-  gridSteps = 10,
-  cvRepetitions = 1,
-  minCVData = 100,
-  noiseLevel = "silent",
-  threads = 1,
-  seed = NULL,
-  resetCoefficients = FALSE,
-  startingVariance = -1,
-  useKKTSwindle = FALSE,
-  tuneSwindle = 10,
-  selectorType = "auto",
-  initialBound = 2,
-  maxBoundCount = 5,
-  algorithm = "ccd"
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
maxIterations

Integer: maximum iterations of Cyclops to attempt before returning a failed-to-converge error

tolerance

Numeric: maximum relative change in convergence criterion from successive iterations to achieve convergence

convergenceType

String: name of convergence criterion to employ (described in more detail below)

cvType

String: name of cross validation search. +

+

Arguments

+
maxIterations
+

Integer: maximum iterations of Cyclops to attempt before returning a failed-to-converge error

+ + +
tolerance
+

Numeric: maximum relative change in convergence criterion from successive iterations to achieve convergence

+ + +
convergenceType
+

String: name of convergence criterion to employ (described in more detail below)

+ + +
cvType
+

String: name of cross validation search. Option "auto" selects an auto-search following BBR. -Option "grid" selects a grid-search cross validation

fold

Numeric: Number of random folds to employ in cross validation

lowerLimit

Numeric: Lower prior variance limit for grid-search

upperLimit

Numeric: Upper prior variance limit for grid-search

gridSteps

Numeric: Number of steps in grid-search

cvRepetitions

Numeric: Number of repetitions of X-fold cross validation

minCVData

Numeric: Minimum number of data for cross validation

noiseLevel

String: level of Cyclops screen output ("silent", "quiet", "noisy")

threads

Numeric: Specify number of CPU threads to employ in cross-validation; default = 1 (auto = -1)

seed

Numeric: Specify random number generator seed. A null value sets seed via Sys.time.

resetCoefficients

Logical: Reset all coefficients to 0 between model fits under cross-validation

startingVariance

Numeric: Starting variance for auto-search cross-validation; default = -1 (use estimate based on data)

useKKTSwindle

Logical: Use the Karush-Kuhn-Tucker conditions to limit search

tuneSwindle

Numeric: Size multiplier for active set

selectorType

String: name of exchangeable sampling unit. +Option "grid" selects a grid-search cross validation

+ + +
fold
+

Numeric: Number of random folds to employ in cross validation

+ + +
lowerLimit
+

Numeric: Lower prior variance limit for grid-search

+ + +
upperLimit
+

Numeric: Upper prior variance limit for grid-search

+ + +
gridSteps
+

Numeric: Number of steps in grid-search

+ + +
cvRepetitions
+

Numeric: Number of repetitions of X-fold cross validation

+ + +
minCVData
+

Numeric: Minimum number of data for cross validation

+ + +
noiseLevel
+

String: level of Cyclops screen output ("silent", "quiet", "noisy")

+ + +
threads
+

Numeric: Specify number of CPU threads to employ in cross-validation; default = 1 (auto = -1)

+ + +
seed
+

Numeric: Specify random number generator seed. A null value sets seed via Sys.time.

+ + +
resetCoefficients
+

Logical: Reset all coefficients to 0 between model fits under cross-validation

+ + +
startingVariance
+

Numeric: Starting variance for auto-search cross-validation; default = -1 (use estimate based on data)

+ + +
useKKTSwindle
+

Logical: Use the Karush-Kuhn-Tucker conditions to limit search

+ + +
tuneSwindle
+

Numeric: Size multiplier for active set

+ + +
selectorType
+

String: name of exchangeable sampling unit. Option "byPid" selects entire strata. Option "byRow" selects single rows. If set to "auto", "byRow" will be used for all models except conditional models where -the average number of rows per stratum is smaller than the number of strata.

initialBound

Numeric: Starting trust-region size

maxBoundCount

Numeric: Maximum number of tries to decrease initial trust-region size

algorithm

String: name of fitting algorithm to employ; default is `ccd`

-

Todo: Describe convegence types

- -

Value

- -

A Cyclops control object of class inheriting from "cyclopsControl" for use with fitCyclopsModel.

- -

Examples

- 
#Generate some simulated data:
-sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
-                           model = "poisson")
-
#> Sparseness = 75.2 %
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
-                                    addIntercept = TRUE)
-
#> Sorting covariates by covariateId and rowId

-#Define the prior and control objects to use cross-validation for finding the 
-#optimal hyperparameter:
-prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
-control <- createControl(cvType = "auto", noiseLevel = "quiet")
-
-#Fit the model
-fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
-
#> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1623936644] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
-#> Using 1 thread(s)
-#> Starting var = 0.248 (default)
-#> Running at Laplace(2.83981) None  Grid-point #1 at 0.248 	Fold #1 Rep #1 pred log like = 482.873
-#> Running at Laplace(2.83981) None  Grid-point #1 at 0.248 	Fold #2 Rep #1 pred log like = 582.911
-#> Running at Laplace(2.83981) None  Grid-point #1 at 0.248 	Fold #3 Rep #1 pred log like = 465.503
-#> Running at Laplace(2.83981) None  Grid-point #1 at 0.248 	Fold #4 Rep #1 pred log like = 383.186
-#> Running at Laplace(2.83981) None  Grid-point #1 at 0.248 	Fold #5 Rep #1 pred log like = 481.628
-#> Running at Laplace(2.83981) None  Grid-point #1 at 0.248 	Fold #6 Rep #1 pred log like = 466.766
-#> Running at Laplace(2.83981) None  Grid-point #1 at 0.248 	Fold #7 Rep #1 pred log like = 495.382
-#> Running at Laplace(2.83981) None  Grid-point #1 at 0.248 	Fold #8 Rep #1 pred log like = 439.733
-#> Running at Laplace(2.83981) None  Grid-point #1 at 0.248 	Fold #9 Rep #1 pred log like = 472.325
-#> Running at Laplace(2.83981) None  Grid-point #1 at 0.248 	Fold #10 Rep #1 pred log like = 454.301
-#> AvgPred = 472.461 with stdev = 47.2957
-#> Completed at 0.248
-#> Next point at 2.48 with value 0 and continue = 1
-#> search[ 0.248 ] = 472.461(47.2957)
-#> 
-#> Running at Laplace(0.898027) None  Grid-point #2 at 2.48 	Fold #1 Rep #1 pred log like = 482.828
-#> Running at Laplace(0.898027) None  Grid-point #2 at 2.48 	Fold #2 Rep #1 pred log like = 582.903
-#> Running at Laplace(0.898027) None  Grid-point #2 at 2.48 	Fold #3 Rep #1 pred log like = 465.476
-#> Running at Laplace(0.898027) None  Grid-point #2 at 2.48 	Fold #4 Rep #1 pred log like = 383.118
-#> Running at Laplace(0.898027) None  Grid-point #2 at 2.48 	Fold #5 Rep #1 pred log like = 481.674
-#> Running at Laplace(0.898027) None  Grid-point #2 at 2.48 	Fold #6 Rep #1 pred log like = 466.739
-#> Running at Laplace(0.898027) None  Grid-point #2 at 2.48 	Fold #7 Rep #1 pred log like = 495.382
-#> Running at Laplace(0.898027) None  Grid-point #2 at 2.48 	Fold #8 Rep #1 pred log like = 439.76
-#> Running at Laplace(0.898027) None  Grid-point #2 at 2.48 	Fold #9 Rep #1 pred log like = 472.319
-#> Running at Laplace(0.898027) None  Grid-point #2 at 2.48 	Fold #10 Rep #1 pred log like = 454.298
-#> AvgPred = 472.45 with stdev = 47.3054
-#> Completed at 2.48
-#> Next point at 0.0248 with value 0 and continue = 1
-#> search[ 0.248 ] = 472.461(47.2957)
-#> search[ 2.48 ] = 472.45(47.3054)
-#> 
-#> Running at Laplace(8.98027) None  Grid-point #3 at 0.0248 	Fold #1 Rep #1 pred log like = 483.009
-#> Running at Laplace(8.98027) None  Grid-point #3 at 0.0248 	Fold #2 Rep #1 pred log like = 582.96
-#> Running at Laplace(8.98027) None  Grid-point #3 at 0.0248 	Fold #3 Rep #1 pred log like = 465.584
-#> Running at Laplace(8.98027) None  Grid-point #3 at 0.0248 	Fold #4 Rep #1 pred log like = 383.357
-#> Running at Laplace(8.98027) None  Grid-point #3 at 0.0248 	Fold #5 Rep #1 pred log like = 481.397
-#> Running at Laplace(8.98027) None  Grid-point #3 at 0.0248 	Fold #6 Rep #1 pred log like = 466.848
-#> Running at Laplace(8.98027) None  Grid-point #3 at 0.0248 	Fold #7 Rep #1 pred log like = 495.378
-#> Running at Laplace(8.98027) None  Grid-point #3 at 0.0248 	Fold #8 Rep #1 pred log like = 439.667
-#> Running at Laplace(8.98027) None  Grid-point #3 at 0.0248 	Fold #9 Rep #1 pred log like = 472.339
-#> Running at Laplace(8.98027) None  Grid-point #3 at 0.0248 	Fold #10 Rep #1 pred log like = 454.307
-#> AvgPred = 472.485 with stdev = 47.2754
-#> Completed at 0.0248
-#> Next point at 0.00248 with value 0 and continue = 1
-#> search[ 0.0248 ] = 472.485(47.2754)
-#> search[ 0.248 ] = 472.461(47.2957)
-#> search[ 2.48 ] = 472.45(47.3054)
-#> 
-#> Running at Laplace(28.3981) None  Grid-point #4 at 0.00248 	Fold #1 Rep #1 pred log like = 483.332
-#> Running at Laplace(28.3981) None  Grid-point #4 at 0.00248 	Fold #2 Rep #1 pred log like = 583.077
-#> Running at Laplace(28.3981) None  Grid-point #4 at 0.00248 	Fold #3 Rep #1 pred log like = 465.746
-#> Running at Laplace(28.3981) None  Grid-point #4 at 0.00248 	Fold #4 Rep #1 pred log like = 383.597
-#> Running at Laplace(28.3981) None  Grid-point #4 at 0.00248 	Fold #5 Rep #1 pred log like = 480.818
-#> Running at Laplace(28.3981) None  Grid-point #4 at 0.00248 	Fold #6 Rep #1 pred log like = 467.006
-#> Running at Laplace(28.3981) None  Grid-point #4 at 0.00248 	Fold #7 Rep #1 pred log like = 495.33
-#> Running at Laplace(28.3981) None  Grid-point #4 at 0.00248 	Fold #8 Rep #1 pred log like = 439.433
-#> Running at Laplace(28.3981) None  Grid-point #4 at 0.00248 	Fold #9 Rep #1 pred log like = 472.295
-#> Running at Laplace(28.3981) None  Grid-point #4 at 0.00248 	Fold #10 Rep #1 pred log like = 454.266
-#> AvgPred = 472.49 with stdev = 47.2658
-#> Completed at 0.00248
-#> Next point at 0.000248 with value 0 and continue = 1
-#> search[ 0.00248 ] = 472.49(47.2658)
-#> search[ 0.0248 ] = 472.485(47.2754)
-#> search[ 0.248 ] = 472.461(47.2957)
-#> search[ 2.48 ] = 472.45(47.3054)
-#> 
-#> Running at Laplace(89.8027) None  Grid-point #5 at 0.000248 	Fold #1 Rep #1 pred log like = 483.782
-#> Running at Laplace(89.8027) None  Grid-point #5 at 0.000248 	Fold #2 Rep #1 pred log like = 583.142
-#> Running at Laplace(89.8027) None  Grid-point #5 at 0.000248 	Fold #3 Rep #1 pred log like = 465.913
-#> Running at Laplace(89.8027) None  Grid-point #5 at 0.000248 	Fold #4 Rep #1 pred log like = 383.927
-#> Running at Laplace(89.8027) None  Grid-point #5 at 0.000248 	Fold #5 Rep #1 pred log like = 480.818
-#> Running at Laplace(89.8027) None  Grid-point #5 at 0.000248 	Fold #6 Rep #1 pred log like = 466.841
-#> Running at Laplace(89.8027) None  Grid-point #5 at 0.000248 	Fold #7 Rep #1 pred log like = 495.207
-#> Running at Laplace(89.8027) None  Grid-point #5 at 0.000248 	Fold #8 Rep #1 pred log like = 439.178
-#> Running at Laplace(89.8027) None  Grid-point #5 at 0.000248 	Fold #9 Rep #1 pred log like = 472.153
-#> Running at Laplace(89.8027) None  Grid-point #5 at 0.000248 	Fold #10 Rep #1 pred log like = 454.135
-#> AvgPred = 472.51 with stdev = 47.2463
-#> Completed at 0.000248
-#> Next point at 2.48e-05 with value 0 and continue = 1
-#> search[ 0.000248 ] = 472.51(47.2463)
-#> search[ 0.00248 ] = 472.49(47.2658)
-#> search[ 0.0248 ] = 472.485(47.2754)
-#> search[ 0.248 ] = 472.461(47.2957)
-#> search[ 2.48 ] = 472.45(47.3054)
-#> 
-#> Running at Laplace(283.981) None  Grid-point #6 at 2.48e-05 	Fold #1 Rep #1 pred log like = 483.782
-#> Running at Laplace(283.981) None  Grid-point #6 at 2.48e-05 	Fold #2 Rep #1 pred log like = 583.142
-#> Running at Laplace(283.981) None  Grid-point #6 at 2.48e-05 	Fold #3 Rep #1 pred log like = 465.913
-#> Running at Laplace(283.981) None  Grid-point #6 at 2.48e-05 	Fold #4 Rep #1 pred log like = 383.927
-#> Running at Laplace(283.981) None  Grid-point #6 at 2.48e-05 	Fold #5 Rep #1 pred log like = 480.818
-#> Running at Laplace(283.981) None  Grid-point #6 at 2.48e-05 	Fold #6 Rep #1 pred log like = 466.841
-#> Running at Laplace(283.981) None  Grid-point #6 at 2.48e-05 	Fold #7 Rep #1 pred log like = 495.207
-#> Running at Laplace(283.981) None  Grid-point #6 at 2.48e-05 	Fold #8 Rep #1 pred log like = 439.178
-#> Running at Laplace(283.981) None  Grid-point #6 at 2.48e-05 	Fold #9 Rep #1 pred log like = 472.153
-#> Running at Laplace(283.981) None  Grid-point #6 at 2.48e-05 	Fold #10 Rep #1 pred log like = 454.135
-#> AvgPred = 472.51 with stdev = 47.2463
-#> Completed at 2.48e-05
-#> Next point at 6.5199e-08 with value 472.521 and continue = 0
-#> search[ 2.48e-05 ] = 472.51(47.2463)
-#> search[ 0.000248 ] = 472.51(47.2463)
-#> search[ 0.00248 ] = 472.49(47.2658)
-#> search[ 0.0248 ] = 472.485(47.2754)
-#> search[ 0.248 ] = 472.461(47.2957)
-#> search[ 2.48 ] = 472.45(47.3054)
-#> 
-#> 
-#> Maximum predicted log likelihood (472.521) estimated at:
-#> 	6.5199e-08 (variance)
-#> 	5538.53 (lambda)
-#> 
-#> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(5538.53) None 

-#Find out what the optimal hyperparameter was:
-getHyperParameter(fit)
-
#> [1] 6.519902e-08

-#Extract the current log-likelihood, and coefficients
-logLik(fit)
-
#> 'log Lik.' -2056.259 (df=3)
coef(fit)
-
#> (Intercept)           1           2 
-#>   -3.850744    0.000000    0.000000 

-#We can only retrieve the confidence interval for unregularized coefficients:
-confint(fit, c(0))
-
#> Using 1 thread(s)
#>      covariate     2.5 %   97.5 % evaluations
-#> [1,]         0 -3.877542 -3.82417          24
+the average number of rows per stratum is smaller than the number of strata.

+ + +
initialBound
+

Numeric: Starting trust-region size

+ + +
maxBoundCount
+

Numeric: Maximum number of tries to decrease initial trust-region size

+ + +
algorithm
+

String: name of fitting algorithm to employ; default is ccd

+

Todo: Describe convegence types

+ +
+
+

Value

+ + +

A Cyclops control object of class inheriting from "cyclopsControl" for use with fitCyclopsModel.

+
+ +
+

Examples

+ 
#Generate some simulated data:
+sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
+                           model = "poisson")
+#> Sparseness = 75.05 %
+cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
+                                    addIntercept = TRUE)
+#> Sorting covariates by covariateId and rowId
+
+#Define the prior and control objects to use cross-validation for finding the 
+#optimal hyperparameter:
+prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
+control <- createControl(cvType = "auto", noiseLevel = "quiet")
+
+#Fit the model
+fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
+#> Using cross-validation selector type byRow
+#> Performing 10-fold cross-validation [seed = 1698757933] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Using 1 thread(s)
+#> Starting var = 0.2495 (default)
+#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #1 Rep #1 pred log like = 693.612
+#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #2 Rep #1 pred log like = 727.871
+#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #3 Rep #1 pred log like = 856.472
+#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #4 Rep #1 pred log like = 872.52
+#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #5 Rep #1 pred log like = 757.649
+#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #6 Rep #1 pred log like = 752.08
+#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #7 Rep #1 pred log like = 777.327
+#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #8 Rep #1 pred log like = 670.9
+#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #9 Rep #1 pred log like = 778.766
+#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #10 Rep #1 pred log like = 958.317
+#> AvgPred = 784.551 with stdev = 83.2879
+#> Completed at 0.2495
+#> Next point at 2.495 with value 0 and continue = 1
+#> search[ 0.2495 ] = 784.551(83.2879)
+#> 
+#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #1 Rep #1 pred log like = 693.629
+#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #2 Rep #1 pred log like = 727.901
+#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #3 Rep #1 pred log like = 856.465
+#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #4 Rep #1 pred log like = 872.541
+#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #5 Rep #1 pred log like = 757.617
+#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #6 Rep #1 pred log like = 752.117
+#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #7 Rep #1 pred log like = 777.31
+#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #8 Rep #1 pred log like = 670.913
+#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #9 Rep #1 pred log like = 778.729
+#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #10 Rep #1 pred log like = 958.301
+#> AvgPred = 784.552 with stdev = 83.2805
+#> Completed at 2.495
+#> Next point at 24.95 with value 0 and continue = 1
+#> search[ 0.2495 ] = 784.551(83.2879)
+#> search[ 2.495 ] = 784.552(83.2805)
+#> 
+#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #1 Rep #1 pred log like = 693.634
+#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #2 Rep #1 pred log like = 727.911
+#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #3 Rep #1 pred log like = 856.462
+#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #4 Rep #1 pred log like = 872.547
+#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #5 Rep #1 pred log like = 757.606
+#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #6 Rep #1 pred log like = 752.129
+#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #7 Rep #1 pred log like = 777.305
+#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #8 Rep #1 pred log like = 670.917
+#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #9 Rep #1 pred log like = 778.718
+#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #10 Rep #1 pred log like = 958.296
+#> AvgPred = 784.552 with stdev = 83.2781
+#> Completed at 24.95
+#> Next point at 249.5 with value 0 and continue = 1
+#> search[ 0.2495 ] = 784.551(83.2879)
+#> search[ 2.495 ] = 784.552(83.2805)
+#> search[ 24.95 ] = 784.552(83.2781)
+#> 
+#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #1 Rep #1 pred log like = 693.635
+#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #2 Rep #1 pred log like = 727.913
+#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #3 Rep #1 pred log like = 856.461
+#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #4 Rep #1 pred log like = 872.549
+#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #5 Rep #1 pred log like = 757.603
+#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #6 Rep #1 pred log like = 752.132
+#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #7 Rep #1 pred log like = 777.303
+#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #8 Rep #1 pred log like = 670.918
+#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #9 Rep #1 pred log like = 778.714
+#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #10 Rep #1 pred log like = 958.294
+#> AvgPred = 784.552 with stdev = 83.2774
+#> Completed at 249.5
+#> Next point at 2495 with value 0 and continue = 1
+#> search[ 0.2495 ] = 784.551(83.2879)
+#> search[ 2.495 ] = 784.552(83.2805)
+#> search[ 24.95 ] = 784.552(83.2781)
+#> search[ 249.5 ] = 784.552(83.2774)
+#> 
+#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #1 Rep #1 pred log like = 693.636
+#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #2 Rep #1 pred log like = 727.914
+#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #3 Rep #1 pred log like = 856.461
+#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #4 Rep #1 pred log like = 872.55
+#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #5 Rep #1 pred log like = 757.602
+#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #6 Rep #1 pred log like = 752.133
+#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #7 Rep #1 pred log like = 777.302
+#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #8 Rep #1 pred log like = 670.918
+#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #9 Rep #1 pred log like = 778.713
+#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #10 Rep #1 pred log like = 958.294
+#> AvgPred = 784.552 with stdev = 83.2771
+#> Completed at 2495
+#> Next point at 146.811 with value 784.553 and continue = 0
+#> search[ 0.2495 ] = 784.551(83.2879)
+#> search[ 2.495 ] = 784.552(83.2805)
+#> search[ 24.95 ] = 784.552(83.2781)
+#> search[ 249.5 ] = 784.552(83.2774)
+#> search[ 2495 ] = 784.552(83.2771)
+#> 
+#> 
+#> Maximum predicted log likelihood (784.553) estimated at:
+#> 	146.811 (variance)
+#> 	0.116718 (lambda)
+#> 
+#> Fitting model at optimal hyperparameter
+#> Using prior: Laplace(0.116718) None 
+
+#Find out what the optimal hyperparameter was:
+getHyperParameter(fit)
+#> [1] 146.8106
+
+#Extract the current log-likelihood, and coefficients
+logLik(fit)
+#> 'log Lik.' -2194.845 (df=3)
+coef(fit)
+#> (Intercept)           1           2 
+#> -3.56117384  0.03211331 -0.01937822 
+
+#We can only retrieve the confidence interval for unregularized coefficients:
+confint(fit, c(0))
+#> Using 1 thread(s)
+#>             covariate     2.5 %    97.5 % evaluations
+#> (Intercept)         0 -3.590514 -3.532095          22
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/createCyclopsData.html b/docs/reference/createCyclopsData.html index 4839b080..9ce426af 100644 --- a/docs/reference/createCyclopsData.html +++ b/docs/reference/createCyclopsData.html @@ -1,67 +1,12 @@ - - - - - - - -Create a Cyclops data object — createCyclopsData • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Create a Cyclops data object — createCyclopsData • Cyclops - - - - + + -
-
- -
- -
+

Create a Cyclops data object

- Source: R/DataManagement.R + Source: R/DataManagement.R
@@ -123,196 +55,186 @@

Create a Cyclops data object

createCyclopsData creates a Cyclops data object from an R formula or data matrices.

- 
createCyclopsData(
-  formula,
-  sparseFormula,
-  indicatorFormula,
-  modelType,
-  data,
-  subset = NULL,
-  weights = NULL,
-  censorWeights = NULL,
-  offset = NULL,
-  time = NULL,
-  pid = NULL,
-  y = NULL,
-  type = NULL,
-  dx = NULL,
-  sx = NULL,
-  ix = NULL,
-  model = FALSE,
-  normalize = NULL,
-  floatingPoint = 64,
-  method = "cyclops.fit"
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
formula

An object of class "formula" that provides a symbolic description of the numerically dense model response and terms.

sparseFormula

An object of class "formula" that provides a symbolic description of numerically sparse model terms.

indicatorFormula

An object of class "formula" that provides a symbolic description of {0,1} model terms.

modelType

character string: Valid types are listed below.

data

An optional data frame, list or environment containing the variables in the model.

subset

Currently unused

weights

Currently unused

censorWeights

Vector of subject-specific censoring weights (between 0 and 1). Currently only supported in modelType = "fgr".

offset

Currently unused

time

Currently undocumented

pid

Optional vector of integer stratum identifiers. If supplied, all rows must be sorted by increasing identifiers

y

Currently undocumented

type

Currently undocumented

dx

Optional dense "Matrix" of covariates

sx

Optional sparse "Matrix" of covariates

ix

Optional {0,1} "Matrix" of covariates

model

Currently undocumented

normalize

String: Name of normalization for all non-indicator covariates (possible values: stdev, max, median)

floatingPoint

Integer: Floating-point representation size (32 or 64)

method

Currently undocumented

- -

Value

- -

A list that contains a Cyclops model data object pointer and an operation duration

-

Details

- -

This function creates a Cyclops model data object from R "formula" or directly from +

+ 
createCyclopsData(
+  formula,
+  sparseFormula,
+  indicatorFormula,
+  modelType,
+  data,
+  subset = NULL,
+  weights = NULL,
+  censorWeights = NULL,
+  offset = NULL,
+  time = NULL,
+  pid = NULL,
+  y = NULL,
+  type = NULL,
+  dx = NULL,
+  sx = NULL,
+  ix = NULL,
+  model = FALSE,
+  normalize = NULL,
+  floatingPoint = 64,
+  method = "cyclops.fit"
+)
+
+ +
+

Arguments

+
formula
+

An object of class "formula" that provides a symbolic description of the numerically dense model response and terms.

+ + +
sparseFormula
+

An object of class "formula" that provides a symbolic description of numerically sparse model terms.

+ + +
indicatorFormula
+

An object of class "formula" that provides a symbolic description of {0,1} model terms.

+ + +
modelType
+

character string: Valid types are listed below.

+ + +
data
+

An optional data frame, list or environment containing the variables in the model.

+ + +
subset
+

Currently unused

+ + +
weights
+

Currently unused

+ + +
censorWeights
+

Vector of subject-specific censoring weights (between 0 and 1). Currently only supported in modelType = "fgr".

+ + +
offset
+

Currently unused

+ + +
time
+

Currently undocumented

+ + +
pid
+

Optional vector of integer stratum identifiers. If supplied, all rows must be sorted by increasing identifiers

+ + +
y
+

Currently undocumented

+ + +
type
+

Currently undocumented

+ + +
dx
+

Optional dense "Matrix" of covariates

+ + +
sx
+

Optional sparse "Matrix" of covariates

+ + +
ix
+

Optional {0,1} "Matrix" of covariates

+ + +
model
+

Currently undocumented

+ + +
normalize
+

String: Name of normalization for all non-indicator covariates (possible values: stdev, max, median)

+ + +
floatingPoint
+

Integer: Floating-point representation size (32 or 64)

+ + +
method
+

Currently undocumented

+ +
+
+

Value

+ + +

A list that contains a Cyclops model data object pointer and an operation duration

+
+
+

Details

+

This function creates a Cyclops model data object from R "formula" or directly from numeric vectors and matrices to define the model response and covariates. -If specifying a model using a "formula", then the left-hand side define the model response and the +If specifying a model using a "formula", then the left-hand side define the model response and the right-hand side defines dense covariate terms. Objects provided with "sparseFormula" and "indicatorFormula" must be include left-hand side responses and terms are coersed into sparse and indicator representations for computational efficiency.

-

Items to discuss: -* Only use formula or (y,dx,...) -* stratum() in formula -* offset() in formula -* when "stratum" (renamed from pid) are necessary -* when "time" are necessary

-

Models

- +

Items to discuss:

  • Only use formula or (y,dx,...)

    • +

  • stratum() in formula

    • +

  • offset() in formula

    • +

  • when "stratum" (renamed from pid) are necessary

    • +

  • when "time" are necessary

    • +
+
+

Models

-

Currently supported model types are:

- - - - - - - - -
"ls"Least squares
"pr"Poisson regression
"lr"Logistic regression
"clr"Conditional logistic regression
"cpr"Conditional Poisson regression
"sccs"Self-controlled case series
"cox"Cox proportional hazards regression
"fgr"Fine-Gray proportional subdistribution hazards regression
- - - -

Examples

- 
## Dobson (1990) Page 93: Randomized Controlled Trial :
-counts <- c(18, 17, 15, 20, 10, 20, 25, 13, 12)
-outcome <- gl(3, 1, 9)
-treatment <- gl(3, 3)
-cyclopsData <- createCyclopsData(
-     counts ~ outcome + treatment,
-     modelType = "pr")
-cyclopsFit <- fitCyclopsModel(cyclopsData)
-
-cyclopsData2 <- createCyclopsData(
-     counts ~ outcome,
-     indicatorFormula = ~ treatment,
-     modelType = "pr")
-summary(cyclopsData2)
-
#>             covariateId nzCount nzMean nzVar      type
-#> (Intercept)           1       9      1     0     dense
-#> outcome2              2       3      1     0     dense
-#> outcome3              3       3      1     0     dense
-#> treatment2            4       3      1     0 indicator
-#> treatment3            5       3      1     0 indicator
cyclopsFit2 <- fitCyclopsModel(cyclopsData2)
-
-
+

Currently supported model types are:

"ls"Least squares
"pr"Poisson regression
"lr"Logistic regression
"clr"Conditional logistic regression
"cpr"Conditional Poisson regression
"sccs"Self-controlled case series
"cox"Cox proportional hazards regression
"fgr"Fine-Gray proportional subdistribution hazards regression
+ +
+

Examples

+ 
## Dobson (1990) Page 93: Randomized Controlled Trial :
+counts <- c(18, 17, 15, 20, 10, 20, 25, 13, 12)
+outcome <- gl(3, 1, 9)
+treatment <- gl(3, 3)
+cyclopsData <- createCyclopsData(
+     counts ~ outcome + treatment,
+     modelType = "pr")
+cyclopsFit <- fitCyclopsModel(cyclopsData)
+
+cyclopsData2 <- createCyclopsData(
+     counts ~ outcome,
+     indicatorFormula = ~ treatment,
+     modelType = "pr")
+summary(cyclopsData2)
+#>             covariateId nzCount nzMean nzVar      type
+#> (Intercept)           1       9      1     0     dense
+#> outcome2              2       3      1     0     dense
+#> outcome3              3       3      1     0     dense
+#> treatment2            4       3      1     0 indicator
+#> treatment3            5       3      1     0 indicator
+cyclopsFit2 <- fitCyclopsModel(cyclopsData2)
+
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/createNonSeparablePrior.html b/docs/reference/createNonSeparablePrior.html index af45b747..4688f2ca 100644 --- a/docs/reference/createNonSeparablePrior.html +++ b/docs/reference/createNonSeparablePrior.html @@ -1,67 +1,12 @@ - - - - - - - -Create a Cyclops prior object that returns the MLE of non-separable coefficients — createNonSeparablePrior • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Create a Cyclops prior object that returns the MLE of non-separable coefficients — createNonSeparablePrior • Cyclops - - + + - - -
-
- -
- -
+

Create a Cyclops prior object that returns the MLE of non-separable coefficients

- Source: R/SpecialPriors.R + Source: R/SpecialPriors.R
-

createNonSeparablePrior creates a Cyclops prior object for use with fitCyclopsModel.

+

createNonSeparablePrior creates a Cyclops prior object for use with fitCyclopsModel.

- 
createNonSeparablePrior(maxIterations = 10, ...)
+
+ 
createNonSeparablePrior(maxIterations = 10, ...)
+
-

Arguments

- - - - - - - - - - -
maxIterations

Numeric: maximum iterations to achieve convergence

...

Additional argument(s) for fitCyclopsModel

+
+

Arguments

+
maxIterations
+

Numeric: maximum iterations to achieve convergence

-

Value

-

A Cyclops prior object of class inheriting from -"cyclopsPrior" for use with fitCyclopsModel.

+
...
+

Additional argument(s) for fitCyclopsModel

-

Examples

- 
prior <- createNonSeparablePrior()
+
+
+

Value

+ -
+

A Cyclops prior object of class inheriting from +"cyclopsPrior" for use with fitCyclopsModel.

+
+ +
+

Examples

+ 
prior <- createNonSeparablePrior()
+
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/createParameterizedPrior.html b/docs/reference/createParameterizedPrior.html index ca805b29..1ed262cc 100644 --- a/docs/reference/createParameterizedPrior.html +++ b/docs/reference/createParameterizedPrior.html @@ -1,68 +1,13 @@ - - - - - - - -Create a Cyclops parameterized prior object — createParameterizedPrior • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Create a Cyclops parameterized prior object — createParameterizedPrior • Cyclops - - + + - - -
-
- -
- -
+

Create a Cyclops parameterized prior object

- Source: R/ParameterizedPrior.R + Source: R/ParameterizedPrior.R
-

createParameterizedPrior creates a Cyclops prior object for use with fitCyclopsModel +

createParameterizedPrior creates a Cyclops prior object for use with fitCyclopsModel in which arbitrary R functions parameterize the prior location and variance.

- 
createParameterizedPrior(
-  priorType,
-  parameterize,
-  values,
-  useCrossValidation = FALSE,
-  forceIntercept = FALSE
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - -
priorType

Character vector: specifies prior distribution. See below for options

parameterize

Function list: parameterizes location and variance

values

Numeric vector: initial parameter values

useCrossValidation

Logical: Perform cross-validation to determine parameters.

forceIntercept

Logical: Force intercept coefficient into prior

- -

Value

- -

A Cyclops prior object of class inheriting from "cyclopsPrior" and "cyclopsFunctionalPrior" -for use with fitCyclopsModel.

+
+ 
createParameterizedPrior(
+  priorType,
+  parameterize,
+  values,
+  useCrossValidation = FALSE,
+  forceIntercept = FALSE
+)
+
+ +
+

Arguments

+
priorType
+

Character vector: specifies prior distribution. See below for options

+ + +
parameterize
+

Function list: parameterizes location and variance

+ + +
values
+

Numeric vector: initial parameter values

+ + +
useCrossValidation
+

Logical: Perform cross-validation to determine parameters.

+ + +
forceIntercept
+

Logical: Force intercept coefficient into prior

+ +
+
+

Value

+ + +

A Cyclops prior object of class inheriting from "cyclopsPrior" and "cyclopsFunctionalPrior"

+ + +

for use with fitCyclopsModel.

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/createPrior.html b/docs/reference/createPrior.html index b2529006..e8aaf3b1 100644 --- a/docs/reference/createPrior.html +++ b/docs/reference/createPrior.html @@ -1,67 +1,12 @@ - - - - - - - -Create a Cyclops prior object — createPrior • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Create a Cyclops prior object — createPrior • Cyclops - - - - + + -
-
- -
- -
+

Create a Cyclops prior object

- Source: R/ModelFit.R + Source: R/ModelFit.R
-

createPrior creates a Cyclops prior object for use with fitCyclopsModel.

+

createPrior creates a Cyclops prior object for use with fitCyclopsModel.

- 
createPrior(
-  priorType,
-  variance = 1,
-  exclude = c(),
-  graph = NULL,
-  neighborhood = NULL,
-  useCrossValidation = FALSE,
-  forceIntercept = FALSE
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
priorType

Character: specifies prior distribution. See below for options

variance

Numeric: prior distribution variance

exclude

A vector of numbers or covariateId names to exclude from prior

graph

Child-to-parent mapping for a hierarchical prior

neighborhood

A list of first-order neighborhoods for a partially fused prior

useCrossValidation

Logical: Perform cross-validation to determine prior variance.

forceIntercept

Logical: Force intercept coefficient into prior

- -

Value

- -

A Cyclops prior object of class inheriting from "cyclopsPrior" for use with fitCyclopsModel.

-

Prior types

+
+ 
createPrior(
+  priorType,
+  variance = 1,
+  exclude = c(),
+  graph = NULL,
+  neighborhood = NULL,
+  useCrossValidation = FALSE,
+  forceIntercept = FALSE
+)
+
+ +
+

Arguments

+
priorType
+

Character: specifies prior distribution. See below for options

+ + +
variance
+

Numeric: prior distribution variance

+ + +
exclude
+

A vector of numbers or covariateId names to exclude from prior

+ + +
graph
+

Child-to-parent mapping for a hierarchical prior

+ +
neighborhood
+

A list of first-order neighborhoods for a partially fused prior

+ + +
useCrossValidation
+

Logical: Perform cross-validation to determine prior variance.

+ + +
forceIntercept
+

Logical: Force intercept coefficient into prior

+ +
+
+

Value

+ + +

A Cyclops prior object of class inheriting from "cyclopsPrior" for use with fitCyclopsModel.

+
+
+

Prior types

@@ -179,667 +113,124 @@

"lambda" per observation. See "glmnet", for example.

variance = 2 * / (nobs * lambda)^2 or lambda = sqrt(2 / variance) / nobs

+

-

Examples

- 
#Generate some simulated data:
-sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
-                           model = "poisson")
-
#> Sparseness = 75.8 %
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
-                                    addIntercept = TRUE)
-
#> Sorting covariates by covariateId and rowId

-#Define the prior and control objects to use cross-validation for finding the 
-#optimal hyperparameter:
-prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
-control <- createControl(cvType = "auto", noiseLevel = "quiet")
-
-#Fit the model
-fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
-
#> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1623936645] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
-#> Using 1 thread(s)
-#> Starting var = 0.242 (default)
-#> Running at Laplace(2.8748) None  Grid-point #1 at 0.242 	Fold #1 Rep #1 pred log like = 661.9
-#> Running at Laplace(2.8748) None  Grid-point #1 at 0.242 	Fold #2 Rep #1 pred log like = 635.024
-#> Running at Laplace(2.8748) None  Grid-point #1 at 0.242 	Fold #3 Rep #1 pred log like = 850.057
-#> Running at Laplace(2.8748) None  Grid-point #1 at 0.242 	Fold #4 Rep #1 pred log like = 914.669
-#> Running at Laplace(2.8748) None  Grid-point #1 at 0.242 	Fold #5 Rep #1 pred log like = 759.963
-#> Running at Laplace(2.8748) None  Grid-point #1 at 0.242 	Fold #6 Rep #1 pred log like = 779.161
-#> Running at Laplace(2.8748) None  Grid-point #1 at 0.242 	Fold #7 Rep #1 pred log like = 791.408
-#> Running at Laplace(2.8748) None  Grid-point #1 at 0.242 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(2.8748) None  Grid-point #1 at 0.242 	Fold #9 Rep #1 pred log like = 848.093
-#> Running at Laplace(2.8748) None  Grid-point #1 at 0.242 	Fold #10 Rep #1 pred log like = 706
-#> AvgPred = 783.141 with stdev = 89.2243
-#> Completed at 0.242
-#> Next point at 2.42 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> 
-#> Running at Laplace(0.909091) None  Grid-point #2 at 2.42 	Fold #1 Rep #1 pred log like = 661.928
-#> Running at Laplace(0.909091) None  Grid-point #2 at 2.42 	Fold #2 Rep #1 pred log like = 634.993
-#> Running at Laplace(0.909091) None  Grid-point #2 at 2.42 	Fold #3 Rep #1 pred log like = 850.119
-#> Running at Laplace(0.909091) None  Grid-point #2 at 2.42 	Fold #4 Rep #1 pred log like = 914.653
-#> Running at Laplace(0.909091) None  Grid-point #2 at 2.42 	Fold #5 Rep #1 pred log like = 759.919
-#> Running at Laplace(0.909091) None  Grid-point #2 at 2.42 	Fold #6 Rep #1 pred log like = 779.115
-#> Running at Laplace(0.909091) None  Grid-point #2 at 2.42 	Fold #7 Rep #1 pred log like = 791.438
-#> Running at Laplace(0.909091) None  Grid-point #2 at 2.42 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(0.909091) None  Grid-point #2 at 2.42 	Fold #9 Rep #1 pred log like = 848.112
-#> Running at Laplace(0.909091) None  Grid-point #2 at 2.42 	Fold #10 Rep #1 pred log like = 706.007
-#> AvgPred = 783.142 with stdev = 89.2304
-#> Completed at 2.42
-#> Next point at 24.2 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> 
-#> Running at Laplace(0.28748) None  Grid-point #3 at 24.2 	Fold #1 Rep #1 pred log like = 661.937
-#> Running at Laplace(0.28748) None  Grid-point #3 at 24.2 	Fold #2 Rep #1 pred log like = 634.983
-#> Running at Laplace(0.28748) None  Grid-point #3 at 24.2 	Fold #3 Rep #1 pred log like = 850.139
-#> Running at Laplace(0.28748) None  Grid-point #3 at 24.2 	Fold #4 Rep #1 pred log like = 914.647
-#> Running at Laplace(0.28748) None  Grid-point #3 at 24.2 	Fold #5 Rep #1 pred log like = 759.905
-#> Running at Laplace(0.28748) None  Grid-point #3 at 24.2 	Fold #6 Rep #1 pred log like = 779.1
-#> Running at Laplace(0.28748) None  Grid-point #3 at 24.2 	Fold #7 Rep #1 pred log like = 791.448
-#> Running at Laplace(0.28748) None  Grid-point #3 at 24.2 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(0.28748) None  Grid-point #3 at 24.2 	Fold #9 Rep #1 pred log like = 848.118
-#> Running at Laplace(0.28748) None  Grid-point #3 at 24.2 	Fold #10 Rep #1 pred log like = 706.009
-#> AvgPred = 783.142 with stdev = 89.2323
-#> Completed at 24.2
-#> Next point at 242 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> 
-#> Running at Laplace(0.0909091) None  Grid-point #4 at 242 	Fold #1 Rep #1 pred log like = 661.939
-#> Running at Laplace(0.0909091) None  Grid-point #4 at 242 	Fold #2 Rep #1 pred log like = 634.98
-#> Running at Laplace(0.0909091) None  Grid-point #4 at 242 	Fold #3 Rep #1 pred log like = 850.145
-#> Running at Laplace(0.0909091) None  Grid-point #4 at 242 	Fold #4 Rep #1 pred log like = 914.646
-#> Running at Laplace(0.0909091) None  Grid-point #4 at 242 	Fold #5 Rep #1 pred log like = 759.9
-#> Running at Laplace(0.0909091) None  Grid-point #4 at 242 	Fold #6 Rep #1 pred log like = 779.096
-#> Running at Laplace(0.0909091) None  Grid-point #4 at 242 	Fold #7 Rep #1 pred log like = 791.451
-#> Running at Laplace(0.0909091) None  Grid-point #4 at 242 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(0.0909091) None  Grid-point #4 at 242 	Fold #9 Rep #1 pred log like = 848.12
-#> Running at Laplace(0.0909091) None  Grid-point #4 at 242 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.233
-#> Completed at 242
-#> Next point at 2420 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> 
-#> Running at Laplace(0.028748) None  Grid-point #5 at 2420 	Fold #1 Rep #1 pred log like = 661.94
-#> Running at Laplace(0.028748) None  Grid-point #5 at 2420 	Fold #2 Rep #1 pred log like = 634.979
-#> Running at Laplace(0.028748) None  Grid-point #5 at 2420 	Fold #3 Rep #1 pred log like = 850.147
-#> Running at Laplace(0.028748) None  Grid-point #5 at 2420 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(0.028748) None  Grid-point #5 at 2420 	Fold #5 Rep #1 pred log like = 759.899
-#> Running at Laplace(0.028748) None  Grid-point #5 at 2420 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(0.028748) None  Grid-point #5 at 2420 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(0.028748) None  Grid-point #5 at 2420 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(0.028748) None  Grid-point #5 at 2420 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(0.028748) None  Grid-point #5 at 2420 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2420
-#> Next point at 24200 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(0.00909091) None  Grid-point #6 at 24200 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(0.00909091) None  Grid-point #6 at 24200 	Fold #2 Rep #1 pred log like = 634.979
-#> Running at Laplace(0.00909091) None  Grid-point #6 at 24200 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(0.00909091) None  Grid-point #6 at 24200 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(0.00909091) None  Grid-point #6 at 24200 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(0.00909091) None  Grid-point #6 at 24200 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(0.00909091) None  Grid-point #6 at 24200 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(0.00909091) None  Grid-point #6 at 24200 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(0.00909091) None  Grid-point #6 at 24200 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(0.00909091) None  Grid-point #6 at 24200 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 24200
-#> Next point at 242000 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(0.0028748) None  Grid-point #7 at 242000 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(0.0028748) None  Grid-point #7 at 242000 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(0.0028748) None  Grid-point #7 at 242000 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(0.0028748) None  Grid-point #7 at 242000 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(0.0028748) None  Grid-point #7 at 242000 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(0.0028748) None  Grid-point #7 at 242000 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(0.0028748) None  Grid-point #7 at 242000 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(0.0028748) None  Grid-point #7 at 242000 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(0.0028748) None  Grid-point #7 at 242000 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(0.0028748) None  Grid-point #7 at 242000 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 242000
-#> Next point at 2.42e+06 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(0.000909091) None  Grid-point #8 at 2.42e+06 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(0.000909091) None  Grid-point #8 at 2.42e+06 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(0.000909091) None  Grid-point #8 at 2.42e+06 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(0.000909091) None  Grid-point #8 at 2.42e+06 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(0.000909091) None  Grid-point #8 at 2.42e+06 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(0.000909091) None  Grid-point #8 at 2.42e+06 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(0.000909091) None  Grid-point #8 at 2.42e+06 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(0.000909091) None  Grid-point #8 at 2.42e+06 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(0.000909091) None  Grid-point #8 at 2.42e+06 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(0.000909091) None  Grid-point #8 at 2.42e+06 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+06
-#> Next point at 2.42e+07 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(0.00028748) None  Grid-point #9 at 2.42e+07 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(0.00028748) None  Grid-point #9 at 2.42e+07 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(0.00028748) None  Grid-point #9 at 2.42e+07 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(0.00028748) None  Grid-point #9 at 2.42e+07 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(0.00028748) None  Grid-point #9 at 2.42e+07 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(0.00028748) None  Grid-point #9 at 2.42e+07 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(0.00028748) None  Grid-point #9 at 2.42e+07 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(0.00028748) None  Grid-point #9 at 2.42e+07 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(0.00028748) None  Grid-point #9 at 2.42e+07 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(0.00028748) None  Grid-point #9 at 2.42e+07 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+07
-#> Next point at 2.42e+08 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(9.09091e-05) None  Grid-point #10 at 2.42e+08 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(9.09091e-05) None  Grid-point #10 at 2.42e+08 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(9.09091e-05) None  Grid-point #10 at 2.42e+08 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(9.09091e-05) None  Grid-point #10 at 2.42e+08 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(9.09091e-05) None  Grid-point #10 at 2.42e+08 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(9.09091e-05) None  Grid-point #10 at 2.42e+08 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(9.09091e-05) None  Grid-point #10 at 2.42e+08 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(9.09091e-05) None  Grid-point #10 at 2.42e+08 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(9.09091e-05) None  Grid-point #10 at 2.42e+08 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(9.09091e-05) None  Grid-point #10 at 2.42e+08 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+08
-#> Next point at 2.42e+09 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(2.8748e-05) None  Grid-point #11 at 2.42e+09 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(2.8748e-05) None  Grid-point #11 at 2.42e+09 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(2.8748e-05) None  Grid-point #11 at 2.42e+09 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(2.8748e-05) None  Grid-point #11 at 2.42e+09 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(2.8748e-05) None  Grid-point #11 at 2.42e+09 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(2.8748e-05) None  Grid-point #11 at 2.42e+09 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(2.8748e-05) None  Grid-point #11 at 2.42e+09 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(2.8748e-05) None  Grid-point #11 at 2.42e+09 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(2.8748e-05) None  Grid-point #11 at 2.42e+09 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(2.8748e-05) None  Grid-point #11 at 2.42e+09 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+09
-#> Next point at 2.42e+10 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(9.09091e-06) None  Grid-point #12 at 2.42e+10 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(9.09091e-06) None  Grid-point #12 at 2.42e+10 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(9.09091e-06) None  Grid-point #12 at 2.42e+10 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(9.09091e-06) None  Grid-point #12 at 2.42e+10 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(9.09091e-06) None  Grid-point #12 at 2.42e+10 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(9.09091e-06) None  Grid-point #12 at 2.42e+10 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(9.09091e-06) None  Grid-point #12 at 2.42e+10 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(9.09091e-06) None  Grid-point #12 at 2.42e+10 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(9.09091e-06) None  Grid-point #12 at 2.42e+10 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(9.09091e-06) None  Grid-point #12 at 2.42e+10 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+10
-#> Next point at 2.42e+11 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(2.8748e-06) None  Grid-point #13 at 2.42e+11 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(2.8748e-06) None  Grid-point #13 at 2.42e+11 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(2.8748e-06) None  Grid-point #13 at 2.42e+11 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(2.8748e-06) None  Grid-point #13 at 2.42e+11 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(2.8748e-06) None  Grid-point #13 at 2.42e+11 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(2.8748e-06) None  Grid-point #13 at 2.42e+11 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(2.8748e-06) None  Grid-point #13 at 2.42e+11 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(2.8748e-06) None  Grid-point #13 at 2.42e+11 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(2.8748e-06) None  Grid-point #13 at 2.42e+11 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(2.8748e-06) None  Grid-point #13 at 2.42e+11 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+11
-#> Next point at 2.42e+12 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> search[ 2.42e+11 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(9.09091e-07) None  Grid-point #14 at 2.42e+12 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(9.09091e-07) None  Grid-point #14 at 2.42e+12 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(9.09091e-07) None  Grid-point #14 at 2.42e+12 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(9.09091e-07) None  Grid-point #14 at 2.42e+12 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(9.09091e-07) None  Grid-point #14 at 2.42e+12 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(9.09091e-07) None  Grid-point #14 at 2.42e+12 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(9.09091e-07) None  Grid-point #14 at 2.42e+12 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(9.09091e-07) None  Grid-point #14 at 2.42e+12 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(9.09091e-07) None  Grid-point #14 at 2.42e+12 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(9.09091e-07) None  Grid-point #14 at 2.42e+12 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+12
-#> Next point at 2.42e+13 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> search[ 2.42e+11 ] = 783.143(89.2332)
-#> search[ 2.42e+12 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(2.8748e-07) None  Grid-point #15 at 2.42e+13 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(2.8748e-07) None  Grid-point #15 at 2.42e+13 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(2.8748e-07) None  Grid-point #15 at 2.42e+13 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(2.8748e-07) None  Grid-point #15 at 2.42e+13 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(2.8748e-07) None  Grid-point #15 at 2.42e+13 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(2.8748e-07) None  Grid-point #15 at 2.42e+13 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(2.8748e-07) None  Grid-point #15 at 2.42e+13 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(2.8748e-07) None  Grid-point #15 at 2.42e+13 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(2.8748e-07) None  Grid-point #15 at 2.42e+13 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(2.8748e-07) None  Grid-point #15 at 2.42e+13 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+13
-#> Next point at 2.42e+14 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> search[ 2.42e+11 ] = 783.143(89.2332)
-#> search[ 2.42e+12 ] = 783.143(89.2332)
-#> search[ 2.42e+13 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(9.09091e-08) None  Grid-point #16 at 2.42e+14 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(9.09091e-08) None  Grid-point #16 at 2.42e+14 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(9.09091e-08) None  Grid-point #16 at 2.42e+14 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(9.09091e-08) None  Grid-point #16 at 2.42e+14 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(9.09091e-08) None  Grid-point #16 at 2.42e+14 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(9.09091e-08) None  Grid-point #16 at 2.42e+14 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(9.09091e-08) None  Grid-point #16 at 2.42e+14 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(9.09091e-08) None  Grid-point #16 at 2.42e+14 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(9.09091e-08) None  Grid-point #16 at 2.42e+14 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(9.09091e-08) None  Grid-point #16 at 2.42e+14 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+14
-#> Next point at 2.42e+15 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> search[ 2.42e+11 ] = 783.143(89.2332)
-#> search[ 2.42e+12 ] = 783.143(89.2332)
-#> search[ 2.42e+13 ] = 783.143(89.2332)
-#> search[ 2.42e+14 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(2.8748e-08) None  Grid-point #17 at 2.42e+15 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(2.8748e-08) None  Grid-point #17 at 2.42e+15 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(2.8748e-08) None  Grid-point #17 at 2.42e+15 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(2.8748e-08) None  Grid-point #17 at 2.42e+15 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(2.8748e-08) None  Grid-point #17 at 2.42e+15 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(2.8748e-08) None  Grid-point #17 at 2.42e+15 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(2.8748e-08) None  Grid-point #17 at 2.42e+15 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(2.8748e-08) None  Grid-point #17 at 2.42e+15 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(2.8748e-08) None  Grid-point #17 at 2.42e+15 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(2.8748e-08) None  Grid-point #17 at 2.42e+15 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+15
-#> Next point at 2.42e+16 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> search[ 2.42e+11 ] = 783.143(89.2332)
-#> search[ 2.42e+12 ] = 783.143(89.2332)
-#> search[ 2.42e+13 ] = 783.143(89.2332)
-#> search[ 2.42e+14 ] = 783.143(89.2332)
-#> search[ 2.42e+15 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(9.09091e-09) None  Grid-point #18 at 2.42e+16 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(9.09091e-09) None  Grid-point #18 at 2.42e+16 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(9.09091e-09) None  Grid-point #18 at 2.42e+16 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(9.09091e-09) None  Grid-point #18 at 2.42e+16 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(9.09091e-09) None  Grid-point #18 at 2.42e+16 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(9.09091e-09) None  Grid-point #18 at 2.42e+16 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(9.09091e-09) None  Grid-point #18 at 2.42e+16 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(9.09091e-09) None  Grid-point #18 at 2.42e+16 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(9.09091e-09) None  Grid-point #18 at 2.42e+16 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(9.09091e-09) None  Grid-point #18 at 2.42e+16 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+16
-#> Next point at 2.42e+17 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> search[ 2.42e+11 ] = 783.143(89.2332)
-#> search[ 2.42e+12 ] = 783.143(89.2332)
-#> search[ 2.42e+13 ] = 783.143(89.2332)
-#> search[ 2.42e+14 ] = 783.143(89.2332)
-#> search[ 2.42e+15 ] = 783.143(89.2332)
-#> search[ 2.42e+16 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(2.8748e-09) None  Grid-point #19 at 2.42e+17 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(2.8748e-09) None  Grid-point #19 at 2.42e+17 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(2.8748e-09) None  Grid-point #19 at 2.42e+17 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(2.8748e-09) None  Grid-point #19 at 2.42e+17 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(2.8748e-09) None  Grid-point #19 at 2.42e+17 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(2.8748e-09) None  Grid-point #19 at 2.42e+17 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(2.8748e-09) None  Grid-point #19 at 2.42e+17 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(2.8748e-09) None  Grid-point #19 at 2.42e+17 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(2.8748e-09) None  Grid-point #19 at 2.42e+17 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(2.8748e-09) None  Grid-point #19 at 2.42e+17 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+17
-#> Next point at 2.42e+18 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> search[ 2.42e+11 ] = 783.143(89.2332)
-#> search[ 2.42e+12 ] = 783.143(89.2332)
-#> search[ 2.42e+13 ] = 783.143(89.2332)
-#> search[ 2.42e+14 ] = 783.143(89.2332)
-#> search[ 2.42e+15 ] = 783.143(89.2332)
-#> search[ 2.42e+16 ] = 783.143(89.2332)
-#> search[ 2.42e+17 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(9.09091e-10) None  Grid-point #20 at 2.42e+18 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(9.09091e-10) None  Grid-point #20 at 2.42e+18 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(9.09091e-10) None  Grid-point #20 at 2.42e+18 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(9.09091e-10) None  Grid-point #20 at 2.42e+18 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(9.09091e-10) None  Grid-point #20 at 2.42e+18 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(9.09091e-10) None  Grid-point #20 at 2.42e+18 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(9.09091e-10) None  Grid-point #20 at 2.42e+18 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(9.09091e-10) None  Grid-point #20 at 2.42e+18 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(9.09091e-10) None  Grid-point #20 at 2.42e+18 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(9.09091e-10) None  Grid-point #20 at 2.42e+18 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+18
-#> Next point at 2.42e+19 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> search[ 2.42e+11 ] = 783.143(89.2332)
-#> search[ 2.42e+12 ] = 783.143(89.2332)
-#> search[ 2.42e+13 ] = 783.143(89.2332)
-#> search[ 2.42e+14 ] = 783.143(89.2332)
-#> search[ 2.42e+15 ] = 783.143(89.2332)
-#> search[ 2.42e+16 ] = 783.143(89.2332)
-#> search[ 2.42e+17 ] = 783.143(89.2332)
-#> search[ 2.42e+18 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(2.8748e-10) None  Grid-point #21 at 2.42e+19 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(2.8748e-10) None  Grid-point #21 at 2.42e+19 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(2.8748e-10) None  Grid-point #21 at 2.42e+19 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(2.8748e-10) None  Grid-point #21 at 2.42e+19 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(2.8748e-10) None  Grid-point #21 at 2.42e+19 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(2.8748e-10) None  Grid-point #21 at 2.42e+19 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(2.8748e-10) None  Grid-point #21 at 2.42e+19 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(2.8748e-10) None  Grid-point #21 at 2.42e+19 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(2.8748e-10) None  Grid-point #21 at 2.42e+19 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(2.8748e-10) None  Grid-point #21 at 2.42e+19 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+19
-#> Next point at 2.42e+20 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> search[ 2.42e+11 ] = 783.143(89.2332)
-#> search[ 2.42e+12 ] = 783.143(89.2332)
-#> search[ 2.42e+13 ] = 783.143(89.2332)
-#> search[ 2.42e+14 ] = 783.143(89.2332)
-#> search[ 2.42e+15 ] = 783.143(89.2332)
-#> search[ 2.42e+16 ] = 783.143(89.2332)
-#> search[ 2.42e+17 ] = 783.143(89.2332)
-#> search[ 2.42e+18 ] = 783.143(89.2332)
-#> search[ 2.42e+19 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(9.09091e-11) None  Grid-point #22 at 2.42e+20 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(9.09091e-11) None  Grid-point #22 at 2.42e+20 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(9.09091e-11) None  Grid-point #22 at 2.42e+20 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(9.09091e-11) None  Grid-point #22 at 2.42e+20 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(9.09091e-11) None  Grid-point #22 at 2.42e+20 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(9.09091e-11) None  Grid-point #22 at 2.42e+20 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(9.09091e-11) None  Grid-point #22 at 2.42e+20 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(9.09091e-11) None  Grid-point #22 at 2.42e+20 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(9.09091e-11) None  Grid-point #22 at 2.42e+20 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(9.09091e-11) None  Grid-point #22 at 2.42e+20 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+20
-#> Next point at 2.42e+21 with value 0 and continue = 1
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> search[ 2.42e+11 ] = 783.143(89.2332)
-#> search[ 2.42e+12 ] = 783.143(89.2332)
-#> search[ 2.42e+13 ] = 783.143(89.2332)
-#> search[ 2.42e+14 ] = 783.143(89.2332)
-#> search[ 2.42e+15 ] = 783.143(89.2332)
-#> search[ 2.42e+16 ] = 783.143(89.2332)
-#> search[ 2.42e+17 ] = 783.143(89.2332)
-#> search[ 2.42e+18 ] = 783.143(89.2332)
-#> search[ 2.42e+19 ] = 783.143(89.2332)
-#> search[ 2.42e+20 ] = 783.143(89.2332)
-#> 
-#> Running at Laplace(2.8748e-11) None  Grid-point #23 at 2.42e+21 	Fold #1 Rep #1 pred log like = 661.941
-#> Running at Laplace(2.8748e-11) None  Grid-point #23 at 2.42e+21 	Fold #2 Rep #1 pred log like = 634.978
-#> Running at Laplace(2.8748e-11) None  Grid-point #23 at 2.42e+21 	Fold #3 Rep #1 pred log like = 850.148
-#> Running at Laplace(2.8748e-11) None  Grid-point #23 at 2.42e+21 	Fold #4 Rep #1 pred log like = 914.645
-#> Running at Laplace(2.8748e-11) None  Grid-point #23 at 2.42e+21 	Fold #5 Rep #1 pred log like = 759.898
-#> Running at Laplace(2.8748e-11) None  Grid-point #23 at 2.42e+21 	Fold #6 Rep #1 pred log like = 779.094
-#> Running at Laplace(2.8748e-11) None  Grid-point #23 at 2.42e+21 	Fold #7 Rep #1 pred log like = 791.452
-#> Running at Laplace(2.8748e-11) None  Grid-point #23 at 2.42e+21 	Fold #8 Rep #1 pred log like = 885.139
-#> Running at Laplace(2.8748e-11) None  Grid-point #23 at 2.42e+21 	Fold #9 Rep #1 pred log like = 848.121
-#> Running at Laplace(2.8748e-11) None  Grid-point #23 at 2.42e+21 	Fold #10 Rep #1 pred log like = 706.01
-#> AvgPred = 783.143 with stdev = 89.2332
-#> Completed at 2.42e+21
-#> Next point at 9.51098e+12 with value 783.143 and continue = 0
-#> search[ 0.242 ] = 783.141(89.2243)
-#> search[ 2.42 ] = 783.142(89.2304)
-#> search[ 24.2 ] = 783.142(89.2323)
-#> search[ 242 ] = 783.143(89.233)
-#> search[ 2420 ] = 783.143(89.2332)
-#> search[ 24200 ] = 783.143(89.2332)
-#> search[ 242000 ] = 783.143(89.2332)
-#> search[ 2.42e+06 ] = 783.143(89.2332)
-#> search[ 2.42e+07 ] = 783.143(89.2332)
-#> search[ 2.42e+08 ] = 783.143(89.2332)
-#> search[ 2.42e+09 ] = 783.143(89.2332)
-#> search[ 2.42e+10 ] = 783.143(89.2332)
-#> search[ 2.42e+11 ] = 783.143(89.2332)
-#> search[ 2.42e+12 ] = 783.143(89.2332)
-#> search[ 2.42e+13 ] = 783.143(89.2332)
-#> search[ 2.42e+14 ] = 783.143(89.2332)
-#> search[ 2.42e+15 ] = 783.143(89.2332)
-#> search[ 2.42e+16 ] = 783.143(89.2332)
-#> search[ 2.42e+17 ] = 783.143(89.2332)
-#> search[ 2.42e+18 ] = 783.143(89.2332)
-#> search[ 2.42e+19 ] = 783.143(89.2332)
-#> search[ 2.42e+20 ] = 783.143(89.2332)
-#> search[ 2.42e+21 ] = 783.143(89.2332)
-#> 
-#> 
-#> Maximum predicted log likelihood (783.143) estimated at:
-#> 	9.51098e+12 (variance)
-#> 	4.58566e-07 (lambda)
-#> 
-#> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(4.58566e-07) None 

-#Find out what the optimal hyperparameter was:
-getHyperParameter(fit)
-
#> [1] 9.510983e+12

-#Extract the current log-likelihood, and coefficients
-logLik(fit)
-
#> 'log Lik.' -2207.566 (df=3)
coef(fit)
-
#> (Intercept)           1           2 
-#> -3.58685740  0.05610044 -0.02769318 

-#We can only retrieve the confidence interval for unregularized coefficients:
-confint(fit, c(0))
-
#> Using 1 thread(s)
#>      covariate     2.5 %    97.5 % evaluations
-#> [1,]         0 -3.616605 -3.557373          22
+
+

Examples

+ 
#Generate some simulated data:
+sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
+                           model = "poisson")
+#> Sparseness = 76.2 %
+cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
+                                    addIntercept = TRUE)
+#> Sorting covariates by covariateId and rowId
+
+#Define the prior and control objects to use cross-validation for finding the 
+#optimal hyperparameter:
+prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
+control <- createControl(cvType = "auto", noiseLevel = "quiet")
+
+#Fit the model
+fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
+#> Using cross-validation selector type byRow
+#> Performing 10-fold cross-validation [seed = 1698757934] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Using 1 thread(s)
+#> Starting var = 0.238 (default)
+#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #1 Rep #1 pred log like = 898.631
+#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #2 Rep #1 pred log like = 1378.61
+#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #3 Rep #1 pred log like = 1439.51
+#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #4 Rep #1 pred log like = 1227.83
+#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #5 Rep #1 pred log like = 1717.57
+#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #6 Rep #1 pred log like = 1272.34
+#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #7 Rep #1 pred log like = 1047.47
+#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #8 Rep #1 pred log like = 1266.38
+#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #9 Rep #1 pred log like = 1253.53
+#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #10 Rep #1 pred log like = 1346.96
+#> AvgPred = 1284.88 with stdev = 208.341
+#> Completed at 0.238
+#> Next point at 2.38 with value 0 and continue = 1
+#> search[ 0.238 ] = 1284.88(208.341)
+#> 
+#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #1 Rep #1 pred log like = 898.623
+#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #2 Rep #1 pred log like = 1378.57
+#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #3 Rep #1 pred log like = 1439.49
+#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #4 Rep #1 pred log like = 1227.81
+#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #5 Rep #1 pred log like = 1717.55
+#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #6 Rep #1 pred log like = 1272.36
+#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #7 Rep #1 pred log like = 1047.55
+#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #8 Rep #1 pred log like = 1266.43
+#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #9 Rep #1 pred log like = 1253.54
+#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #10 Rep #1 pred log like = 1346.91
+#> AvgPred = 1284.88 with stdev = 208.324
+#> Completed at 2.38
+#> Next point at 23.8 with value 0 and continue = 1
+#> search[ 0.238 ] = 1284.88(208.341)
+#> search[ 2.38 ] = 1284.88(208.324)
+#> 
+#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #1 Rep #1 pred log like = 898.62
+#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #2 Rep #1 pred log like = 1378.56
+#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #3 Rep #1 pred log like = 1439.48
+#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #4 Rep #1 pred log like = 1227.81
+#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #5 Rep #1 pred log like = 1717.54
+#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #6 Rep #1 pred log like = 1272.37
+#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #7 Rep #1 pred log like = 1047.58
+#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #8 Rep #1 pred log like = 1266.45
+#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #9 Rep #1 pred log like = 1253.54
+#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #10 Rep #1 pred log like = 1346.9
+#> AvgPred = 1284.88 with stdev = 208.318
+#> Completed at 23.8
+#> Next point at 5.37835 with value 1284.88 and continue = 0
+#> search[ 0.238 ] = 1284.88(208.341)
+#> search[ 2.38 ] = 1284.88(208.324)
+#> search[ 23.8 ] = 1284.88(208.318)
+#> 
+#> 
+#> Maximum predicted log likelihood (1284.88) estimated at:
+#> 	5.37835 (variance)
+#> 	0.609804 (lambda)
+#> 
+#> Fitting model at optimal hyperparameter
+#> Using prior: Laplace(0.609804) None 
+
+#Find out what the optimal hyperparameter was:
+getHyperParameter(fit)
+#> [1] 5.37835
+
+#Extract the current log-likelihood, and coefficients
+logLik(fit)
+#> 'log Lik.' -2158.207 (df=3)
+coef(fit)
+#> (Intercept)           1           2 
+#> -3.92974607 -0.02127371  1.41692709 
+
+#We can only retrieve the confidence interval for unregularized coefficients:
+confint(fit, c(0))
+#> Using 1 thread(s)
+#>             covariate     2.5 %  97.5 % evaluations
+#> (Intercept)         0 -3.962925 -3.8969          22
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/createWeightBasedSearchControl.html b/docs/reference/createWeightBasedSearchControl.html new file mode 100644 index 00000000..0b35f3ec --- /dev/null +++ b/docs/reference/createWeightBasedSearchControl.html @@ -0,0 +1,113 @@ + +Create a Cyclops control object that supports in- / out-of-sample hyperparameter search using weights — createWeightBasedSearchControl • Cyclops + + +
+
+ + + +
+
+
+

Create a Cyclops control object that supports in- / out-of-sample hyperparameter search using weights

+ Source: R/WeightBasedSearchControl.R + +
+ +
+

createWeightBasedSearchControl creates a Cyclops control object for use with fitCyclopsModel +that supports hyperparameter optimization through an auto-search where weight = 1 identifies in-sample observations +and weight = 0 identifies out-of-sample observations.

+
+ +
+ 
createWeightBasedSearchControl(cvType = "auto", initialValue = 1, ...)
+
+ +
+

Arguments

+
cvType
+

Must equal "auto"

+ + +
initialValue
+

Initial value for auto-search parameter

+ + +
...
+

Additional parameters passed through to createControl

+ +
+
+

Value

+ + +

A Cyclops prior object of class inheriting from "cyclopsControl"

+ + +

for use with fitCyclopsModel.

+
+ +
+ +
+ + +
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+ +
+

Site built with pkgdown 2.0.7.

+
+ +
+ + + + + + + + diff --git a/docs/reference/cyclops.html b/docs/reference/cyclops.html index 53faae39..349f61d6 100644 --- a/docs/reference/cyclops.html +++ b/docs/reference/cyclops.html @@ -1,71 +1,16 @@ - - - - - - - -Cyclops: Cyclic coordinate descent for logistic, Poisson and survival analysis — cyclops • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Cyclops: Cyclic coordinate descent for logistic, Poisson and survival analysis — cyclops • Cyclops - - - - - - - - - - + + - - - -
-
- -
- -
+

Cyclops: Cyclic coordinate descent for logistic, Poisson and survival analysis

- Source: R/cyclops.R + Source: R/cyclops.R
@@ -133,32 +65,27 @@

Cyclops: Cyclic coordinate descent for logistic, Poisson and survival analys -

+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/finalizeSqlCyclopsData.html b/docs/reference/finalizeSqlCyclopsData.html index 09794054..7bececa1 100644 --- a/docs/reference/finalizeSqlCyclopsData.html +++ b/docs/reference/finalizeSqlCyclopsData.html @@ -1,67 +1,12 @@ - - - - - - - -finalizeSqlCyclopsData — finalizeSqlCyclopsData • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -finalizeSqlCyclopsData — finalizeSqlCyclopsData • Cyclops - - + + - - -
-
- -
- -
+

finalizeSqlCyclopsData

- Source: R/DataManagement.R + Source: R/DataManagement.R
@@ -123,73 +55,68 @@

finalizeSqlCyclopsData

finalizeSqlCyclopsData finalizes a Cyclops data object

- 
finalizeSqlCyclopsData(
-  object,
-  addIntercept = FALSE,
-  useOffsetCovariate = NULL,
-  offsetAlreadyOnLogScale = FALSE,
-  sortCovariates = FALSE,
-  makeCovariatesDense = NULL
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - -
object

Cyclops data object

addIntercept

Add an intercept covariate if one was not imported through SQL

useOffsetCovariate

Specify is a covariate should be used as an offset (fixed coefficient = 1). +

+ 
finalizeSqlCyclopsData(
+  object,
+  addIntercept = FALSE,
+  useOffsetCovariate = NULL,
+  offsetAlreadyOnLogScale = FALSE,
+  sortCovariates = FALSE,
+  makeCovariatesDense = NULL
+)
+
+ +
+

Arguments

+
object
+

Cyclops data object

+ + +
addIntercept
+

Add an intercept covariate if one was not imported through SQL

+ + +
useOffsetCovariate
+

Specify is a covariate should be used as an offset (fixed coefficient = 1). Set option to -1 to specify the time-to-event column, -otherwise include a single numeric or character covariate name.

offsetAlreadyOnLogScale

Set to TRUE to indicate that offsets were log-transformed before importing into Cyclops data object.

sortCovariates

Sort covariates in numeric-order with intercept first if it exists.

makeCovariatesDense

List of numeric or character covariates names to densely represent in Cyclops data object. -For efficiency, we suggest making at least the intercept dense.

+otherwise include a single numeric or character covariate name.

+ + +
offsetAlreadyOnLogScale
+

Set to TRUE to indicate that offsets were log-transformed before importing into Cyclops data object.

+ +
sortCovariates
+

Sort covariates in numeric-order with intercept first if it exists.

+ + +
makeCovariatesDense
+

List of numeric or character covariates names to densely represent in Cyclops data object. +For efficiency, we suggest making at least the intercept dense.

+ +
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/fitCyclopsModel.html b/docs/reference/fitCyclopsModel.html index ffccc03f..1be94590 100644 --- a/docs/reference/fitCyclopsModel.html +++ b/docs/reference/fitCyclopsModel.html @@ -1,67 +1,12 @@ - - - - - - - -Fit a Cyclops model — fitCyclopsModel • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Fit a Cyclops model — fitCyclopsModel • Cyclops - - - - + + -
-
- -
- -
+

Fit a Cyclops model

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -123,78 +55,80 @@

Fit a Cyclops model

fitCyclopsModel fits a Cyclops model data object

- 
fitCyclopsModel(
-  cyclopsData,
-  prior = createPrior("none"),
-  control = createControl(),
-  weights = NULL,
-  forceNewObject = FALSE,
-  returnEstimates = TRUE,
-  startingCoefficients = NULL,
-  fixedCoefficients = NULL,
-  computeDevice = "native"
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
cyclopsData

A Cyclops data object

prior

A prior object. More details are given below.

control

A "cyclopsControl" object constructed by createControl

weights

Vector of 0/1 weights for each data row

forceNewObject

Logical, forces the construction of a new Cyclops model fit object

returnEstimates

Logical, return regression coefficient estimates in Cyclops model fit object

startingCoefficients

Vector of starting values for optimization

fixedCoefficients

Vector of booleans indicating if coefficient should be fix

computeDevice

String: Name of compute device to employ; defaults to "native" C++ on CPU

- -

Value

- -

A list that contains a Cyclops model fit object pointer and an operation duration

-

Details

+
+ 
fitCyclopsModel(
+  cyclopsData,
+  prior = createPrior("none"),
+  control = createControl(),
+  weights = NULL,
+  forceNewObject = FALSE,
+  returnEstimates = TRUE,
+  startingCoefficients = NULL,
+  fixedCoefficients = NULL,
+  warnings = TRUE,
+  computeDevice = "native"
+)
+
-

This function performs numerical optimization to fit a Cyclops model data object.

-

Prior

+
+

Arguments

+
cyclopsData
+

A Cyclops data object

- -

Currently supported prior types are:

- - - -
"none"Useful for finding MLE
"laplace"L_1 regularization
"normal"L_2 regularization
+
prior
+

A prior object. More details are given below.

+ + +
control
+

A "cyclopsControl" object constructed by createControl

+ + +
weights
+

Vector of 0/1 weights for each data row

+ + +
forceNewObject
+

Logical, forces the construction of a new Cyclops model fit object

+ + +
returnEstimates
+

Logical, return regression coefficient estimates in Cyclops model fit object

+ + +
startingCoefficients
+

Vector of starting values for optimization

+ +
fixedCoefficients
+

Vector of booleans indicating if coefficient should be fix

-

References

+
warnings
+

Logical, report regularization warnings

+ + +
computeDevice
+

String: Name of compute device to employ; defaults to "native" C++ on CPU

+ +
+
+

Value

+ + +

A list that contains a Cyclops model fit object pointer and an operation duration

+
+
+

Details

+

This function performs numerical optimization to fit a Cyclops model data object.

+
+
+

Prior

+ + +

Currently supported prior types are:

"none"Useful for finding MLE
"laplace"L_1 regularization
"normal"L_2 regularization
+
+

References

Suchard MA, Simpson SE, Zorych I, Ryan P, Madigan D. Massive parallelization of serial inference algorithms for complex generalized linear models. ACM Transactions on Modeling and Computer Simulation, 23, 10, 2013.

@@ -204,50 +138,52 @@

R

Mittal S, Madigan D, Burd RS, Suchard MA. High-dimensional, massive sample-size Cox proportional hazards regression for survival analysis. Biostatistics, 15, 207-221, 2014.

+

-

Examples

- 
## Dobson (1990) Page 93: Randomized Controlled Trial :
-counts <- c(18,17,15,20,10,20,25,13,12)
-outcome <- gl(3,1,9)
-treatment <- gl(3,3)
-cyclopsData <- createCyclopsData(counts ~ outcome + treatment, modelType = "pr")
-cyclopsFit <- fitCyclopsModel(cyclopsData, prior = createPrior("none"))
-coef(cyclopsFit)
-
#>   (Intercept)      outcome2      outcome3    treatment2    treatment3 
-#>  3.044510e+00 -4.542553e-01 -2.929871e-01  1.268003e-05  1.268003e-05 
confint(cyclopsFit, c("outcome2","treatment3"))
-
#>            covariate      2.5 %      97.5 % evaluations
-#> outcome2           2 -0.8576926 -0.06254563          22
-#> treatment3         5 -0.3931725  0.39317270          28
predict(cyclopsFit)
-
#>        1        2        3        4        5        6        7        8 
-#> 20.99973 13.33316 15.66647 21.00000 13.33333 15.66667 21.00000 13.33333 
-#>        9 
-#> 15.66667 

-
+
+

Examples

+ 
## Dobson (1990) Page 93: Randomized Controlled Trial :
+counts <- c(18,17,15,20,10,20,25,13,12)
+outcome <- gl(3,1,9)
+treatment <- gl(3,3)
+cyclopsData <- createCyclopsData(counts ~ outcome + treatment, modelType = "pr")
+cyclopsFit <- fitCyclopsModel(cyclopsData, prior = createPrior("none"))
+coef(cyclopsFit)
+#>   (Intercept)      outcome2      outcome3    treatment2    treatment3 
+#>  3.044510e+00 -4.542553e-01 -2.929871e-01  1.268003e-05  1.268003e-05 
+confint(cyclopsFit, c("outcome2","treatment3"))
+#>            covariate      2.5 %      97.5 % evaluations
+#> outcome2           2 -0.8576926 -0.06254563          22
+#> treatment3         5 -0.3931725  0.39317270          28
+predict(cyclopsFit)
+#>        1        2        3        4        5        6        7        8 
+#> 20.99973 13.33316 15.66647 21.00000 13.33333 15.66667 21.00000 13.33333 
+#>        9 
+#> 15.66667 
+
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/fitCyclopsSimulation.html b/docs/reference/fitCyclopsSimulation.html index 1a315f32..6f7dd885 100644 --- a/docs/reference/fitCyclopsSimulation.html +++ b/docs/reference/fitCyclopsSimulation.html @@ -1,69 +1,14 @@ - - - - - - - -Fit simulated data — fitCyclopsSimulation • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Fit simulated data — fitCyclopsSimulation • Cyclops - - - - - - - - - - + + - - - -
-
- -
- -
+

Fit simulated data

- Source: R/Simulation.R + Source: R/Simulation.R
@@ -127,65 +59,60 @@

Fit simulated data

large, sparse datasets.

- 
fitCyclopsSimulation(
-  sim,
-  useCyclops = TRUE,
-  model = "logistic",
-  coverage = TRUE,
-  includePenalty = FALSE
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - -
sim

A simulated Cyclops dataset generated via simulateCyclopsData

useCyclops

Logical: use Cyclops or a standard routine

model

String: Fitted regression model type

coverage

Logical: report coverage statistics

includePenalty

Logical: include regularized regression penalty in computing profile likelihood based confidence intervals

+
+ 
fitCyclopsSimulation(
+  sim,
+  useCyclops = TRUE,
+  model = "logistic",
+  coverage = TRUE,
+  includePenalty = FALSE
+)
+
+ +
+

Arguments

+
sim
+

A simulated Cyclops dataset generated via simulateCyclopsData

+
useCyclops
+

Logical: use Cyclops or a standard routine

+ + +
model
+

String: Fitted regression model type

+ + +
coverage
+

Logical: report coverage statistics

+ + +
includePenalty
+

Logical: include regularized regression penalty in computing profile likelihood based confidence intervals

+ +
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getCovariateIds.html b/docs/reference/getCovariateIds.html index 7d7c12f4..91c960cb 100644 --- a/docs/reference/getCovariateIds.html +++ b/docs/reference/getCovariateIds.html @@ -1,67 +1,12 @@ - - - - - - - -Get covariate identifiers — getCovariateIds • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Get covariate identifiers — getCovariateIds • Cyclops - + + - - - -
-
- -
- -
+

Get covariate identifiers

- Source: R/RcppExports.R + Source: R/RcppExports.R
@@ -123,43 +55,38 @@

Get covariate identifiers

getCovariateIds returns a vector of integer64 covariate identifiers in a Cyclops data object

- 
getCovariateIds(object)
+
+ 
getCovariateIds(object)
+
-

Arguments

- - - - - - -
object

A Cyclops data object

+
+

Arguments

+
object
+

A Cyclops data object

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getCovariateTypes.html b/docs/reference/getCovariateTypes.html index 147277de..0706764c 100644 --- a/docs/reference/getCovariateTypes.html +++ b/docs/reference/getCovariateTypes.html @@ -1,67 +1,12 @@ - - - - - - - -Get covariate types — getCovariateTypes • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Get covariate types — getCovariateTypes • Cyclops - - + + - - -
-
- -
- -
+

Get covariate types

- Source: R/DataManagement.R + Source: R/DataManagement.R
@@ -123,47 +55,42 @@

Get covariate types

getCovariateTypes returns a vector covariate types in a Cyclops data object

- 
getCovariateTypes(object, covariateLabel)
+
+ 
getCovariateTypes(object, covariateLabel)
+
+ +
+

Arguments

+
object
+

A Cyclops data object

+ -

Arguments

- - - - - - - - - - -
object

A Cyclops data object

covariateLabel

Integer vector: covariate identifiers to return

+
covariateLabel
+

Integer vector: covariate identifiers to return

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getCrossValidationInfo.html b/docs/reference/getCrossValidationInfo.html index 874154f0..361f1128 100644 --- a/docs/reference/getCrossValidationInfo.html +++ b/docs/reference/getCrossValidationInfo.html @@ -1,67 +1,12 @@ - - - - - - - -Get cross-validation information from a Cyclops model fit — getCrossValidationInfo • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Get cross-validation information from a Cyclops model fit — getCrossValidationInfo • Cyclops - + + - - - -
-
- -
- -
+

Get cross-validation information from a Cyclops model fit

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -123,43 +55,38 @@

Get cross-validation information from a Cyclops model fit

getCrossValidationInfo returns the predicted optimal cross-validation point and ordinate

- 
getCrossValidationInfo(object)
+
+ 
getCrossValidationInfo(object)
+
-

Arguments

- - - - - - -
object

A Cyclops model fit object

+
+

Arguments

+
object
+

A Cyclops model fit object

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getCyclopsPredictiveLogLikelihood.html b/docs/reference/getCyclopsPredictiveLogLikelihood.html index 4db67f23..09256f0d 100644 --- a/docs/reference/getCyclopsPredictiveLogLikelihood.html +++ b/docs/reference/getCyclopsPredictiveLogLikelihood.html @@ -1,67 +1,12 @@ - - - - - - - -Compute predictive log-likelihood from a Cyclops model fit — getCyclopsPredictiveLogLikelihood • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Compute predictive log-likelihood from a Cyclops model fit — getCyclopsPredictiveLogLikelihood • Cyclops - - - - + + -
-
- -
- -
+

Compute predictive log-likelihood from a Cyclops model fit

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -123,50 +55,48 @@

Compute predictive log-likelihood from a Cyclops model fit

getCyclopsPredictiveLogLikelihood returns the log-likelihood of a subset of the data in a Cyclops model fit object.

- 
getCyclopsPredictiveLogLikelihood(object, weights)
+
+ 
getCyclopsPredictiveLogLikelihood(object, weights)
+
+ +
+

Arguments

+
object
+

A Cyclops model fit object

-

Arguments

- - - - - - - - - - -
object

A Cyclops model fit object

weights

Numeric vector: vector of 0/1 identifying subset (=1) of rows from object to use in computing the log-likelihood

-

Value

+
weights
+

Numeric vector: vector of 0/1 identifying subset (=1) of rows from object to use in computing the log-likelihood

-

The predictive log-likelihood

+
+
+

Value

+ + +

The predictive log-likelihood

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getCyclopsProfileLogLikelihood.html b/docs/reference/getCyclopsProfileLogLikelihood.html index 6b2b4ae9..f901fcf2 100644 --- a/docs/reference/getCyclopsProfileLogLikelihood.html +++ b/docs/reference/getCyclopsProfileLogLikelihood.html @@ -1,67 +1,12 @@ - - - - - - - -Profile likelihood for Cyclops model parameters — getCyclopsProfileLogLikelihood • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Profile likelihood for Cyclops model parameters — getCyclopsProfileLogLikelihood • Cyclops - - + + - - -
-
- -
- -
+

Profile likelihood for Cyclops model parameters

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -123,80 +55,78 @@

Profile likelihood for Cyclops model parameters

getCyclopsProfileLogLikelihood evaluates the profile likelihood at a grid of parameter values.

- 
getCyclopsProfileLogLikelihood(
-  object,
-  parm,
-  x = NULL,
-  bounds = NULL,
-  tolerance = 0.001,
-  initialGridSize = 10,
-  includePenalty = TRUE
-)
- -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
object

Fitted Cyclops model object

parm

Specification of which parameter requires profiling, -either a vector of numbers of covariateId names

x

Vector of values of the parameter

bounds

Pair of values to bound adaptive profiling

tolerance

Absolute tolerance allowed for adaptive profiling

initialGridSize

Initial grid size for adaptive profiling

includePenalty

Logical: Include regularized covariate penalty in profile

- -

Value

- -

A data frame containing the profile log likelihood. Returns NULL when the adaptive profiling fails +

+ 
getCyclopsProfileLogLikelihood(
+  object,
+  parm,
+  x = NULL,
+  bounds = NULL,
+  tolerance = 0.001,
+  initialGridSize = 10,
+  includePenalty = TRUE
+)
+
+ +
+

Arguments

+
object
+

Fitted Cyclops model object

+ + +
parm
+

Specification of which parameter requires profiling, +either a vector of numbers of covariateId names

+ + +
x
+

Vector of values of the parameter

+ + +
bounds
+

Pair of values to bound adaptive profiling

+ + +
tolerance
+

Absolute tolerance allowed for adaptive profiling

+ + +
initialGridSize
+

Initial grid size for adaptive profiling

+ + +
includePenalty
+

Logical: Include regularized covariate penalty in profile

+ +
+
+

Value

+ + +

A data frame containing the profile log likelihood. Returns NULL when the adaptive profiling fails to converge.

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getFineGrayWeights.html b/docs/reference/getFineGrayWeights.html index cbb03913..39546846 100644 --- a/docs/reference/getFineGrayWeights.html +++ b/docs/reference/getFineGrayWeights.html @@ -1,67 +1,12 @@ - - - - - - - -Creates a Surv object that forces in competing risks and the IPCW needed for Fine-Gray estimation. — getFineGrayWeights • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Creates a Surv object that forces in competing risks and the IPCW needed for Fine-Gray estimation. — getFineGrayWeights • Cyclops - - - - + + -
-
- -
- -
+

Creates a Surv object that forces in competing risks and the IPCW needed for Fine-Gray estimation.

- Source: R/GetFrineGrayWeights.R + Source: R/GetFrineGrayWeights.R
@@ -123,68 +55,69 @@

Creates a Surv object that forces in competing risks and the IP

getFineGrayWeights creates a list Surv object and vector of weights required for estimation.

- 
getFineGrayWeights(ftime, fstatus, cencode = 0, failcode = 1)
- -

Arguments

- - - - - - - - - - - - - - - - - - -
ftime

Numeric: Observed event (failure) times

fstatus

Numeric: Observed event (failure) types

cencode

Numeric: Code to denote censored observations (Default is 0)

failcode

Numeric: Code to denote event of interest (Default is 1)

- -

Value

- -

A list that returns both an object of class Surv that forces in the competing risks indicators and a vector of weights needed for parameter estimation.

- -

Examples

- 
ftime <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
-fstatus <- c(1, 2, 0, 1, 2, 0, 1, 2, 0, 1)
-getFineGrayWeights(ftime, fstatus, cencode = 0, failcode = 1)
-
#> $surv
-#>  [1]  1   2   3+  4   5   6+  7   8   9+ 10 
-#> 
-#> $weights
-#>  [1] 1.000 1.000 1.000 0.875 0.875 0.875 0.700 0.700 0.700 0.350
-#>
+
+ 
getFineGrayWeights(ftime, fstatus, cencode = 0, failcode = 1)
+
+ +
+

Arguments

+
ftime
+

Numeric: Observed event (failure) times

+ + +
fstatus
+

Numeric: Observed event (failure) types

+ + +
cencode
+

Numeric: Code to denote censored observations (Default is 0)

+ + +
failcode
+

Numeric: Code to denote event of interest (Default is 1)

+ +
+
+

Value

+ + +

A list that returns both an object of class Surv that forces in the competing risks indicators and a vector of weights needed for parameter estimation.

+
+ +
+

Examples

+ 
ftime <- c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
+fstatus <- c(1, 2, 0, 1, 2, 0, 1, 2, 0, 1)
+getFineGrayWeights(ftime, fstatus, cencode = 0, failcode = 1)
+#> $surv
+#>  [1]  1   2   3+  4   5   6+  7   8   9+ 10 
+#> 
+#> $weights
+#>  [1] 1.000 1.000 1.000 0.875 0.875 0.875 0.700 0.700 0.700 0.350
+#> 
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getFloatingPointSize.html b/docs/reference/getFloatingPointSize.html index 4f99ad41..02252c17 100644 --- a/docs/reference/getFloatingPointSize.html +++ b/docs/reference/getFloatingPointSize.html @@ -1,67 +1,12 @@ - - - - - - - -Get floating point size — getFloatingPointSize • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Get floating point size — getFloatingPointSize • Cyclops - + + - - - -
-
- -
- -
+

Get floating point size

- Source: R/RcppExports.R + Source: R/RcppExports.R
@@ -123,43 +55,38 @@

Get floating point size

getFloatingPointSize returns the floating-point representation size in a Cyclops data object

- 
getFloatingPointSize(object)
+
+ 
getFloatingPointSize(object)
+
-

Arguments

- - - - - - -
object

A Cyclops data object

+
+

Arguments

+
object
+

A Cyclops data object

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getHyperParameter.html b/docs/reference/getHyperParameter.html index 7a3b09a7..961106f3 100644 --- a/docs/reference/getHyperParameter.html +++ b/docs/reference/getHyperParameter.html @@ -1,67 +1,12 @@ - - - - - - - -Get hyperparameter — getHyperParameter • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Get hyperparameter — getHyperParameter • Cyclops - - + + - - -
-
- -
- -
+

Get hyperparameter

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -123,165 +55,646 @@

Get hyperparameter

getHyperParameter returns the current hyper parameter in a Cyclops model fit object

- 
getHyperParameter(object)
- -

Arguments

- - - - - - -
object

A Cyclops model fit object

- - -

Examples

- 
#Generate some simulated data:
-sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
-                           model = "poisson")
-
#> Sparseness = 75.45 %
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
-                                    addIntercept = TRUE)
-
#> Sorting covariates by covariateId and rowId

-#Define the prior and control objects to use cross-validation for finding the 
-#optimal hyperparameter:
-prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
-control <- createControl(cvType = "auto", noiseLevel = "quiet")
+    

+    
getHyperParameter(object)

+    

 
-#Fit the model
-fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
-
#> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1623936646] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
-#> Using 1 thread(s)
-#> Starting var = 0.2455 (default)
-#> Running at Laplace(2.85423) None  Grid-point #1 at 0.2455 	Fold #1 Rep #1 pred log like = 200.993
-#> Running at Laplace(2.85423) None  Grid-point #1 at 0.2455 	Fold #2 Rep #1 pred log like = 206.093
-#> Running at Laplace(2.85423) None  Grid-point #1 at 0.2455 	Fold #3 Rep #1 pred log like = 245.023
-#> Running at Laplace(2.85423) None  Grid-point #1 at 0.2455 	Fold #4 Rep #1 pred log like = 264.254
-#> Running at Laplace(2.85423) None  Grid-point #1 at 0.2455 	Fold #5 Rep #1 pred log like = 332.052
-#> Running at Laplace(2.85423) None  Grid-point #1 at 0.2455 	Fold #6 Rep #1 pred log like = 241.658
-#> Running at Laplace(2.85423) None  Grid-point #1 at 0.2455 	Fold #7 Rep #1 pred log like = 267.085
-#> Running at Laplace(2.85423) None  Grid-point #1 at 0.2455 	Fold #8 Rep #1 pred log like = 309.134
-#> Running at Laplace(2.85423) None  Grid-point #1 at 0.2455 	Fold #9 Rep #1 pred log like = 215.561
-#> Running at Laplace(2.85423) None  Grid-point #1 at 0.2455 	Fold #10 Rep #1 pred log like = 236.844
-#> AvgPred = 251.87 with stdev = 40.5863
-#> Completed at 0.2455
-#> Next point at 2.455 with value 0 and continue = 1
-#> search[ 0.2455 ] = 251.87(40.5863)
-#> 
-#> Running at Laplace(0.902587) None  Grid-point #2 at 2.455 	Fold #1 Rep #1 pred log like = 201.025
-#> Running at Laplace(0.902587) None  Grid-point #2 at 2.455 	Fold #2 Rep #1 pred log like = 206.105
-#> Running at Laplace(0.902587) None  Grid-point #2 at 2.455 	Fold #3 Rep #1 pred log like = 244.985
-#> Running at Laplace(0.902587) None  Grid-point #2 at 2.455 	Fold #4 Rep #1 pred log like = 264.222
-#> Running at Laplace(0.902587) None  Grid-point #2 at 2.455 	Fold #5 Rep #1 pred log like = 332.034
-#> Running at Laplace(0.902587) None  Grid-point #2 at 2.455 	Fold #6 Rep #1 pred log like = 241.635
-#> Running at Laplace(0.902587) None  Grid-point #2 at 2.455 	Fold #7 Rep #1 pred log like = 267.08
-#> Running at Laplace(0.902587) None  Grid-point #2 at 2.455 	Fold #8 Rep #1 pred log like = 309.102
-#> Running at Laplace(0.902587) None  Grid-point #2 at 2.455 	Fold #9 Rep #1 pred log like = 215.544
-#> Running at Laplace(0.902587) None  Grid-point #2 at 2.455 	Fold #10 Rep #1 pred log like = 236.821
-#> AvgPred = 251.855 with stdev = 40.5755
-#> Completed at 2.455
-#> Next point at 0.02455 with value 0 and continue = 1
-#> search[ 0.2455 ] = 251.87(40.5863)
-#> search[ 2.455 ] = 251.855(40.5755)
-#> 
-#> Running at Laplace(9.02587) None  Grid-point #3 at 0.02455 	Fold #1 Rep #1 pred log like = 200.993
-#> Running at Laplace(9.02587) None  Grid-point #3 at 0.02455 	Fold #2 Rep #1 pred log like = 206.063
-#> Running at Laplace(9.02587) None  Grid-point #3 at 0.02455 	Fold #3 Rep #1 pred log like = 245.129
-#> Running at Laplace(9.02587) None  Grid-point #3 at 0.02455 	Fold #4 Rep #1 pred log like = 264.304
-#> Running at Laplace(9.02587) None  Grid-point #3 at 0.02455 	Fold #5 Rep #1 pred log like = 332.096
-#> Running at Laplace(9.02587) None  Grid-point #3 at 0.02455 	Fold #6 Rep #1 pred log like = 241.667
-#> Running at Laplace(9.02587) None  Grid-point #3 at 0.02455 	Fold #7 Rep #1 pred log like = 267.089
-#> Running at Laplace(9.02587) None  Grid-point #3 at 0.02455 	Fold #8 Rep #1 pred log like = 309.223
-#> Running at Laplace(9.02587) None  Grid-point #3 at 0.02455 	Fold #9 Rep #1 pred log like = 215.609
-#> Running at Laplace(9.02587) None  Grid-point #3 at 0.02455 	Fold #10 Rep #1 pred log like = 236.912
-#> AvgPred = 251.908 with stdev = 40.6039
-#> Completed at 0.02455
-#> Next point at 0.002455 with value 0 and continue = 1
-#> search[ 0.02455 ] = 251.908(40.6039)
-#> search[ 0.2455 ] = 251.87(40.5863)
-#> search[ 2.455 ] = 251.855(40.5755)
-#> 
-#> Running at Laplace(28.5423) None  Grid-point #4 at 0.002455 	Fold #1 Rep #1 pred log like = 200.993
-#> Running at Laplace(28.5423) None  Grid-point #4 at 0.002455 	Fold #2 Rep #1 pred log like = 206.03
-#> Running at Laplace(28.5423) None  Grid-point #4 at 0.002455 	Fold #3 Rep #1 pred log like = 245.18
-#> Running at Laplace(28.5423) None  Grid-point #4 at 0.002455 	Fold #4 Rep #1 pred log like = 264.306
-#> Running at Laplace(28.5423) None  Grid-point #4 at 0.002455 	Fold #5 Rep #1 pred log like = 332.076
-#> Running at Laplace(28.5423) None  Grid-point #4 at 0.002455 	Fold #6 Rep #1 pred log like = 241.668
-#> Running at Laplace(28.5423) None  Grid-point #4 at 0.002455 	Fold #7 Rep #1 pred log like = 267.058
-#> Running at Laplace(28.5423) None  Grid-point #4 at 0.002455 	Fold #8 Rep #1 pred log like = 309.405
-#> Running at Laplace(28.5423) None  Grid-point #4 at 0.002455 	Fold #9 Rep #1 pred log like = 215.596
-#> Running at Laplace(28.5423) None  Grid-point #4 at 0.002455 	Fold #10 Rep #1 pred log like = 237.054
-#> AvgPred = 251.936 with stdev = 40.6232
-#> Completed at 0.002455
-#> Next point at 0.0002455 with value 0 and continue = 1
-#> search[ 0.002455 ] = 251.936(40.6232)
-#> search[ 0.02455 ] = 251.908(40.6039)
-#> search[ 0.2455 ] = 251.87(40.5863)
-#> search[ 2.455 ] = 251.855(40.5755)
-#> 
-#> Running at Laplace(90.2587) None  Grid-point #5 at 0.0002455 	Fold #1 Rep #1 pred log like = 200.993
-#> Running at Laplace(90.2587) None  Grid-point #5 at 0.0002455 	Fold #2 Rep #1 pred log like = 206.03
-#> Running at Laplace(90.2587) None  Grid-point #5 at 0.0002455 	Fold #3 Rep #1 pred log like = 245.18
-#> Running at Laplace(90.2587) None  Grid-point #5 at 0.0002455 	Fold #4 Rep #1 pred log like = 264.306
-#> Running at Laplace(90.2587) None  Grid-point #5 at 0.0002455 	Fold #5 Rep #1 pred log like = 332.076
-#> Running at Laplace(90.2587) None  Grid-point #5 at 0.0002455 	Fold #6 Rep #1 pred log like = 241.668
-#> Running at Laplace(90.2587) None  Grid-point #5 at 0.0002455 	Fold #7 Rep #1 pred log like = 267.058
-#> Running at Laplace(90.2587) None  Grid-point #5 at 0.0002455 	Fold #8 Rep #1 pred log like = 309.405
-#> Running at Laplace(90.2587) None  Grid-point #5 at 0.0002455 	Fold #9 Rep #1 pred log like = 215.596
-#> Running at Laplace(90.2587) None  Grid-point #5 at 0.0002455 	Fold #10 Rep #1 pred log like = 237.054
-#> AvgPred = 251.936 with stdev = 40.6232
-#> Completed at 0.0002455
-#> Next point at 1.99853e-06 with value 251.954 and continue = 0
-#> search[ 0.0002455 ] = 251.936(40.6232)
-#> search[ 0.002455 ] = 251.936(40.6232)
-#> search[ 0.02455 ] = 251.908(40.6039)
-#> search[ 0.2455 ] = 251.87(40.5863)
-#> search[ 2.455 ] = 251.855(40.5755)
-#> 
-#> 
-#> Maximum predicted log likelihood (251.954) estimated at:
-#> 	1.99853e-06 (variance)
-#> 	1000.37 (lambda)
-#> 
-#> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(1000.37) None 

-#Find out what the optimal hyperparameter was:
-getHyperParameter(fit)
-
#> [1] 1.998532e-06

-#Extract the current log-likelihood, and coefficients
-logLik(fit)
-
#> 'log Lik.' -1927.858 (df=3)
coef(fit)
-
#> (Intercept)           1           2 
-#>   -4.118361    0.000000    0.000000 

-#We can only retrieve the confidence interval for unregularized coefficients:
-confint(fit, c(0))
-
#> Using 1 thread(s)
#>      covariate     2.5 %    97.5 % evaluations
-#> [1,]         0 -4.149079 -4.087942          24
+
+

Arguments

+
object
+

A Cyclops model fit object

+ +
+ +
+

Examples

+ 
#Generate some simulated data:
+sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
+                           model = "poisson")
+#> Sparseness = 73.85 %
+cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
+                                    addIntercept = TRUE)
+#> Sorting covariates by covariateId and rowId
+
+#Define the prior and control objects to use cross-validation for finding the 
+#optimal hyperparameter:
+prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
+control <- createControl(cvType = "auto", noiseLevel = "quiet")
+
+#Fit the model
+fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
+#> Using cross-validation selector type byRow
+#> Performing 10-fold cross-validation [seed = 1698757937] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Using 1 thread(s)
+#> Starting var = 0.2615 (default)
+#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #1 Rep #1 pred log like = 372.484
+#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #2 Rep #1 pred log like = 427.249
+#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #3 Rep #1 pred log like = 468.957
+#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #4 Rep #1 pred log like = 505.492
+#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #5 Rep #1 pred log like = 364.273
+#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #6 Rep #1 pred log like = 433.21
+#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #7 Rep #1 pred log like = 443.256
+#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #8 Rep #1 pred log like = 438.388
+#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #9 Rep #1 pred log like = 475.904
+#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #10 Rep #1 pred log like = 470.303
+#> AvgPred = 439.952 with stdev = 42.2492
+#> Completed at 0.2615
+#> Next point at 2.615 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> 
+#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #1 Rep #1 pred log like = 372.478
+#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #2 Rep #1 pred log like = 427.302
+#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #3 Rep #1 pred log like = 468.968
+#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #4 Rep #1 pred log like = 505.462
+#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #5 Rep #1 pred log like = 364.28
+#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #6 Rep #1 pred log like = 433.206
+#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #7 Rep #1 pred log like = 443.204
+#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #8 Rep #1 pred log like = 438.398
+#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #9 Rep #1 pred log like = 475.914
+#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #10 Rep #1 pred log like = 470.313
+#> AvgPred = 439.952 with stdev = 42.2447
+#> Completed at 2.615
+#> Next point at 26.15 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> 
+#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #2 Rep #1 pred log like = 427.318
+#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #3 Rep #1 pred log like = 468.971
+#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #4 Rep #1 pred log like = 505.453
+#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #5 Rep #1 pred log like = 364.282
+#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #6 Rep #1 pred log like = 433.205
+#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #7 Rep #1 pred log like = 443.188
+#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #8 Rep #1 pred log like = 438.4
+#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #9 Rep #1 pred log like = 475.917
+#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #10 Rep #1 pred log like = 470.316
+#> AvgPred = 439.953 with stdev = 42.243
+#> Completed at 26.15
+#> Next point at 261.5 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> 
+#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #2 Rep #1 pred log like = 427.323
+#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #4 Rep #1 pred log like = 505.45
+#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #5 Rep #1 pred log like = 364.282
+#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #7 Rep #1 pred log like = 443.182
+#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #8 Rep #1 pred log like = 438.401
+#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #9 Rep #1 pred log like = 475.917
+#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #10 Rep #1 pred log like = 470.317
+#> AvgPred = 439.953 with stdev = 42.2425
+#> Completed at 261.5
+#> Next point at 2615 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> 
+#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #4 Rep #1 pred log like = 505.449
+#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #5 Rep #1 pred log like = 364.282
+#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #7 Rep #1 pred log like = 443.181
+#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #10 Rep #1 pred log like = 470.317
+#> AvgPred = 439.953 with stdev = 42.2423
+#> Completed at 2615
+#> Next point at 26150 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> 
+#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #4 Rep #1 pred log like = 505.449
+#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2423
+#> Completed at 26150
+#> Next point at 261500 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> 
+#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 261500
+#> Next point at 2.615e+06 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+06
+#> Next point at 2.615e+07 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+07
+#> Next point at 2.615e+08 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+08
+#> Next point at 2.615e+09 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+09
+#> Next point at 2.615e+10 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+10
+#> Next point at 2.615e+11 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+11
+#> Next point at 2.615e+12 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> search[ 2.615e+11 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+12
+#> Next point at 2.615e+13 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> search[ 2.615e+11 ] = 439.953(42.2422)
+#> search[ 2.615e+12 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+13
+#> Next point at 2.615e+14 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> search[ 2.615e+11 ] = 439.953(42.2422)
+#> search[ 2.615e+12 ] = 439.953(42.2422)
+#> search[ 2.615e+13 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+14
+#> Next point at 2.615e+15 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> search[ 2.615e+11 ] = 439.953(42.2422)
+#> search[ 2.615e+12 ] = 439.953(42.2422)
+#> search[ 2.615e+13 ] = 439.953(42.2422)
+#> search[ 2.615e+14 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+15
+#> Next point at 2.615e+16 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> search[ 2.615e+11 ] = 439.953(42.2422)
+#> search[ 2.615e+12 ] = 439.953(42.2422)
+#> search[ 2.615e+13 ] = 439.953(42.2422)
+#> search[ 2.615e+14 ] = 439.953(42.2422)
+#> search[ 2.615e+15 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+16
+#> Next point at 2.615e+17 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> search[ 2.615e+11 ] = 439.953(42.2422)
+#> search[ 2.615e+12 ] = 439.953(42.2422)
+#> search[ 2.615e+13 ] = 439.953(42.2422)
+#> search[ 2.615e+14 ] = 439.953(42.2422)
+#> search[ 2.615e+15 ] = 439.953(42.2422)
+#> search[ 2.615e+16 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+17
+#> Next point at 2.615e+18 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> search[ 2.615e+11 ] = 439.953(42.2422)
+#> search[ 2.615e+12 ] = 439.953(42.2422)
+#> search[ 2.615e+13 ] = 439.953(42.2422)
+#> search[ 2.615e+14 ] = 439.953(42.2422)
+#> search[ 2.615e+15 ] = 439.953(42.2422)
+#> search[ 2.615e+16 ] = 439.953(42.2422)
+#> search[ 2.615e+17 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+18
+#> Next point at 2.615e+19 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> search[ 2.615e+11 ] = 439.953(42.2422)
+#> search[ 2.615e+12 ] = 439.953(42.2422)
+#> search[ 2.615e+13 ] = 439.953(42.2422)
+#> search[ 2.615e+14 ] = 439.953(42.2422)
+#> search[ 2.615e+15 ] = 439.953(42.2422)
+#> search[ 2.615e+16 ] = 439.953(42.2422)
+#> search[ 2.615e+17 ] = 439.953(42.2422)
+#> search[ 2.615e+18 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+19
+#> Next point at 2.615e+20 with value 0 and continue = 1
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> search[ 2.615e+11 ] = 439.953(42.2422)
+#> search[ 2.615e+12 ] = 439.953(42.2422)
+#> search[ 2.615e+13 ] = 439.953(42.2422)
+#> search[ 2.615e+14 ] = 439.953(42.2422)
+#> search[ 2.615e+15 ] = 439.953(42.2422)
+#> search[ 2.615e+16 ] = 439.953(42.2422)
+#> search[ 2.615e+17 ] = 439.953(42.2422)
+#> search[ 2.615e+18 ] = 439.953(42.2422)
+#> search[ 2.615e+19 ] = 439.953(42.2422)
+#> 
+#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #1 Rep #1 pred log like = 372.477
+#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #2 Rep #1 pred log like = 427.325
+#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #3 Rep #1 pred log like = 468.972
+#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #4 Rep #1 pred log like = 505.448
+#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #5 Rep #1 pred log like = 364.283
+#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #6 Rep #1 pred log like = 433.204
+#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #7 Rep #1 pred log like = 443.18
+#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #8 Rep #1 pred log like = 438.402
+#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #9 Rep #1 pred log like = 475.918
+#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #10 Rep #1 pred log like = 470.318
+#> AvgPred = 439.953 with stdev = 42.2422
+#> Completed at 2.615e+20
+#> Next point at 3.27402e+12 with value 439.953 and continue = 0
+#> search[ 0.2615 ] = 439.952(42.2492)
+#> search[ 2.615 ] = 439.952(42.2447)
+#> search[ 26.15 ] = 439.953(42.243)
+#> search[ 261.5 ] = 439.953(42.2425)
+#> search[ 2615 ] = 439.953(42.2423)
+#> search[ 26150 ] = 439.953(42.2423)
+#> search[ 261500 ] = 439.953(42.2422)
+#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> search[ 2.615e+11 ] = 439.953(42.2422)
+#> search[ 2.615e+12 ] = 439.953(42.2422)
+#> search[ 2.615e+13 ] = 439.953(42.2422)
+#> search[ 2.615e+14 ] = 439.953(42.2422)
+#> search[ 2.615e+15 ] = 439.953(42.2422)
+#> search[ 2.615e+16 ] = 439.953(42.2422)
+#> search[ 2.615e+17 ] = 439.953(42.2422)
+#> search[ 2.615e+18 ] = 439.953(42.2422)
+#> search[ 2.615e+19 ] = 439.953(42.2422)
+#> search[ 2.615e+20 ] = 439.953(42.2422)
+#> 
+#> 
+#> Maximum predicted log likelihood (439.953) estimated at:
+#> 	3.27402e+12 (variance)
+#> 	7.81582e-07 (lambda)
+#> 
+#> Fitting model at optimal hyperparameter
+#> Using prior: Laplace(7.81582e-07) None 
+
+#Find out what the optimal hyperparameter was:
+getHyperParameter(fit)
+#> [1] 3.274021e+12
+
+#Extract the current log-likelihood, and coefficients
+logLik(fit)
+#> 'log Lik.' -2097.62 (df=3)
+coef(fit)
+#> (Intercept)           1           2 
+#> -3.87566911  0.05844875  0.01875022 
+
+#We can only retrieve the confidence interval for unregularized coefficients:
+confint(fit, c(0))
+#> Using 1 thread(s)
+#>             covariate     2.5 %    97.5 % evaluations
+#> (Intercept)         0 -3.910302 -3.841399          22
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getNumberOfCovariates.html b/docs/reference/getNumberOfCovariates.html index f221361d..bf695d09 100644 --- a/docs/reference/getNumberOfCovariates.html +++ b/docs/reference/getNumberOfCovariates.html @@ -1,67 +1,12 @@ - - - - - - - -Get total number of covariates — getNumberOfCovariates • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Get total number of covariates — getNumberOfCovariates • Cyclops - + + - - - -
-
- -
- -
+

Get total number of covariates

- Source: R/RcppExports.R + Source: R/RcppExports.R
@@ -123,43 +55,38 @@

Get total number of covariates

getNumberOfCovariates returns the total number of covariates in a Cyclops data object

- 
getNumberOfCovariates(object)
+
+ 
getNumberOfCovariates(object)
+
-

Arguments

- - - - - - -
object

A Cyclops data object

+
+

Arguments

+
object
+

A Cyclops data object

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getNumberOfRows.html b/docs/reference/getNumberOfRows.html index a219f338..df4d164e 100644 --- a/docs/reference/getNumberOfRows.html +++ b/docs/reference/getNumberOfRows.html @@ -1,67 +1,12 @@ - - - - - - - -Get total number of rows — getNumberOfRows • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Get total number of rows — getNumberOfRows • Cyclops - + + - - - -
-
- -
- -
+

Get total number of rows

- Source: R/RcppExports.R + Source: R/RcppExports.R
@@ -123,43 +55,38 @@

Get total number of rows

getNumberOfRows returns the total number of outcome rows in a Cyclops data object

- 
getNumberOfRows(object)
+
+ 
getNumberOfRows(object)
+
-

Arguments

- - - - - - -
object

A Cyclops data object

+
+

Arguments

+
object
+

A Cyclops data object

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getNumberOfStrata.html b/docs/reference/getNumberOfStrata.html index 09eedc36..c7c15798 100644 --- a/docs/reference/getNumberOfStrata.html +++ b/docs/reference/getNumberOfStrata.html @@ -1,67 +1,12 @@ - - - - - - - -Get number of strata — getNumberOfStrata • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Get number of strata — getNumberOfStrata • Cyclops - + + - - - -
-
- -
- -
+

Get number of strata

- Source: R/RcppExports.R + Source: R/RcppExports.R
@@ -123,43 +55,38 @@

Get number of strata

getNumberOfStrata return the number of unique strata in a Cyclops data object

- 
getNumberOfStrata(object)
+
+ 
getNumberOfStrata(object)
+
-

Arguments

- - - - - - -
object

A Cyclops data object

+
+

Arguments

+
object
+

A Cyclops data object

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getNumberOfTypes.html b/docs/reference/getNumberOfTypes.html index e09c992e..086f373b 100644 --- a/docs/reference/getNumberOfTypes.html +++ b/docs/reference/getNumberOfTypes.html @@ -1,67 +1,12 @@ - - - - - - - -Get total number of outcome types — getNumberOfTypes • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Get total number of outcome types — getNumberOfTypes • Cyclops - + + - - - -
-
- -
- -
+

Get total number of outcome types

- Source: R/RcppExports.R + Source: R/RcppExports.R
@@ -123,43 +55,38 @@

Get total number of outcome types

getNumberOfTypes returns the total number of outcome types in a Cyclops data object

- 
getNumberOfTypes(object)
+
+ 
getNumberOfTypes(object)
+
-

Arguments

- - - - - - -
object

A Cyclops data object

+
+

Arguments

+
object
+

A Cyclops data object

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getSEs.html b/docs/reference/getSEs.html index 357d85aa..8c241997 100644 --- a/docs/reference/getSEs.html +++ b/docs/reference/getSEs.html @@ -1,67 +1,12 @@ - - - - - - - -Extract standard errors — getSEs • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Extract standard errors — getSEs • Cyclops - - - - + + -
-
- -
- -
+

Extract standard errors

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -123,58 +55,57 @@

Extract standard errors

getSEs extracts asymptotic standard errors for specific covariates from a Cyclops model fit object.

- 
getSEs(object, covariates)
+
+ 
getSEs(object, covariates)
+
+ +
+

Arguments

+
object
+

A Cyclops model fit object

-

Arguments

- - - - - - - - - - -
object

A Cyclops model fit object

covariates

Integer or string vector: list of covariates for which asymptotic standard errors are wanted

-

Value

+
covariates
+

Integer or string vector: list of covariates for which asymptotic standard errors are wanted

-

Vector of standard error estimates

-

Details

+
+
+

Value

+ +

Vector of standard error estimates

+
+
+

Details

This function first computes the (partial) Fisher information matrix for just the requested covariates and then returns the square root of the diagonal elements of the inverse of the Fisher information matrix. These are the asymptotic standard errors when all possible covariates are included. When the requested covariates do not equate to all coefficients in the model, then interpretation is more challenging.

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getUnivariableCorrelation.html b/docs/reference/getUnivariableCorrelation.html index d3821613..7ea0bafb 100644 --- a/docs/reference/getUnivariableCorrelation.html +++ b/docs/reference/getUnivariableCorrelation.html @@ -1,67 +1,12 @@ - - - - - - - -Get univariable correlation — getUnivariableCorrelation • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Get univariable correlation — getUnivariableCorrelation • Cyclops - + + - - - -
-
- -
- -
+

Get univariable correlation

- Source: R/DataManagement.R + Source: R/DataManagement.R
@@ -123,54 +55,52 @@

Get univariable correlation

getUnivariableCorrelation reports covariates that have high correlation with the outcome

- 
getUnivariableCorrelation(cyclopsData, covariates = NULL, threshold = 0)
- -

Arguments

- - - - - - - - - - - - - - -
cyclopsData

A Cyclops data object

covariates

Integer or string vector: list of covariates to report; default (NULL) implies all covariates

threshold

Correlation threshold for reporting

- -

Value

- -

A list of covariates whose absolute correlation with the outcome is greater than or equal to the threshold

+
+ 
getUnivariableCorrelation(cyclopsData, covariates = NULL, threshold = 0)
+
+ +
+

Arguments

+
cyclopsData
+

A Cyclops data object

+ + +
covariates
+

Integer or string vector: list of covariates to report; default (NULL) implies all covariates

+ + +
threshold
+

Correlation threshold for reporting

+ +
+
+

Value

+ + +

A list of covariates whose absolute correlation with the outcome is greater than or equal to the threshold

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/getUnivariableSeparability.html b/docs/reference/getUnivariableSeparability.html index ae00bafe..ec0f8feb 100644 --- a/docs/reference/getUnivariableSeparability.html +++ b/docs/reference/getUnivariableSeparability.html @@ -1,67 +1,12 @@ - - - - - - - -Get univariable linear separability — getUnivariableSeparability • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Get univariable linear separability — getUnivariableSeparability • Cyclops - - - - + + -
-
- -
- -
+

Get univariable linear separability

- Source: R/DataManagement.R + Source: R/DataManagement.R
@@ -123,50 +55,48 @@

Get univariable linear separability

getUnivariableSeparability reports covariates that are univariably separable with the outcome

- 
getUnivariableSeparability(cyclopsData, covariates = NULL)
+
+ 
getUnivariableSeparability(cyclopsData, covariates = NULL)
+
+ +
+

Arguments

+
cyclopsData
+

A Cyclops data object

-

Arguments

- - - - - - - - - - -
cyclopsData

A Cyclops data object

covariates

Integer or string vector: list of covariates to report; default (NULL) implies all covariates

-

Value

+
covariates
+

Integer or string vector: list of covariates to report; default (NULL) implies all covariates

-

A list of covariates that are univariably separable with the outcome

+
+
+

Value

+ + +

A list of covariates that are univariably separable with the outcome

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/index.html b/docs/reference/index.html index b294ffe6..8edaea93 100644 --- a/docs/reference/index.html +++ b/docs/reference/index.html @@ -1,66 +1,12 @@ - - - - - - - -Function reference • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Function reference • Cyclops - + + - - - -
-
- -
- -
+

Reference

- - - - - - - - - - -
-

All functions

+ - - - - - - - - - - - - - - - - - - - - - + + - - - - - - - - - - - - - - - - - - - - - + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + - - - - - - - - -
+

All functions

+

Multitype()

Create a multitype outcome object

+

coef(<cyclopsFit>)

Extract model coefficients

+

confint(<cyclopsFit>)

Confidence intervals for Cyclops model parameters

+

convertToCyclopsData()

Convert data from two data frames or ffdf objects into a CyclopsData object

+
+

convertToTimeVaryingCoef()

+

Convert short sparse covariate table to long sparse covariate table for time-varying coefficients.

coverage()

Coverage

+

createAutoGridCrossValidationControl()

Create a Cyclops control object that supports multiple hyperparameters

+

createControl()

Create a Cyclops control object

+

createCyclopsData()

Create a Cyclops data object

+

createNonSeparablePrior()

Create a Cyclops prior object that returns the MLE of non-separable coefficients

+

createParameterizedPrior()

Create a Cyclops parameterized prior object

+

createPrior()

Create a Cyclops prior object

+
+

createWeightBasedSearchControl()

+

Create a Cyclops control object that supports in- / out-of-sample hyperparameter search using weights

cyclops

Cyclops: Cyclic coordinate descent for logistic, Poisson and survival analysis

+

fitCyclopsModel()

Fit a Cyclops model

+

fitCyclopsSimulation()

Fit simulated data

+

getCovariateIds()

Get covariate identifiers

+

getCovariateTypes()

Get covariate types

+

getCyclopsProfileLogLikelihood()

Profile likelihood for Cyclops model parameters

+

getFineGrayWeights()

Creates a Surv object that forces in competing risks and the IPCW needed for Fine-Gray estimation.

+

getFloatingPointSize()

Get floating point size

+

getHyperParameter()

Get hyperparameter

+

getNumberOfCovariates()

Get total number of covariates

+

getNumberOfRows()

Get total number of rows

+

getNumberOfStrata()

Get number of strata

+

getUnivariableCorrelation()

Get univariable correlation

+

getUnivariableSeparability()

Get univariable linear separability

+

isInitialized()

Check if a Cyclops data object is initialized

+

logLik(<cyclopsFit>)

Extract log-likelihood

+

meanLinearPredictor()

Calculates xbar*beta

+

mse()

Mean squared error

+

oxford

Oxford self-controlled case series data

+

predict(<cyclopsFit>)

Model predictions

+

print(<cyclopsData>)

Print a Cyclops data object

+

print(<cyclopsFit>)

Print a Cyclops model fit object

+

readCyclopsData()

Read Cyclops data from file

+

simulateCyclopsData()

Simulation Cyclops dataset

+
+

splitTime()

+

Split the analysis time into several intervals for time-varying coefficients.

summary(<cyclopsData>)

Cyclops data object summary

+

survfit(<cyclopsFit>)

Calculate baseline hazard function

+

vcov(<cyclopsFit>)

Calculate variance-covariance matrix for a fitted Cyclops model object

- +
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/isInitialized.html b/docs/reference/isInitialized.html index e6eed93a..38851be3 100644 --- a/docs/reference/isInitialized.html +++ b/docs/reference/isInitialized.html @@ -1,69 +1,14 @@ - - - - - - - -Check if a Cyclops data object is initialized — isInitialized • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Check if a Cyclops data object is initialized — isInitialized • Cyclops - - - - - - - - - - + + - - - -
-
- -
- -
+

Check if a Cyclops data object is initialized

- Source: R/DataManagement.R + Source: R/DataManagement.R
@@ -127,43 +59,38 @@

Check if a Cyclops data object is initialized

serialized/deserialize their back-end memory across R sessions.

- 
isInitialized(object)
+
+ 
isInitialized(object)
+
-

Arguments

- - - - - - -
object

Cyclops data object to test

+
+

Arguments

+
object
+

Cyclops data object to test

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/logLik.cyclopsFit.html b/docs/reference/logLik.cyclopsFit.html index b47df32c..5f68c200 100644 --- a/docs/reference/logLik.cyclopsFit.html +++ b/docs/reference/logLik.cyclopsFit.html @@ -1,67 +1,12 @@ - - - - - - - -Extract log-likelihood — logLik.cyclopsFit • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Extract log-likelihood — logLik.cyclopsFit • Cyclops - - + + - - -
-
- -
- -
+

Extract log-likelihood

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -123,133 +55,138 @@

Extract log-likelihood

logLik returns the current log-likelihood of the fit in a Cyclops model fit object

- 
# S3 method for cyclopsFit
-logLik(object, ...)
- -

Arguments

- - - - - - - - - - -
object

A Cyclops model fit object

...

Additional arguments

- - -

Examples

- 
#Generate some simulated data:
-sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
-                           model = "poisson")
-
#> Sparseness = 76.3 %
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
-                                    addIntercept = TRUE)
-
#> Sorting covariates by covariateId and rowId

-#Define the prior and control objects to use cross-validation for finding the 
-#optimal hyperparameter:
-prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
-control <- createControl(cvType = "auto", noiseLevel = "quiet")
-
-#Fit the model
-fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
-
#> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1623936646] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
-#> Using 1 thread(s)
-#> Starting var = 0.237 (default)
-#> Running at Laplace(2.90496) None  Grid-point #1 at 0.237 	Fold #1 Rep #1 pred log like = 81.7154
-#> Running at Laplace(2.90496) None  Grid-point #1 at 0.237 	Fold #2 Rep #1 pred log like = 84.3058
-#> Running at Laplace(2.90496) None  Grid-point #1 at 0.237 	Fold #3 Rep #1 pred log like = 44.7229
-#> Running at Laplace(2.90496) None  Grid-point #1 at 0.237 	Fold #4 Rep #1 pred log like = 67.5691
-#> Running at Laplace(2.90496) None  Grid-point #1 at 0.237 	Fold #5 Rep #1 pred log like = 102.612
-#> Running at Laplace(2.90496) None  Grid-point #1 at 0.237 	Fold #6 Rep #1 pred log like = -1.50097
-#> Running at Laplace(2.90496) None  Grid-point #1 at 0.237 	Fold #7 Rep #1 pred log like = 92.0468
-#> Running at Laplace(2.90496) None  Grid-point #1 at 0.237 	Fold #8 Rep #1 pred log like = 37.2992
-#> Running at Laplace(2.90496) None  Grid-point #1 at 0.237 	Fold #9 Rep #1 pred log like = 83.6135
-#> Running at Laplace(2.90496) None  Grid-point #1 at 0.237 	Fold #10 Rep #1 pred log like = 30.8871
-#> AvgPred = 62.327 with stdev = 31.3759
-#> Completed at 0.237
-#> Next point at 2.37 with value 0 and continue = 1
-#> search[ 0.237 ] = 62.327(31.3759)
-#> 
-#> Running at Laplace(0.91863) None  Grid-point #2 at 2.37 	Fold #1 Rep #1 pred log like = 81.7226
-#> Running at Laplace(0.91863) None  Grid-point #2 at 2.37 	Fold #2 Rep #1 pred log like = 84.2611
-#> Running at Laplace(0.91863) None  Grid-point #2 at 2.37 	Fold #3 Rep #1 pred log like = 44.7842
-#> Running at Laplace(0.91863) None  Grid-point #2 at 2.37 	Fold #4 Rep #1 pred log like = 67.5706
-#> Running at Laplace(0.91863) None  Grid-point #2 at 2.37 	Fold #5 Rep #1 pred log like = 102.538
-#> Running at Laplace(0.91863) None  Grid-point #2 at 2.37 	Fold #6 Rep #1 pred log like = -1.49342
-#> Running at Laplace(0.91863) None  Grid-point #2 at 2.37 	Fold #7 Rep #1 pred log like = 91.9862
-#> Running at Laplace(0.91863) None  Grid-point #2 at 2.37 	Fold #8 Rep #1 pred log like = 37.3588
-#> Running at Laplace(0.91863) None  Grid-point #2 at 2.37 	Fold #9 Rep #1 pred log like = 83.6881
-#> Running at Laplace(0.91863) None  Grid-point #2 at 2.37 	Fold #10 Rep #1 pred log like = 30.8629
-#> AvgPred = 62.3279 with stdev = 31.3558
-#> Completed at 2.37
-#> Next point at 23.7 with value 0 and continue = 1
-#> search[ 0.237 ] = 62.327(31.3759)
-#> search[ 2.37 ] = 62.3279(31.3558)
-#> 
-#> Running at Laplace(0.290496) None  Grid-point #3 at 23.7 	Fold #1 Rep #1 pred log like = 81.7245
-#> Running at Laplace(0.290496) None  Grid-point #3 at 23.7 	Fold #2 Rep #1 pred log like = 84.2464
-#> Running at Laplace(0.290496) None  Grid-point #3 at 23.7 	Fold #3 Rep #1 pred log like = 44.8033
-#> Running at Laplace(0.290496) None  Grid-point #3 at 23.7 	Fold #4 Rep #1 pred log like = 67.5705
-#> Running at Laplace(0.290496) None  Grid-point #3 at 23.7 	Fold #5 Rep #1 pred log like = 102.514
-#> Running at Laplace(0.290496) None  Grid-point #3 at 23.7 	Fold #6 Rep #1 pred log like = -1.49139
-#> Running at Laplace(0.290496) None  Grid-point #3 at 23.7 	Fold #7 Rep #1 pred log like = 91.9666
-#> Running at Laplace(0.290496) None  Grid-point #3 at 23.7 	Fold #8 Rep #1 pred log like = 37.3773
-#> Running at Laplace(0.290496) None  Grid-point #3 at 23.7 	Fold #9 Rep #1 pred log like = 83.7113
-#> Running at Laplace(0.290496) None  Grid-point #3 at 23.7 	Fold #10 Rep #1 pred log like = 30.8547
-#> AvgPred = 62.3278 with stdev = 31.3495
-#> Completed at 23.7
-#> Next point at 5.15795 with value 62.328 and continue = 0
-#> search[ 0.237 ] = 62.327(31.3759)
-#> search[ 2.37 ] = 62.3279(31.3558)
-#> search[ 23.7 ] = 62.3278(31.3495)
-#> 
-#> 
-#> Maximum predicted log likelihood (62.328) estimated at:
-#> 	5.15795 (variance)
-#> 	0.622697 (lambda)
-#> 
-#> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(0.622697) None 

-#Find out what the optimal hyperparameter was:
-getHyperParameter(fit)
-
#> [1] 5.157948

-#Extract the current log-likelihood, and coefficients
-logLik(fit)
-
#> 'log Lik.' -1691.249 (df=3)
coef(fit)
-
#> (Intercept)           1           2 
-#> -4.39513986 -0.04641266 -0.55810190 

-#We can only retrieve the confidence interval for unregularized coefficients:
-confint(fit, c(0))
-
#> Using 1 thread(s)
#>      covariate     2.5 %    97.5 % evaluations
-#> [1,]         0 -4.439663 -4.351258          20
+
+ 
# S3 method for cyclopsFit
+logLik(object, ...)
+
+ +
+

Arguments

+
object
+

A Cyclops model fit object

+ + +
...
+

Additional arguments

+ +
+ +
+

Examples

+ 
#Generate some simulated data:
+sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
+                           model = "poisson")
+#> Sparseness = 77.4 %
+cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
+                                    addIntercept = TRUE)
+#> Sorting covariates by covariateId and rowId
+
+#Define the prior and control objects to use cross-validation for finding the 
+#optimal hyperparameter:
+prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
+control <- createControl(cvType = "auto", noiseLevel = "quiet")
+
+#Fit the model
+fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
+#> Using cross-validation selector type byRow
+#> Performing 10-fold cross-validation [seed = 1698757939] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Using 1 thread(s)
+#> Starting var = 0.226 (default)
+#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #1 Rep #1 pred log like = 424.312
+#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #2 Rep #1 pred log like = 286.112
+#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #3 Rep #1 pred log like = 542.244
+#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #4 Rep #1 pred log like = 462.595
+#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #5 Rep #1 pred log like = 523.632
+#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #6 Rep #1 pred log like = 390.675
+#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #7 Rep #1 pred log like = 360.237
+#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #8 Rep #1 pred log like = 399.312
+#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #9 Rep #1 pred log like = 395.077
+#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #10 Rep #1 pred log like = 331.197
+#> AvgPred = 411.539 with stdev = 76.2186
+#> Completed at 0.226
+#> Next point at 2.26 with value 0 and continue = 1
+#> search[ 0.226 ] = 411.539(76.2186)
+#> 
+#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #1 Rep #1 pred log like = 424.271
+#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #2 Rep #1 pred log like = 286.187
+#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #3 Rep #1 pred log like = 542.304
+#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #4 Rep #1 pred log like = 462.57
+#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #5 Rep #1 pred log like = 523.608
+#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #6 Rep #1 pred log like = 390.669
+#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #7 Rep #1 pred log like = 360.212
+#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #8 Rep #1 pred log like = 399.333
+#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #9 Rep #1 pred log like = 395.126
+#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #10 Rep #1 pred log like = 331.12
+#> AvgPred = 411.54 with stdev = 76.2193
+#> Completed at 2.26
+#> Next point at 22.6 with value 0 and continue = 1
+#> search[ 0.226 ] = 411.539(76.2186)
+#> search[ 2.26 ] = 411.54(76.2193)
+#> 
+#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #1 Rep #1 pred log like = 424.258
+#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #2 Rep #1 pred log like = 286.211
+#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #3 Rep #1 pred log like = 542.322
+#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #4 Rep #1 pred log like = 462.562
+#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #5 Rep #1 pred log like = 523.601
+#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #6 Rep #1 pred log like = 390.667
+#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #7 Rep #1 pred log like = 360.204
+#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #8 Rep #1 pred log like = 399.34
+#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #9 Rep #1 pred log like = 395.142
+#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #10 Rep #1 pred log like = 331.095
+#> AvgPred = 411.54 with stdev = 76.2195
+#> Completed at 22.6
+#> Next point at 7.08693 with value 411.54 and continue = 0
+#> search[ 0.226 ] = 411.539(76.2186)
+#> search[ 2.26 ] = 411.54(76.2193)
+#> search[ 22.6 ] = 411.54(76.2195)
+#> 
+#> 
+#> Maximum predicted log likelihood (411.54) estimated at:
+#> 	7.08693 (variance)
+#> 	0.531234 (lambda)
+#> 
+#> Fitting model at optimal hyperparameter
+#> Using prior: Laplace(0.531234) None 
+
+#Find out what the optimal hyperparameter was:
+getHyperParameter(fit)
+#> [1] 7.086931
+
+#Extract the current log-likelihood, and coefficients
+logLik(fit)
+#> 'log Lik.' -2045.115 (df=3)
+coef(fit)
+#> (Intercept)           1           2 
+#> -3.89896635 -0.03932575  0.03150517 
+
+#We can only retrieve the confidence interval for unregularized coefficients:
+confint(fit, c(0))
+#> Using 1 thread(s)
+#>             covariate     2.5 %    97.5 % evaluations
+#> (Intercept)         0 -3.932993 -3.865291          22
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/meanLinearPredictor.html b/docs/reference/meanLinearPredictor.html index 075937fd..322c12d4 100644 --- a/docs/reference/meanLinearPredictor.html +++ b/docs/reference/meanLinearPredictor.html @@ -1,67 +1,12 @@ - - - - - - - -Calculates xbar*beta — meanLinearPredictor • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Calculates xbar*beta — meanLinearPredictor • Cyclops - + + - - - -
-
- -
- -
+

Calculates xbar*beta

- Source: R/Predict.R + Source: R/Predict.R
@@ -123,43 +55,38 @@

Calculates xbar*beta

meanLinearPredictor computes xbar*beta for model fit

- 
meanLinearPredictor(cyclopsFit)
+
+ 
meanLinearPredictor(cyclopsFit)
+
-

Arguments

- - - - - - -
cyclopsFit

A Cyclops model fit object

+
+

Arguments

+
cyclopsFit
+

A Cyclops model fit object

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/mse.html b/docs/reference/mse.html index ed869eac..d61256a4 100644 --- a/docs/reference/mse.html +++ b/docs/reference/mse.html @@ -1,67 +1,12 @@ - - - - - - - -Mean squared error — mse • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Mean squared error — mse • Cyclops - - - - + + -
-
- -
- -
+

Mean squared error

- Source: R/Simulation.R + Source: R/Simulation.R
@@ -123,50 +55,48 @@

Mean squared error

mse computes the mean squared error between two numeric vectors

- 
mse(goldStandard, estimates)
+
+ 
mse(goldStandard, estimates)
+
+ +
+

Arguments

+
goldStandard
+

Numeric vector

-

Arguments

- - - - - - - - - - -
goldStandard

Numeric vector

estimates

Numeric vector

-

Value

+
estimates
+

Numeric vector

-

MSE(goldStandard, estimates)

+
+
+

Value

+ + +

MSE(goldStandard, estimates)

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/oxford.html b/docs/reference/oxford.html index 55d09700..216a123e 100644 --- a/docs/reference/oxford.html +++ b/docs/reference/oxford.html @@ -1,68 +1,13 @@ - - - - - - - -Oxford self-controlled case series data — oxford • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Oxford self-controlled case series data — oxford • Cyclops - - - - + + -
-
- -
- -
+

Oxford self-controlled case series data

- Source: R/ExampleData.R + Source: R/ExampleData.R
@@ -125,48 +57,55 @@

Oxford self-controlled case series data

Farrington and Whitaker. There are 10 patients comprising 38 unique exposure intervals.

- 
data(oxford)
+
+ 
data(oxford)
+
+ +
+

Format

+

A data frame with 38 rows and 6 variables:

indiv
+

patient identifier

+
event
+

number of events in interval

-

Format

+
interval
+

interval length in days

-

A data frame with 38 rows and 6 variables:

-
indiv

patient identifier

-
event

number of events in interval

-
interval

interval length in days

-
agegr

age group

-
exgr

exposure group

-
loginterval

log interval length

- ... +
agegr
+

age group

-
+
exgr
+

exposure group

+
loginterval
+

log interval length

+ +... + +
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/plotCyclopsSimulationFit.html b/docs/reference/plotCyclopsSimulationFit.html index 845d5501..4d7547c9 100644 --- a/docs/reference/plotCyclopsSimulationFit.html +++ b/docs/reference/plotCyclopsSimulationFit.html @@ -1,68 +1,13 @@ - - - - - - - -Plot Cyclops simulation model fit — plotCyclopsSimulationFit • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Plot Cyclops simulation model fit — plotCyclopsSimulationFit • Cyclops - - + + - - -
-
- -
- -
+

Plot Cyclops simulation model fit

- Source: R/Simulation.R + Source: R/Simulation.R
@@ -125,51 +57,46 @@

Plot Cyclops simulation model fit

Cyclops model fit.

- 
plotCyclopsSimulationFit(fit, goldStandard, label)
- -

Arguments

- - - - - - - - - - - - - - -
fit

A Cyclops simulation fit generated by fitCyclopsSimulation

goldStandard

Numeric vector. True relative risks.

label

String. Name of estimate type.

+
+ 
plotCyclopsSimulationFit(fit, goldStandard, label)
+
+ +
+

Arguments

+
fit
+

A Cyclops simulation fit generated by fitCyclopsSimulation

+ + +
goldStandard
+

Numeric vector. True relative risks.

+
label
+

String. Name of estimate type.

+ +
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/predict.cyclopsFit.html b/docs/reference/predict.cyclopsFit.html index ae7ad7d7..b10cf40b 100644 --- a/docs/reference/predict.cyclopsFit.html +++ b/docs/reference/predict.cyclopsFit.html @@ -1,67 +1,12 @@ - - - - - - - -Model predictions — predict.cyclopsFit • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Model predictions — predict.cyclopsFit • Cyclops + + - - - - -
-
- -
- -
+

Model predictions

- Source: R/Predict.R + Source: R/Predict.R
@@ -123,56 +55,51 @@

Model predictions

predict.cyclopsFit computes model response-scale predictive values for all data rows

- 
# S3 method for cyclopsFit
-predict(object, newOutcomes, newCovariates, ...)
- -

Arguments

- - - - - - - - - - - - - - - - - - -
object

A Cyclops model fit object

newOutcomes

An optional data frame or Andromeda table object, similar to the object used in convertToCyclopsData.

newCovariates

An optional data frame or Andromeda table object, similar to the object used in convertToCyclopsData.

...

Additional arguments

+
+ 
# S3 method for cyclopsFit
+predict(object, newOutcomes, newCovariates, ...)
+
+
+

Arguments

+
object
+

A Cyclops model fit object

+ + +
newOutcomes
+

An optional data frame or Andromeda table object, similar to the object used in convertToCyclopsData.

+ + +
newCovariates
+

An optional data frame or Andromeda table object, similar to the object used in convertToCyclopsData.

+ + +
...
+

Additional arguments

+ +
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/print.cyclopsData.html b/docs/reference/print.cyclopsData.html index d768bd9d..08f4ea17 100644 --- a/docs/reference/print.cyclopsData.html +++ b/docs/reference/print.cyclopsData.html @@ -1,67 +1,12 @@ - - - - - - - -Print a Cyclops data object — print.cyclopsData • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Print a Cyclops data object — print.cyclopsData • Cyclops - - + + - - -
-
- -
- -
+

Print a Cyclops data object

- Source: R/DataManagement.R + Source: R/DataManagement.R
@@ -123,52 +55,47 @@

Print a Cyclops data object

print.cyclopsData displays information about a Cyclops data model object.

- 
# S3 method for cyclopsData
-print(x, show.call = TRUE, ...)
- -

Arguments

- - - - - - - - - - - - - - -
x

A Cyclops data model object

show.call

Logical: display last call to construct the Cyclops data model object

...

Additional arguments

+
+ 
# S3 method for cyclopsData
+print(x, show.call = TRUE, ...)
+
+ +
+

Arguments

+
x
+

A Cyclops data model object

+ + +
show.call
+

Logical: display last call to construct the Cyclops data model object

+
...
+

Additional arguments

+ +
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/print.cyclopsFit.html b/docs/reference/print.cyclopsFit.html index 7b678661..37eed6bf 100644 --- a/docs/reference/print.cyclopsFit.html +++ b/docs/reference/print.cyclopsFit.html @@ -1,67 +1,12 @@ - - - - - - - -Print a Cyclops model fit object — print.cyclopsFit • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Print a Cyclops model fit object — print.cyclopsFit • Cyclops - - + + - - -
-
- -
- -
+

Print a Cyclops model fit object

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -123,52 +55,47 @@

Print a Cyclops model fit object

print.cyclopsFit displays information about a Cyclops model fit object

- 
# S3 method for cyclopsFit
-print(x, show.call = TRUE, ...)
- -

Arguments

- - - - - - - - - - - - - - -
x

A Cyclops model fit object

show.call

Logical: display last call to update the Cyclops model fit object

...

Additional arguments

+
+ 
# S3 method for cyclopsFit
+print(x, show.call = TRUE, ...)
+
+ +
+

Arguments

+
x
+

A Cyclops model fit object

+ + +
show.call
+

Logical: display last call to update the Cyclops model fit object

+
...
+

Additional arguments

+ +
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/printMatrixMarket.html b/docs/reference/printMatrixMarket.html index 95f04b5e..eb499916 100644 --- a/docs/reference/printMatrixMarket.html +++ b/docs/reference/printMatrixMarket.html @@ -1,67 +1,12 @@ - - - - - - - -Print Cyclops data matrix to file — printMatrixMarket • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Print Cyclops data matrix to file — printMatrixMarket • Cyclops - - + + - - -
-
- -
- -
+

Print Cyclops data matrix to file

- Source: R/RcppExports.R + Source: R/RcppExports.R
@@ -123,47 +55,42 @@

Print Cyclops data matrix to file

printMatrixMarket prints the data matrix to a file

- 
printMatrixMarket(object, file)
+
+ 
printMatrixMarket(object, file)
+
+ +
+

Arguments

+
object
+

A Cyclops data object

+ -

Arguments

- - - - - - - - - - -
object

A Cyclops data object

file

Filename

+
file
+

Filename

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/readCyclopsData.html b/docs/reference/readCyclopsData.html index 0d6995b4..c2bd6779 100644 --- a/docs/reference/readCyclopsData.html +++ b/docs/reference/readCyclopsData.html @@ -1,67 +1,12 @@ - - - - - - - -Read Cyclops data from file — readCyclopsData • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Read Cyclops data from file — readCyclopsData • Cyclops - - - - + + -
-
- -
- -
+

Read Cyclops data from file

- Source: R/DataManagement.R + Source: R/DataManagement.R
@@ -123,54 +55,37 @@

Read Cyclops data from file

readCyclopsData reads a Cyclops-formatted text file.

- 
readCyclopsData(fileName, modelType)
+
+ 
readCyclopsData(fileName, modelType)
+
-

Arguments

- - - - - - - - - - -
fileName

Name of text file to be read. If fileName does not contain an absolute path,

modelType

character string: Valid types are listed below.

+
+

Arguments

+
fileName
+

Name of text file to be read. If fileName does not contain an absolute path,

-

Value

-

A list that contains a Cyclops model data object pointer and an operation duration

-

Details

+
modelType
+

character string: Valid types are listed below.

+ +
+
+

Value

+ +

A list that contains a Cyclops model data object pointer and an operation duration

+
+
+

Details

This function reads a Cyclops-formatted text file and returns a Cyclops data object. The first line of the file may start with '#', indicating that it contains header options. Valid header options are:

-

- - - - - - - - - - - - -
row_label(assume file contains a numeric column of unique row identifiers)
stratum_label(assume file contains a numeric column of stratum identifiers)
weight(assume file contains a column of row-specific model weights, currently unused)
offset(assume file contains a dense column of linear predictor offsets)
bbr_outcome(assume logistic outcomes are encoded -1/+1 following BBR)
log_offset(assume file contains a dense column of values x_i for which log(x_i) is the offset)
add_intercept(automatically include an intercept column of all 1s for each entry)
indicator_only(assume all covariates 0/1-valued and only covariate name is given)
sparse(force all BBR formatted covariates to be represented as sparse, instead of
sparse-indicator, columns .. really only for debugging)
dense(force all BBR formatted covariates to be represented as dense columns.. really
only for debugging)
- - -

Successive lines of the file are white-space delimited and follow the format:

-
	[Row ID] {Stratum ID} [Weight] <Outcome> {Censored} {Offset} <BBR covariates>
- -
    -

  • [optional]

    • +
    row_label(assume file contains a numeric column of unique row identifiers)
    stratum_label(assume file contains a numeric column of stratum identifiers)
    weight(assume file contains a column of row-specific model weights, currently unused)
    offset(assume file contains a dense column of linear predictor offsets)
    bbr_outcome(assume logistic outcomes are encoded -1/+1 following BBR)
    log_offset(assume file contains a dense column of values x_i for which log(x_i) is the offset)
    add_intercept(automatically include an intercept column of all 1s for each entry)
    indicator_only(assume all covariates 0/1-valued and only covariate name is given)
    sparse(force all BBR formatted covariates to be represented as sparse, instead of
    sparse-indicator, columns .. really only for debugging)
    dense(force all BBR formatted covariates to be represented as dense columns.. really
    only for debugging)

    Successive lines of the file are white-space delimited and follow the format:

    +
    	[Row ID] {Stratum ID} [Weight] <Outcome> {Censored} {Offset} <BBR covariates>
    + +

    • [optional]

    • <required>

    • {required or optional depending on model}

      • -
    - -

    Bayesian binary regression (BBR) covariates are white-space delimited and generally in a sparse +

Bayesian binary regression (BBR) covariates are white-space delimited and generally in a sparse <name>:<value> format, where name must (currently) be numeric and value is non-zero. If option indicator_only is specified, then format is simply <name>. Row ID and Stratum ID must be numeric, and rows must be sorted such that equal Stratum ID @@ -178,53 +93,41 @@

Details Stratum ID is required for clr and sccs models. Censored is required for a cox model. Offset is (currently) required for a sccs model.

-

Models

- +
+
+

Models

-

Currently supported model types are:

- - - - - - - - -
"ls"Least squares
"pr"Poisson regression
"lr"Logistic regression
"clr"Conditional logistic regression
"cpr"Conditional Poisson regression
"sccs"Self-controlled case series
"cox"Cox proportional hazards regression
"fgr"Fine-Gray proportional subdistribution hazards regression
+

Currently supported model types are:

"ls"Least squares
"pr"Poisson regression
"lr"Logistic regression
"clr"Conditional logistic regression
"cpr"Conditional Poisson regression
"sccs"Self-controlled case series
"cox"Cox proportional hazards regression
"fgr"Fine-Gray proportional subdistribution hazards regression
- - -

Examples

- 
if (FALSE) {
-dataPtr = readCyclopsData(system.file("extdata/infert_ccd.txt", package="Cyclops"), "clr")
-}
-
+
+

Examples

+ 
if (FALSE) {
+dataPtr = readCyclopsData(system.file("extdata/infert_ccd.txt", package="Cyclops"), "clr")
+}
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/reduce.html b/docs/reference/reduce.html index 8e8d571c..095deb92 100644 --- a/docs/reference/reduce.html +++ b/docs/reference/reduce.html @@ -1,67 +1,12 @@ - - - - - - - -Apply simple data reductions — reduce • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Apply simple data reductions — reduce • Cyclops - - + + - - -
-
- -
- -
+

Apply simple data reductions

- Source: R/DataManagement.R + Source: R/DataManagement.R
@@ -123,58 +55,56 @@

Apply simple data reductions

reduce reports the count of non-zero elements, sum and sum-of-squares for specified covariates in a Cyclops data object.

- 
reduce(object, covariates, groupBy, power = 1)
- -

Arguments

- - - - - - - - - - - - - - - - - - -
object

A Cyclops data object

covariates

Integer or string vector: list of covariates to report

groupBy

Integer or string (optional): generates a segmented reduction stratified by this covariate. Setting groupBy = "stratum" segments reduction for strataID

power

Integer: 0 = non-zero count, 1 = sum, 2 = sum-of-squares

- -

Value

- -

Specified reduction as number or data.frame if segmented.

+
+ 
reduce(object, covariates, groupBy, power = 1)
+
+ +
+

Arguments

+
object
+

A Cyclops data object

+ + +
covariates
+

Integer or string vector: list of covariates to report

+ + +
groupBy
+

Integer or string (optional): generates a segmented reduction stratified by this covariate. Setting groupBy = "stratum" segments reduction for strataID

+ + +
power
+

Integer: 0 = non-zero count, 1 = sum, 2 = sum-of-squares

+ +
+
+

Value

+ + +

Specified reduction as number or data.frame if segmented.

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/simulateCyclopsData.html b/docs/reference/simulateCyclopsData.html index 73d5b3f1..222a5a05 100644 --- a/docs/reference/simulateCyclopsData.html +++ b/docs/reference/simulateCyclopsData.html @@ -1,67 +1,12 @@ - - - - - - - -Simulation Cyclops dataset — simulateCyclopsData • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Simulation Cyclops dataset — simulateCyclopsData • Cyclops - - - - + + -
-
- -
- -
+

Simulation Cyclops dataset

- Source: R/Simulation.R + Source: R/Simulation.R
@@ -123,220 +55,253 @@

Simulation Cyclops dataset

simulateCyclopsData generates a simulated large, sparse data set for use by fitCyclopsSimulation.

- 
simulateCyclopsData(
-  nstrata = 200,
-  nrows = 10000,
-  ncovars = 20,
-  effectSizeSd = 1,
-  zeroEffectSizeProp = 0.9,
-  eCovarsPerRow = ncovars/100,
-  model = "survival"
-)
+
+ 
simulateCyclopsData(
+  nstrata = 200,
+  nrows = 10000,
+  ncovars = 20,
+  effectSizeSd = 1,
+  zeroEffectSizeProp = 0.9,
+  eCovarsPerRow = ncovars/100,
+  model = "survival"
+)
+
+ +
+

Arguments

+
nstrata
+

Numeric: Number of strata

+ + +
nrows
+

Numeric: Number of observation rows

+ -

Arguments

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
nstrata

Numeric: Number of strata

nrows

Numeric: Number of observation rows

ncovars

Numeric: Number of covariates

effectSizeSd

Numeric: Standard derivation of the non-zero simulated regression coefficients

zeroEffectSizeProp

Numeric: Expected proportion of zero effect size

eCovarsPerRow

Number: Effective number of non-zero covariates per data row

model

String: Simulation model. Choices are: logistic, poisson or survival

+
ncovars
+

Numeric: Number of covariates

-

Value

-

A simulated data set

+
effectSizeSd
+

Numeric: Standard derivation of the non-zero simulated regression coefficients

-

Examples

- 
#Generate some simulated data:
-sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
-                           model = "poisson")
-
#> Sparseness = 77.4 %
cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
-                                    addIntercept = TRUE)
-
#> Sorting covariates by covariateId and rowId

-#Define the prior and control objects to use cross-validation for finding the 
-#optimal hyperparameter:
-prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
-control <- createControl(cvType = "auto", noiseLevel = "quiet")
 
-#Fit the model
-fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
-
#> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1623936647] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
-#> Using 1 thread(s)
-#> Starting var = 0.226 (default)
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #1 Rep #1 pred log like = 657.252
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #2 Rep #1 pred log like = 695.827
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #3 Rep #1 pred log like = 565.49
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #4 Rep #1 pred log like = 658.746
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #5 Rep #1 pred log like = 796.882
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #6 Rep #1 pred log like = 585.307
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #7 Rep #1 pred log like = 823.083
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #8 Rep #1 pred log like = 702.257
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #9 Rep #1 pred log like = 606.283
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #10 Rep #1 pred log like = 578.22
-#> AvgPred = 666.935 with stdev = 84.8616
-#> Completed at 0.226
-#> Next point at 2.26 with value 0 and continue = 1
-#> search[ 0.226 ] = 666.935(84.8616)
-#> 
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #1 Rep #1 pred log like = 657.25
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #2 Rep #1 pred log like = 695.793
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #3 Rep #1 pred log like = 565.477
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #4 Rep #1 pred log like = 658.699
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #5 Rep #1 pred log like = 796.848
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #6 Rep #1 pred log like = 585.3
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #7 Rep #1 pred log like = 823.096
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #8 Rep #1 pred log like = 702.252
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #9 Rep #1 pred log like = 606.293
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #10 Rep #1 pred log like = 578.204
-#> AvgPred = 666.921 with stdev = 84.8612
-#> Completed at 2.26
-#> Next point at 0.0226 with value 0 and continue = 1
-#> search[ 0.226 ] = 666.935(84.8616)
-#> search[ 2.26 ] = 666.921(84.8612)
-#> 
-#> Running at Laplace(9.40721) None  Grid-point #3 at 0.0226 	Fold #1 Rep #1 pred log like = 657.255
-#> Running at Laplace(9.40721) None  Grid-point #3 at 0.0226 	Fold #2 Rep #1 pred log like = 695.928
-#> Running at Laplace(9.40721) None  Grid-point #3 at 0.0226 	Fold #3 Rep #1 pred log like = 565.524
-#> Running at Laplace(9.40721) None  Grid-point #3 at 0.0226 	Fold #4 Rep #1 pred log like = 658.892
-#> Running at Laplace(9.40721) None  Grid-point #3 at 0.0226 	Fold #5 Rep #1 pred log like = 796.982
-#> Running at Laplace(9.40721) None  Grid-point #3 at 0.0226 	Fold #6 Rep #1 pred log like = 585.323
-#> Running at Laplace(9.40721) None  Grid-point #3 at 0.0226 	Fold #7 Rep #1 pred log like = 823.038
-#> Running at Laplace(9.40721) None  Grid-point #3 at 0.0226 	Fold #8 Rep #1 pred log like = 702.265
-#> Running at Laplace(9.40721) None  Grid-point #3 at 0.0226 	Fold #9 Rep #1 pred log like = 606.248
-#> Running at Laplace(9.40721) None  Grid-point #3 at 0.0226 	Fold #10 Rep #1 pred log like = 578.158
-#> AvgPred = 666.961 with stdev = 84.8743
-#> Completed at 0.0226
-#> Next point at 0.00226 with value 0 and continue = 1
-#> search[ 0.0226 ] = 666.961(84.8743)
-#> search[ 0.226 ] = 666.935(84.8616)
-#> search[ 2.26 ] = 666.921(84.8612)
-#> 
-#> Running at Laplace(29.7482) None  Grid-point #4 at 0.00226 	Fold #1 Rep #1 pred log like = 657.243
-#> Running at Laplace(29.7482) None  Grid-point #4 at 0.00226 	Fold #2 Rep #1 pred log like = 696.195
-#> Running at Laplace(29.7482) None  Grid-point #4 at 0.00226 	Fold #3 Rep #1 pred log like = 565.587
-#> Running at Laplace(29.7482) None  Grid-point #4 at 0.00226 	Fold #4 Rep #1 pred log like = 659.291
-#> Running at Laplace(29.7482) None  Grid-point #4 at 0.00226 	Fold #5 Rep #1 pred log like = 797.232
-#> Running at Laplace(29.7482) None  Grid-point #4 at 0.00226 	Fold #6 Rep #1 pred log like = 585.335
-#> Running at Laplace(29.7482) None  Grid-point #4 at 0.00226 	Fold #7 Rep #1 pred log like = 822.886
-#> Running at Laplace(29.7482) None  Grid-point #4 at 0.00226 	Fold #8 Rep #1 pred log like = 702.347
-#> Running at Laplace(29.7482) None  Grid-point #4 at 0.00226 	Fold #9 Rep #1 pred log like = 606.113
-#> Running at Laplace(29.7482) None  Grid-point #4 at 0.00226 	Fold #10 Rep #1 pred log like = 578.005
-#> AvgPred = 667.023 with stdev = 84.9109
-#> Completed at 0.00226
-#> Next point at 0.000226 with value 0 and continue = 1
-#> search[ 0.00226 ] = 667.023(84.9109)
-#> search[ 0.0226 ] = 666.961(84.8743)
-#> search[ 0.226 ] = 666.935(84.8616)
-#> search[ 2.26 ] = 666.921(84.8612)
-#> 
-#> Running at Laplace(94.0721) None  Grid-point #5 at 0.000226 	Fold #1 Rep #1 pred log like = 657.235
-#> Running at Laplace(94.0721) None  Grid-point #5 at 0.000226 	Fold #2 Rep #1 pred log like = 696.232
-#> Running at Laplace(94.0721) None  Grid-point #5 at 0.000226 	Fold #3 Rep #1 pred log like = 565.599
-#> Running at Laplace(94.0721) None  Grid-point #5 at 0.000226 	Fold #4 Rep #1 pred log like = 659.49
-#> Running at Laplace(94.0721) None  Grid-point #5 at 0.000226 	Fold #5 Rep #1 pred log like = 797.258
-#> Running at Laplace(94.0721) None  Grid-point #5 at 0.000226 	Fold #6 Rep #1 pred log like = 585.335
-#> Running at Laplace(94.0721) None  Grid-point #5 at 0.000226 	Fold #7 Rep #1 pred log like = 822.886
-#> Running at Laplace(94.0721) None  Grid-point #5 at 0.000226 	Fold #8 Rep #1 pred log like = 702.377
-#> Running at Laplace(94.0721) None  Grid-point #5 at 0.000226 	Fold #9 Rep #1 pred log like = 606.113
-#> Running at Laplace(94.0721) None  Grid-point #5 at 0.000226 	Fold #10 Rep #1 pred log like = 578.005
-#> AvgPred = 667.053 with stdev = 84.9141
-#> Completed at 0.000226
-#> Next point at 2.26e-05 with value 0 and continue = 1
-#> search[ 0.000226 ] = 667.053(84.9141)
-#> search[ 0.00226 ] = 667.023(84.9109)
-#> search[ 0.0226 ] = 666.961(84.8743)
-#> search[ 0.226 ] = 666.935(84.8616)
-#> search[ 2.26 ] = 666.921(84.8612)
-#> 
-#> Running at Laplace(297.482) None  Grid-point #6 at 2.26e-05 	Fold #1 Rep #1 pred log like = 657.235
-#> Running at Laplace(297.482) None  Grid-point #6 at 2.26e-05 	Fold #2 Rep #1 pred log like = 696.232
-#> Running at Laplace(297.482) None  Grid-point #6 at 2.26e-05 	Fold #3 Rep #1 pred log like = 565.599
-#> Running at Laplace(297.482) None  Grid-point #6 at 2.26e-05 	Fold #4 Rep #1 pred log like = 659.49
-#> Running at Laplace(297.482) None  Grid-point #6 at 2.26e-05 	Fold #5 Rep #1 pred log like = 797.258
-#> Running at Laplace(297.482) None  Grid-point #6 at 2.26e-05 	Fold #6 Rep #1 pred log like = 585.335
-#> Running at Laplace(297.482) None  Grid-point #6 at 2.26e-05 	Fold #7 Rep #1 pred log like = 822.886
-#> Running at Laplace(297.482) None  Grid-point #6 at 2.26e-05 	Fold #8 Rep #1 pred log like = 702.377
-#> Running at Laplace(297.482) None  Grid-point #6 at 2.26e-05 	Fold #9 Rep #1 pred log like = 606.113
-#> Running at Laplace(297.482) None  Grid-point #6 at 2.26e-05 	Fold #10 Rep #1 pred log like = 578.005
-#> AvgPred = 667.053 with stdev = 84.9141
-#> Completed at 2.26e-05
-#> Next point at 1.40708e-18 with value 667.235 and continue = 0
-#> search[ 2.26e-05 ] = 667.053(84.9141)
-#> search[ 0.000226 ] = 667.053(84.9141)
-#> search[ 0.00226 ] = 667.023(84.9109)
-#> search[ 0.0226 ] = 666.961(84.8743)
-#> search[ 0.226 ] = 666.935(84.8616)
-#> search[ 2.26 ] = 666.921(84.8612)
-#> 
-#> 
-#> Maximum predicted log likelihood (667.235) estimated at:
-#> 	1.40708e-18 (variance)
-#> 	1.19222e+09 (lambda)
-#> 
-#> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(1.19222e+09) None 

-#Find out what the optimal hyperparameter was:
-getHyperParameter(fit)
-
#> [1] 1.407076e-18

-#Extract the current log-likelihood, and coefficients
-logLik(fit)
-
#> 'log Lik.' -2176.569 (df=3)
coef(fit)
-
#> (Intercept)           1           2 
-#>   -3.668132    0.000000    0.000000 

-#We can only retrieve the confidence interval for unregularized coefficients:
-confint(fit, c(0))
-
#> Using 1 thread(s)
#>      covariate    2.5 %    97.5 % evaluations
-#> [1,]         0 -3.69286 -3.643592          24
+
zeroEffectSizeProp
+

Numeric: Expected proportion of zero effect size

+ + +
eCovarsPerRow
+

Number: Effective number of non-zero covariates per data row

+ + +
model
+

String: Simulation model. Choices are: logistic, poisson or survival

+ +
+
+

Value

+ + +

A simulated data set

+
+ +
+

Examples

+ 
#Generate some simulated data:
+sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
+                           model = "poisson")
+#> Sparseness = 76.25 %
+cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
+                                    addIntercept = TRUE)
+#> Sorting covariates by covariateId and rowId
+
+#Define the prior and control objects to use cross-validation for finding the 
+#optimal hyperparameter:
+prior <- createPrior("laplace", exclude = 0, useCrossValidation = TRUE)
+control <- createControl(cvType = "auto", noiseLevel = "quiet")
+
+#Fit the model
+fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
+#> Using cross-validation selector type byRow
+#> Performing 10-fold cross-validation [seed = 1698757941] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Using 1 thread(s)
+#> Starting var = 0.2375 (default)
+#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #1 Rep #1 pred log like = 102.616
+#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #2 Rep #1 pred log like = 194.806
+#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #3 Rep #1 pred log like = 198.183
+#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #4 Rep #1 pred log like = 145.178
+#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #5 Rep #1 pred log like = 75.747
+#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #6 Rep #1 pred log like = 78.3006
+#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #7 Rep #1 pred log like = 123.887
+#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #8 Rep #1 pred log like = 192.631
+#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #9 Rep #1 pred log like = 153.328
+#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #10 Rep #1 pred log like = 101.303
+#> AvgPred = 136.598 with stdev = 45.0972
+#> Completed at 0.2375
+#> Next point at 2.375 with value 0 and continue = 1
+#> search[ 0.2375 ] = 136.598(45.0972)
+#> 
+#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #1 Rep #1 pred log like = 102.586
+#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #2 Rep #1 pred log like = 194.788
+#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #3 Rep #1 pred log like = 198.074
+#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #4 Rep #1 pred log like = 145.144
+#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #5 Rep #1 pred log like = 75.6951
+#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #6 Rep #1 pred log like = 78.2926
+#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #7 Rep #1 pred log like = 123.843
+#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #8 Rep #1 pred log like = 192.573
+#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #9 Rep #1 pred log like = 153.292
+#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #10 Rep #1 pred log like = 101.237
+#> AvgPred = 136.553 with stdev = 45.0876
+#> Completed at 2.375
+#> Next point at 0.02375 with value 0 and continue = 1
+#> search[ 0.2375 ] = 136.598(45.0972)
+#> search[ 2.375 ] = 136.553(45.0876)
+#> 
+#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #1 Rep #1 pred log like = 102.69
+#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #2 Rep #1 pred log like = 194.857
+#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #3 Rep #1 pred log like = 198.387
+#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #4 Rep #1 pred log like = 145.273
+#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #5 Rep #1 pred log like = 75.8784
+#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #6 Rep #1 pred log like = 78.3257
+#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #7 Rep #1 pred log like = 124.02
+#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #8 Rep #1 pred log like = 192.801
+#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #9 Rep #1 pred log like = 153.42
+#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #10 Rep #1 pred log like = 101.43
+#> AvgPred = 136.708 with stdev = 45.1178
+#> Completed at 0.02375
+#> Next point at 0.002375 with value 0 and continue = 1
+#> search[ 0.02375 ] = 136.708(45.1178)
+#> search[ 0.2375 ] = 136.598(45.0972)
+#> search[ 2.375 ] = 136.553(45.0876)
+#> 
+#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #1 Rep #1 pred log like = 102.69
+#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #2 Rep #1 pred log like = 194.874
+#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #3 Rep #1 pred log like = 198.387
+#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #4 Rep #1 pred log like = 145.273
+#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #5 Rep #1 pred log like = 75.988
+#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #6 Rep #1 pred log like = 78.3279
+#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #7 Rep #1 pred log like = 124.209
+#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #8 Rep #1 pred log like = 192.831
+#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #9 Rep #1 pred log like = 153.42
+#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #10 Rep #1 pred log like = 101.43
+#> AvgPred = 136.743 with stdev = 45.1033
+#> Completed at 0.002375
+#> Next point at 0.0002375 with value 0 and continue = 1
+#> search[ 0.002375 ] = 136.743(45.1033)
+#> search[ 0.02375 ] = 136.708(45.1178)
+#> search[ 0.2375 ] = 136.598(45.0972)
+#> search[ 2.375 ] = 136.553(45.0876)
+#> 
+#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #1 Rep #1 pred log like = 102.69
+#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #2 Rep #1 pred log like = 194.874
+#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #3 Rep #1 pred log like = 198.387
+#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #4 Rep #1 pred log like = 145.273
+#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #5 Rep #1 pred log like = 75.988
+#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #6 Rep #1 pred log like = 78.3279
+#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #7 Rep #1 pred log like = 124.209
+#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #8 Rep #1 pred log like = 192.831
+#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #9 Rep #1 pred log like = 153.42
+#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #10 Rep #1 pred log like = 101.43
+#> AvgPred = 136.743 with stdev = 45.1033
+#> Completed at 0.0002375
+#> Next point at 0.00014571 with value 136.751 and continue = 0
+#> search[ 0.0002375 ] = 136.743(45.1033)
+#> search[ 0.002375 ] = 136.743(45.1033)
+#> search[ 0.02375 ] = 136.708(45.1178)
+#> search[ 0.2375 ] = 136.598(45.0972)
+#> search[ 2.375 ] = 136.553(45.0876)
+#> 
+#> 
+#> Maximum predicted log likelihood (136.751) estimated at:
+#> 	0.00014571 (variance)
+#> 	117.158 (lambda)
+#> 
+#> Fitting model at optimal hyperparameter
+#> Using prior: Laplace(117.158) None 
+
+#Find out what the optimal hyperparameter was:
+getHyperParameter(fit)
+#> [1] 0.0001457099
+
+#Extract the current log-likelihood, and coefficients
+logLik(fit)
+#> 'log Lik.' -1805.625 (df=3)
+coef(fit)
+#> (Intercept)           1           2 
+#>   -4.287453    0.000000    0.000000 
+
+#We can only retrieve the confidence interval for unregularized coefficients:
+confint(fit, c(0))
+#> Using 1 thread(s)
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#>             covariate     2.5 %    97.5 % evaluations
+#> (Intercept)         0 -4.321798 -4.253487          23
+
+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/splitTime.html b/docs/reference/splitTime.html new file mode 100644 index 00000000..5b5c91ca --- /dev/null +++ b/docs/reference/splitTime.html @@ -0,0 +1,103 @@ + +Split the analysis time into several intervals for time-varying coefficients. — splitTime • Cyclops + + +
+
+ + + +
+
+
+

Split the analysis time into several intervals for time-varying coefficients.

+ Source: R/TimeEffects.R + +
+ +
+

splitTime split the analysis time into several intervals for time-varying coefficients

+
+ +
+ 
splitTime(shortOut, cut)
+
+ +
+

Arguments

+
shortOut
+

A data frame containing the outcomes with predefined columns (see below).

+ + +
cut
+

Numeric: Time points to cut at

+

These columns are expected in the shortOut object:

rowId(integer)Row ID is used to link multiple covariates (x) to a single outcome (y)
y(real)Observed event status
time(real)Observed event time
+ +
+
+

Value

+ + +

A long outcome table for time-varying coefficients.

+
+ +
+ +
+ + +
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+ +
+

Site built with pkgdown 2.0.7.

+
+ +
+ + + + + + + + diff --git a/docs/reference/summary.cyclopsData.html b/docs/reference/summary.cyclopsData.html index 98c75b26..654baf39 100644 --- a/docs/reference/summary.cyclopsData.html +++ b/docs/reference/summary.cyclopsData.html @@ -1,67 +1,12 @@ - - - - - - - -Cyclops data object summary — summary.cyclopsData • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Cyclops data object summary — summary.cyclopsData • Cyclops - - - - + + -
-
- -
- -
+

Cyclops data object summary

- Source: R/DataManagement.R + Source: R/DataManagement.R
@@ -123,51 +55,49 @@

Cyclops data object summary

summary.cyclopsData summarizes the data held in an Cyclops data object.

- 
# S3 method for cyclopsData
-summary(object, ...)
+
+ 
# S3 method for cyclopsData
+summary(object, ...)
+
+ +
+

Arguments

+
object
+

A Cyclops data object

-

Arguments

- - - - - - - - - - -
object

A Cyclops data object

...

Additional arguments

-

Value

+
...
+

Additional arguments

-

Returns a data.frame that reports simply summarize statistics for each covariate in a Cyclops data object.

+
+
+

Value

+ + +

Returns a data.frame that reports simply summarize statistics for each covariate in a Cyclops data object.

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/survfit.cyclopsFit.html b/docs/reference/survfit.cyclopsFit.html index 34bbfe06..300ce6f0 100644 --- a/docs/reference/survfit.cyclopsFit.html +++ b/docs/reference/survfit.cyclopsFit.html @@ -1,67 +1,12 @@ - - - - - - - -Calculate baseline hazard function — survfit.cyclopsFit • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Calculate baseline hazard function — survfit.cyclopsFit • Cyclops - - + + - - -
-
- -
- -
+

Calculate baseline hazard function

- Source: R/Survfit.R + Source: R/Survfit.R
@@ -123,51 +55,53 @@

Calculate baseline hazard function

survfit.cyclopsFit computes baseline hazard function

- 
# S3 method for cyclopsFit
-survfit(cyclopsFit, type = "aalen")
+
+ 
# S3 method for cyclopsFit
+survfit(formula, type = "aalen", ...)
+
+ +
+

Arguments

+
formula
+

A Cyclops survival model fit object

+ + +
type
+

type of baseline survival, choices are: "aalen" (Breslow)

-

Arguments

- - - - - - - - - - -
cyclopsFit

A Cyclops survival model fit object

type

type of baseline survival, choices are: "aalen" (Breslow)

-

Value

+
...
+

for future methods

-

Baseline survival function for mean covariates

+
+
+

Value

+ + +

Baseline survival function for mean covariates

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/reference/vcov.cyclopsFit.html b/docs/reference/vcov.cyclopsFit.html index f0f653da..b755e776 100644 --- a/docs/reference/vcov.cyclopsFit.html +++ b/docs/reference/vcov.cyclopsFit.html @@ -1,67 +1,12 @@ - - - - - - - -Calculate variance-covariance matrix for a fitted Cyclops model object — vcov.cyclopsFit • Cyclops - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Calculate variance-covariance matrix for a fitted Cyclops model object — vcov.cyclopsFit • Cyclops - - + + - - -
-
- -
- -
+

Calculate variance-covariance matrix for a fitted Cyclops model object

- Source: R/ModelFit.R + Source: R/ModelFit.R
@@ -123,59 +55,57 @@

Calculate variance-covariance matrix for a fitted Cyclops model object

vcov.cyclopsFit returns the variance-covariance matrix for all covariates of a Cyclops model object

- 
# S3 method for cyclopsFit
-vcov(object, control, overrideNoRegularization = FALSE, ...)
- -

Arguments

- - - - - - - - - - - - - - - - - - -
object

A fitted Cyclops model object

control

A "cyclopsControl" object constructed by createControl

overrideNoRegularization

Logical: Enable variance-covariance estimation for regularized parameters

...

Additional argument(s) for methods

- -

Value

- -

A matrix of the estimates covariances between all covariate estimates.

+
+ 
# S3 method for cyclopsFit
+vcov(object, control, overrideNoRegularization = FALSE, ...)
+
+ +
+

Arguments

+
object
+

A fitted Cyclops model object

+ + +
control
+

A "cyclopsControl" object constructed by createControl

+ + +
overrideNoRegularization
+

Logical: Enable variance-covariance estimation for regularized parameters

+ + +
...
+

Additional argument(s) for methods

+ +
+
+

Value

+ + +

A matrix of the estimates covariances between all covariate estimates.

+
+
-
-
-

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

+
+

Developed by Marc A. Suchard, Martijn J. Schuemie, Trevor R. Shaddox, Yuxi Tian, Jianxiao Yang, Eric Kawaguchi.

-

Site built with pkgdown 1.6.1.

+

Site built with pkgdown 2.0.7.

-
-
+
- - + + diff --git a/docs/sitemap.xml b/docs/sitemap.xml new file mode 100644 index 00000000..0ead7e03 --- /dev/null +++ b/docs/sitemap.xml @@ -0,0 +1,186 @@ + + + + /404.html + + + /authors.html + + + /index.html + + + /news/index.html + + + /reference/Cyclops-package.html + + + /reference/Multitype.html + + + /reference/aconfint.html + + + /reference/appendSqlCyclopsData.html + + + /reference/coef.cyclopsFit.html + + + /reference/confint.cyclopsFit.html + + + /reference/convertToCyclopsData.html + + + /reference/convertToCyclopsVariance.html + + + /reference/convertToGlmnetLambda.html + + + /reference/convertToTimeVaryingCoef.html + + + /reference/coverage.html + + + /reference/createAutoGridCrossValidationControl.html + + + /reference/createControl.html + + + /reference/createCyclopsData.html + + + /reference/createNonSeparablePrior.html + + + /reference/createParameterizedPrior.html + + + /reference/createPrior.html + + + /reference/createWeightBasedSearchControl.html + + + /reference/cyclops.html + + + /reference/finalizeSqlCyclopsData.html + + + /reference/fitCyclopsModel.html + + + /reference/fitCyclopsSimulation.html + + + /reference/getCovariateIds.html + + + /reference/getCovariateTypes.html + + + /reference/getCrossValidationInfo.html + + + /reference/getCyclopsPredictiveLogLikelihood.html + + + /reference/getCyclopsProfileLogLikelihood.html + + + /reference/getFineGrayWeights.html + + + /reference/getFloatingPointSize.html + + + /reference/getHyperParameter.html + + + /reference/getNumberOfCovariates.html + + + /reference/getNumberOfRows.html + + + /reference/getNumberOfStrata.html + + + /reference/getNumberOfTypes.html + + + /reference/getSEs.html + + + /reference/getUnivariableCorrelation.html + + + /reference/getUnivariableSeparability.html + + + /reference/index.html + + + /reference/isInitialized.html + + + /reference/isSorted.html + + + /reference/logLik.cyclopsFit.html + + + /reference/meanLinearPredictor.html + + + /reference/mse.html + + + /reference/oxford.html + + + /reference/plotCyclopsSimulationFit.html + + + /reference/predict.cyclopsFit.html + + + /reference/print.cyclopsData.html + + + /reference/print.cyclopsFit.html + + + /reference/printCyclopsRowIds.html + + + /reference/printMatrixMarket.html + + + /reference/readCyclopsData.html + + + /reference/reduce.html + + + /reference/simulateCyclopsData.html + + + /reference/splitTime.html + + + /reference/summary.cyclopsData.html + + + /reference/survfit.cyclopsFit.html + + + /reference/vcov.cyclopsFit.html + + diff --git a/extras/Cyclops.pdf b/extras/Cyclops.pdf index 19e904759c297c89909e69e87912b9426c2a8456..f6e48a3ee3750260e83e5938ce7acec24dae18dc 100644 GIT binary patch delta 122633 zcmaI-V{j)-^eqaYNV`AI3?c~n$Kez6A>(r^YKkcgS>TkXF zT5GTV-hfL9g+?J){3TA$%)kyqKD#))3d79FnTTA32Exshh^$5hNLJslJ>Wp{nNfeO z=0I8?acK;2^(V`u(<0mGbA@??NQyTPk0yg5>;7}I;%5Fk=1BDr42nbvZ#s+HX>S$x zh}7=!Y|`tOEPe6e&!cOn0!f)+JYd4-1goJ&GN+g+u3WnbD4m-1R2Ie89tAL4|0 zc6ZfBN%}>`5>dhhg9Ozt6V_#H>rzeOz_iVAc}k}5&J8U;=|kwM^=beM7|r4}sY1?e zTE6w3bm6vU5MmD3b_&7G(ZZ|^j>E1kcOCLErZH)5iEOq9L~Vv=(M~CkOa$&qhp#i3 zXRoCmiTm!MqQvy30h*fh7_GEy(bWfIG`*LZt(CqZn4kX2(jcTjct02gB`&iQf{)^| znGExy;pCFrJwl5T53R>)$y9=PuX|{OM{%3|-18N%*E)4BinPJ&mWptQfXrO0SQ`2w zg*{Rstr-vj;70u5!ldIA;6DFwXp^CTsY`xG<9seetaLfTy0usobPIO|7XEH#rkTP!1P0TgG@GlN2|Q2Utc>EFdN9om5b3f>&K4lyOKc$T7wMFf3>)ObdBAz`#DjiZL4Ui?4UB z%Zg0K#$&uE_EQ>JE;M4RTv|ACux+S!M&ehjC^WMh82Hh_4Q-BqW*~iOOOhYH@{Q}7 zv?J;x1!7Y(oAOwkR67n;K~>My08s66u&o-_XZ1TTYzJ>(hDxn`K?HYohzi!dpXQOE z=>q$JXtKpHuRq>ApaFmM!dw+Vkmx0K!sJF=SG~JD=|qm2?JSl-fjnx@MN36R z;3c9+m2~N$Q}b<7qol?FX_uUz{bVYi;=qS=C+BoezC$?!_Ra;?;EV2YHyGVt@2-m- zjWi$xV8itmV>G>}-?aBPQqrmg!+;C5G8->W_#!=nyKTQ##EPz>^5V;B=#V<%@v69b$7 zDmz0<7#0?;e`tmZ%EZC?KX7)HDd)7$fi-gD4MTX>UsHvteO@h-$(DVY0^P)K?PXsl z!p4q48tHsiT5FsM27+&l!LuNY2^SbOsW9`Ii^&ht&j-|hwL9p1J0%ALg3*Xp(*H;; z2^5AbA4mtzEXxH(Ylp>*w^;j0CJ99kd4>>0Gj<43POs&CKm>?fHP=dMK{Z0XLxd;qv)8FcyUejxx=Jra0;@ZZZ2BQj(4Xl(18SxELP#%SH|obYgp zBc_#p)+XJZC6yABh}Q4+hDasAIW=P}c^ey#NMe`}++!S0A~y_gFi)TGMJcAZcMG(@ zZIw1wL!7IL-swEtsA+A}C`BbzT};o)C>?5zT9VOL8(U0ee*)}?c?<)sCAXs5`kx~x zNCoy^Y0mV0%5K{DU9S$aiIk1jq~<~IDK+I@S=8T*#zv$i(Z#7ta?S-*7X!~%J^4Xh z`q|a@?R2eYL1LeQv^F7aWKhUQWo|W{({VJfn?ZWl?9(IP8o%RKy3%fSrgHTDkWHK} zt=XN6-_VD1qybRuD$JsTaamopp|lrg|2W?%VRY56PmQax5Qr1BosG}z;kBz8l z_?g@FvF3(k`jz^^X?F>u*DJDvHpDS?on{c;7cB2amu3{a1ZFJ%vR_HJ!!ln^JPT`8 z0oHcmN$mz=DB!Yx$J0-uR%cYONbwu1kB%;-0Lp{d_tpK~>E0x1hB?a#$!4vFd(^z) zcWQzdr2+XX21&w~W47@ww6+oNH7Ht##nmg?VFDfkq1J8vjG3P{wKG&=;U`#K&R>4d{SVwY#4-nr4S+8QbVA_x&Gsz}t}& zjdr5w>Os%q?>3uJI_+-3+4+kV zi2j2WK0X*m6%Tt8B1Q#6OJ!#p7)E&_W+o;WMsW*ACubrq)_n+g6|IMnEoDN;%*K4b z5KK~H_{LmO+<-~OQ9N=Uyc5u=hL9=@MMwwGDA_2O3xga7j6yJjthyF{ z?L+6t*g`}hqvy90N&gL!G6dVkHiV;e03$+=#|oqZgbWE8`^BJZg{z4Mqy%Xr*W>ts zq5no@fJ#Qr2~1FlvX_BL194yXW4MJo081zX?okX9OG3_{!;wL}Y{QZi$3jhz^j{W8 z4I0iswSYR9Rn^??^B<5km(F8u3K8j3);f@I41t7z1ZxaTX>fq%lr}X2%}dap-X#mh0Ih(_LhLS&u{R0^k)eqY(vOg|xdQz{w-SNlWcIcJ z{HX+slCzPK@_ zAbt?MFk#dUVox_txh8K6|s96nKc>hmH|gCd!_i-=b@UqR^FG57a7=%Fd}d-xp1n3pG(v z)l2l?kUOs$4HeT(9qv*$JPWq5-u~okPE7_ZGkxqzu$?P(9~a;Jew+Af`S2VDh|a6J zN;mj0+Y-;Yng1TP>=8c(4zJg~R$|HDyKf&IIb)$t%=F-)X)N#-D4em8iTa8(;r-0) z#8v1xW3hx35Bz<-&kM37rd4Y4?8f6myr%?ND>uJ$b(Jfp_xBzBS1##ED_iE) z(oF(QcFaOi)@CF5=2TGHOG4cKqdnE^F)3)PkSxI*~<`En9)N zTEMDwypI2e>?&;wrqao-z_RzVa>T^b8A5$KM&`#FGPSu>+{7VsYC&NbaH;&vpKazQ z#>}6zYMUFq&Rys5ULx*$Z)f&xws7=8vH01@yW@c$-JOwb;_;p@ORz$IfW(^HoXTk7 zWvI|q(Qg##SxW4K_JIgsy6@Syve2H(j^s4Jhh#Xa%>w}Q@ zTu(YXZYC$#ts_v2!D;aZxTu~<65V`RTL}uz4dX2GeVTizvaWb`?4tYTq3D#Exvm{N zjJ;?u%YG7pICx%ccFP85(7Ug4KwH)rETCKXF6bRTi$q+uE){K2Q^mzhxsv(@Z|q0C zw#`qQYJ9&ti5JxWN^7>#CB3TG4y@vtY2+Dffw&lEm``UMKC$TmxMUu6SuwBDJ8jFN zdbJ!rWUGFecixF*9Of#XCpxN>ELi_`s};q(a?#!{NphTps#33 zm1r(R(W^RUAFx~FelO_0EN>+-R*vkfj||-?xP(g(PlVJ1;V5511)gZGehKPx?1hfS zfSkA=Q!nVrK557XWY7F?Ij>GP4x7~4_%6HASf`bEx$bLs7M>}+>@0ac_1;(sH3O6Y zn>Qd!C{J6y_!lOPmsGtQxxJos>XBl<1+F6pEBMhFc?1gaIY}y2Jz{;MTZg9L+SiT*KCM0hoFDB1B&lRzcUG{Djx11D zrZGW<#wiFQAF3o%7ZHlZ)-%HH>1x9jSw*T3^*tWW{wNt;v;?EAqd8jG$V^@HSrF?w zh<+*{0g6*ATM7?dK>Mx7QGL>_5?~iCXTmj*^b~SG!mkMEg7mn^b1tvUe2Ag1!qD9< zMHK9B7*6;Ad#}0z3!)6xL@s@C6kClxqiElQrReNz??8BxcFEA1BG#YWv>DBbfJ-Rceuf-3bixk z0)>P7pWYwgD1SLJrCW-Xh{MXa&yHF~F+=ujZc(T@b!P$5L)6TFAor>8Gm7dpTbllX zywOh? zZC(U4GtfuN$PE6uxQ!ZQMVR5@Yy4~UkENb#9j~u8Z#EA!|F6>su{?a|w`GHc|3{HF zXoL{U&3AnJuP~J0cHC3Qc)gLQTK{~FS0qU&BS|Wg1j9)Jiw+zmu>4IRY2oypWWDlI z%r6y@dGD)&fMS5oEYkdh7Y7|O_mdJR(j3DNUasmVRgw$x1C2(82-Yy*Bov;X@ZzK> z=pPsc^0kOCppWulM?FLn7T1*ng6Y4BlFa(WwKGf>~q*(1|hSgVE96I_O&V1RQ}-K9v4G zA9+?w8$LPG_CklR`AZe7DP0BFzeaH(VMU|cqB8?b)@_maA&Nu!ryb^1nGp(-Dy|K- z_7R|Szc!*)3r8_e8d|=fY)<*EUGVC5N}97ofsv;D#WJP}VWtU*k1ANLboa>IoAUvQ z#CzG>{4~J{1)`lIA%V_V>DZsQ%U%YbKFLKQDc&7#%HAJKTL=&e$VCM>Vru=CC8L)6 ztr54%`wD6|ATcxjh=dHrED$@Xkq6%M zm5j{jnor+i++J#Os|_H4Dqlr57R4GtrCrzPs16@p4eDm-_&&&Sn(jRMUXvf2+$F>y zi4+3%R}jkK-N&-m<|>Ur!bj}Qm*dBIX=kQA!?HBzXS5pcc2zsgjEo3WwJTpTCgc$l zWv%r|-kYcPjrKu0_gUnlB1|Ce0ZB7{{0;Z1=90^FIMr#CJ;VWkV3S~^@{dP#^P#Ly zYZw(l(Vk&z8;etBb%RuSIvU`iqIZAY?!>lUoC%ffjnHvo;{v1riIP~NH2mjemP8^R zItO9a8rOwe;M(_Ehlo!yVyXSp`9nJBHkqT_vN=piah?l7_rdIBUhV$L<8#g0T@v;I z0@1{0K%t(K<1!eahY5c6+c~62q9m5<48QUNL~+@YbX?$y;dB1+sX$$wiG@$F&^%)> z&GhF=rvy469iGWPSqs|ad&|5<>|&sT?~jX15uBZ?ECJ^{w}88`Z;N)q3BLLttlgwz zrvA5;^j$P1Nvbbt)J+4b$s=mr!?+NaK2Cr%P12JE;FIs{$FH&UEvFrkl(-gliNvl!#>}n|A7eL|Cu11iSg`cpzPc%|KovVYbdy7av}A8DBsQ#+7Vdn`nH%rxa1VKK zdUdB~_sE4MzFVMBOqV!=h>T4_4d zlJWlJ_rV<&MO}`;tnv}6e7v0im~Tfvw_59x`*t8ilh+>WVxhj!5*w_{iOkHR@RxfC z)ADDj*yi6Uc47{F)5JUxbjmI&h@yepb{29c*4+cDjCO6s4vRlSt_>#ct10~Nt4i?E zt8-xA3(W$~p@*a@sLT_U>Bn&Nw`K-crz%{DEs%tlZOUg+(!WnfkMS{4xP%@8`V-q+Y+Nh{r8woj4-3CzCcP! z(6WHcP$jWg^w>a*H)iJcmQsck~)Z{#&qJWKtih(D56{WV8i4v30Hk5nhBdYsj!$j&2TBN?>aY7S?8fmHxg zM|LY1xf?fL(Z-o16hrn4#oPup6pIu)_A__mV~5LkCq~WM&8d`@MVjdPc5GxFEU8*U z{F(+CEmfN5gs6%6Ie#-%GG|`8f7U3H7*5i#szNOdJm`2?54Mf}vUn7SizkUk(Jutx z-X#~0LQI%ZGs*j^S{}4Vqb^%pF$h4}JbIOaJ7_z4On6hgk~%f2#q+~O)wb&6-p39P zs+D32T`YD}0G!C5neDj{7?(Ojk?;&hwho1(5Y*Oo>adx>7CRTZQk}LNm*&fCz<8eFve!7Da%4Ak!`M zqb-KHwHm}HCGYfl3MVB6)ctjO+$7{yrU^$@YWL;c>*zmA+iBa4o2%sy9{-~bHaTnt zF^yzqCO&>Y3Z=OO%BvF2hIvDQJEL7k)-{ie?Za8^gFm@A2Awo09l^}@Yyx{5zB7ks z9jYvW4Y!I#WQj{aVXw1O=pNv-?faQN;v}H8x-}FOpp%HHeA!bWj)=48KNd9E0R0 zp9eA;y7XrKV1^aS;Of6)#vi~XCZ?sVHPh=sF7*>z1v+0`=cZa-*Bl^k573U~N`5%G zjP<(VdNORy?F3@g95A)mr?jvS@+$om>)EfWPwl@l!oxJRiw)>G76#Wjk;=RN#ZNQr zjosO`+<4tbiIumc$jHmCK2=aO;oCrWn8^ffXH}^KGE#uE$SmS>((LhZp7ZEd7jR7` zowILuq+W^1O`|RD+w?bkM<|hT^?Ew<+5sT8iJ8p%(+~9NZW5q$R}~i{o%(lzi6$5Z zII1Jida~$eepSt|52;ThSZLmuvP_hyoChp!0=fUMMuO%7$X~UK#3N-?)gb+#^BG&d zE_>vvt%vPz&493&pXAp>-$15sNWjp}(Erh6{%bK@|5^+x7&j|3(f{|tVxnIfF?oCo44h~RmuRFu70QtXK7>|*kxfIHQq#g^Eg|4<%DMZqU(HseN6EFo zmd~d!ad6?Ih{LdG1KNRs8HEa zzKnr5J$_7fyG|<_i$^QKx9(maeij-E6LGy~q;TK*5nRWL?&hxbh}&iM$lWiy^|;U& zfd<`GtBYZ|05_R52qQM|3cB1+amwz@TZypz5DukqM+u_A)%S;Hy4MJolfS?np+kW- zWo2b}0~M{fuKre35Gp&J`3q}Q(toejL#=dxeWQKC~8>BA#7ghq! z&t1-gqFFGXMwTDk+7+jr^`Vd93VNc9u9jDSFndIXYqqjk2Q6|E2%oTS_Ks$1PQ>px zIXyh-V(dC3=iz67Uom!C!6DKzRy-UT7^3{KhCzbpz|aq`K>{P4>}PY(8+#J<$&=kt z*Lq-5k-l`pV8al#q|qazNqDb`W`bRf-uFra9)c!6h7m}YG^1FM{%f0Vy|^pn$mQPM zc`Sfw*NYGowSes7p57iiI+2W-Usc<|9Jg|9aYeK?lIkzu95VQPo5%!9P~ayUeV&IZ zSz3$zSmTMc{Siul@ZqLBLFQr>My(+h=`TDj|F3Rc_AP<^=55{*BqO*%?#g!g6Dd|$ z2$yHZBwCd}bU<^)?%?u;P{<1L4SZtbY-su6g=IQze`cZ^yf({zQg9!H0R1-3c?x4f z+$l*Te&nct2NO+_L3w*NsT#rZmD2F&))EyeA#%jhy(KNElG>QtdCV)@9X=jj`ml?&(9X3blOQCRhqdN2af(C$E&N%6E?h&C2&W5l>(X1{e5MVp zyA_(YpafXxNls7$;;Owz54_-?;LfQZcYI%6tZFMOC@;!Mruq@~GVh&aXL42=UFduM z>qn5*!SmDm>taO`_sULx9IF!ebUa#*(ZNiIr6g5ha?DWJ6&y>C z71am+_3p9vMXTlRt(9ONO_r=E2w$wKq|2<@%7xglEf+B2G;J(PwCLjCkwgdTvF}93H;xT6;l!P@!FwuaP zrP`YSAa_=DTHE!r$8b*lm&>)lE%F>2Gxz6%F~rJ5vsB<5F)A2yCT$y2Fr!1yers&~ z!%pWGY15nI{{6voN)4=Mj1IIy{jnNZK9yyd0{MH zbPmL5X-~*qfJ}<%lD{#0Fp9`7F^C)+ulkCgOlOps+RZ(4xeoOK!ax$o&>|R7?G%dA zgvRCN;5(wmhYl&>y*$-`3UTQuEc{I}U3wM3O+7sR-0vJp=~Al#T}H?}&}>4c8bYN0 zSOG0UGsT6(qmce0v=Z~Zqy97CI#I>0p4t+Q_N$3{Jv_)tjgqX1Oj-m?tVc?O+O~9X z)`}4BK)pWi`_mPQi~X&PR;Cy2J)`(d0<>}3Sj*T3C;1H5B=R4fdrqSoal_|dhHC^^ zPPVS82rRYuln#eltP+X|k8S99_*WWp?RCN%!q3JyGcMo*-~wcZGgL#Ry5hMLZ4f3a zn`RIsw43a8%9IuPD#jy5);o~glwmGR_SY$}e?gzD5(wjtO~NAePZ*?$j(BuyI~^#b ziDcCIxKP=F#pp{G76ix7Ph*zG&Yn84Lmr{*je+FFyAA#Cma;rXwg@q3Z)L#Ho>pwp}AgGdnOIv{RNosa8XAQlD$8;E-BI zN^le+AcbN>_@kiU7Gop~PFW>Ru1E@;B45fJ5Ra)?lX6eK26+NH7^{-d8ukSHu+kc2 zM1x3KN4od#waEC#s^#EgS=9i|KBolhpk;po_y9nk{KelVA@4{YO!KaS?40LjB|oHv zOyu@rnF&|!l$XTXzCnDOEg>fzow{&8@z!3+;y#(b(=16dd(oNmd#J1<>gzZ5UN>_g zWM6?nvid-y-VbT-iB{Hb#(4OD1)KnX>|EXY4XjYB?`1`xtuFM z7K51Y`9kfoHEm3-=OF;d+l()X9OcaYn%?{x4m)c;lyk;D*V^G9Y-pDD)9q!IjlMNG zB_6*=`0527_1T7_Eqr1nN4ZepKUT$p+!5ylr#`^oKd57wq3SRflO`x@S0x6uRO=e{ z^~gr9zdEm<&s3y)m`Cdjega)Y^H&mP2`J376BO{!|A;OAu?qoog*L3jiZhi)X33qc zap61^VBf3B&0NHL;g}tjj~NQZ;l7EkHIlUl^cP2Y5JTcJ&H#KL8d4EEJ%svAXuPH= z4>niHIRxAdNW6+U%4a=w()1%(R8ehzyxFXK)ozwj7IY3jn*d1H=!2=1iM>FIUuu^B zKcM_y`QN~imFa&_8I*cR#_ES6USh>4p(x*0(4(-M00OR91nDUN z3Q%wkLeI2{AsTg?@&bTiVc=Q;h+7hwKnZ>aTqY640TC?q{?akK?$$lkK&V1dB(TD? zc%pu2LxW?XMZ~V;NK+--w?EqgsZZ|}d$f%6t(?$zcuGmdWNDRFzoH5&OLCa`RHsdy zq|a2WaaiF>4O3fL14;uj0qPOlX&J314DIP84`&_*_m_jI&(3y)^6GMx z1)-xSeX1D46hhEICx{TlvQbQJz*%J3zWr$oGP*MUY?pIGL(n>dx9sI})L{+C_``68 zLF;HbPW9Fk*>wK>qRTIr9~QE}>JdV@W~f|>r1@wDD7@?pHh-i10IC%l^JdY-87@;? ze6Cuhb4_OW1iZ^jbQjT6YkUJ5jrTH?SJ_PuONSdEC5ed!+Q7Xl>~+^IFsEa;3ZYjb zxJhl4$z&lgH~&mRfT&yi#AcM5P0tYnWb@=i$4vOLaw|cp=hlG=C&4tQE^gy~u&Qe|TNPUiV4NRh04)Q_Nph%$rg;8j zbtOEX?UFgyG`WmXFUhm%ouwyhYXfHpXkFvs8NUxgN!x!Z@2W*7BeMZ0J2irH``P|! zDdKh@he=Hfn-zzfuGR{{qIxJEi1v`Ec|99FRpfWcjo1?LY&!GtecBj@f@YSlhd=T6 z8s_g96NcH?D+PDYrQ3;N3?%c;k?IH|Oy`k@$(pePpbX61kg1ZEQ8&md*&hNvWdGOf ztSB`}olQ1tz-cd)<4S0+@Qz4J`(;a^MKsH=#7A!}L2SaFze_y_zj)U;z&Yg%u#Ca9 zKiKY+sd?Zn`J`EYyp#Tp093-;|CCX=tmxdSHBaUsrAm%zSJFGQ1kgj9aYxF#)yTZP z6S~$g18{N}3wAa3ysTb`7LVTtj*eb2_N>7;BiPkNS~RTZcr9FN>@LBJ@f@1Ok1u|# zlwsypP4~S2uq&9(W@NSMKyeY{8yg-ZSi2eT>!U9XYeYd2^gUvRKmY_UkHx;}Vy;K~ zRk1`rOp&F-u4LUBqvZdb^cbHAF%M8bxGq1>N*3`p@w4IY2zQDuydAq7db9cVkt2(- zz4!m{$HnDSUCbyTei2fhd|UNh>p}S3hZX^|whJJZ6Z(Q+c>fxp`ykNx0kVS2@Jz&a zBTB?8Vg+=oZ#iXgAOU)N1IAD%!Nfp@B+TA-+oVd;+ZHIyddWQEgxw?{k&yK%e|*#> z?fqt$S3G$Lv`?*GT049HRM$7R);-xicy@X`aSW*iB+SBAUrm!>kqSapQw@c^=QK}M z&A48AZ}o%*-W}#iPzQilDHJ6%rsz3WyHh?~{su&pv^zi%bI{&LHMf^Bh%HGgQAy!i zFZO!MB!)|_j5>EqR$Gkq-cclbRR5a1CNOz*jv%Z_1oLn(_6z4_Sj)kMEh&K@&^V9A z2y3|3+UD{D*|_q*h*jYVT6a5-O0h02PtM5hvTW~i;)6-y)H>Vzi}a%P zhY8TFHZIrrC zdIaq<*cqzj<LQ0QJr)iawk;2{9kPRK>i1inhT2=*2!s@#P99iOsLVGT!D4&~F&JDm+ zE4;s)b$oq+vaDj3A}u{?u4k3ND9}*h4fH&rH>6Bh9h3k*?^lunGcjcR|pVA zdHkY+_)FsIHgq{=XUIkDM;AX9>@MVR%BJ?<$w;W{FXVeso@2djoNjfJgJHl74PjCv zn8A$RFU1AotT|xQ5Cj+_taZrH^$-Lh@URZUXGng7WNiOC+re~M#CKO)j$gx1 z5)i>i#=TBzD-@2G0_l>-5*obO{D?cfx3=*Qa%BX-xl{?G`9hhIW zyPUY01V(G8tHebokB+d@HHguxC)BjQbJdxLHRofpbumYp`M5L<4U195^M7F$X3C3P z^4Mc) zF0;DzwaPYRuuln19*B|_H`;x9;X*)-e1GlDH2qMdL*3o~gZMZgAomwuL1u|3hrPM) zIfVx{C#Nhe-;Z$YA_CSE)iNAbzXBip(Mp~wPnc8~n6wQC05jL1igueDQRtUa1rFXN z37Q?iP<0B^8<+`(MrTQ;N;6kqkf#I+UYBpg zRBosN;jD{35lt>coU#C{1{Fb!JPKZ&SE%Ks#~h>raQh2Ge&sGK?J@$})^PyNyrhV3 zBxMx~F0NO7iIMudur5Kvk{Ftf6NZ8|0_Kq%Nfk9*Pmwf_1W8pnCL=^75=UXmaBWVM z_4F4}g_;sQlXxXY!r#UZX{JVusQl8!O(J9@i><=EG3WsOvN9$tJzP@@=NPUE$0cNph-47g_*_I#Pb_RHDO8a zcK5qk;>XO{^%nX!eZM~o+;5o~`k=>P5D&Enzy&oD{d9kaNvzLfu&9##JTyWBA7tp6 z<}+SZ>gEO*_@5k+;4`B{K>jQa)zX0@)09h*r}+(K12KJYeuXG#JKOuz<)O;a^MXoyYLPcg)?h0&?^okyn--QG|;PVZ%AYy9eG{BUPB;6Bqt`(lZzn^ zk#vcR0X)!*fP=!(_fSz8a{1l>4>k)F5fXzoOEmGoQQsKDMUgD>aQwe52LK)_USkxR z)GdO5gZ|h(Gujgrfp|nzCs1}+zVRDS2wy-bKlr&lg7R1m9U-q`@YzHieOW(u8eVE( zKlkEZS3yO4Dzw!2eLW~~7CHW*kfd+v0A{_$OBPdBvqw}5~3Zrgn2E_J9{;iDAOx!%{Y zhu@>6pKalNY*51D%ll!ErTZT}p-h{x`~o7inPyp%cF+^1EmxDopK>u)>Ew*;HqZNNK9GEZYZkSI8%o;r0YKi>;`h2>?LS0T zng%5Wn{n9VfvpOg+o$ow(CFi~y#)ZJ(Iw7g>1UOVdsiEdbaavE)!X~z>fs3MJy(0r ziQh%;NKYu9tZ3PK%FuIW)*dmtGAbC~{N+IG>O>^Zfev{f$qhBp?_MMXLU`FK`hv2* zq$>7cxW}n=?|$!52N-=<|NU&idB8QFv@56=)vsX|>3tLE*{*`M-kRP?b9sq=;xN5p z+o>|T+^&+`iFoqZ#VP;Eul9nnh8omv^w@0+Y+^|aAz6*NnQZK9n2=nba$8Ma>h(bi z;Cs7R`Zsaq)cC6VTw024biY2=>ql?^|6Mwqk6vo-k_{QN2EdsCCoM<1jCci&<$D*XjOS<_Y+qmCG<%!cn1CcykZ-+VAh6T3lTV%4AnO^_k5KV! zxt79?xB47|S4?el=uDX%dplk_qEOrQ_Ig)EzyuU9ZHPwI|F~TefUOW{<-)4X-lgxp z21GBIQE*K+37o$PVjR|{{qN5A|G5yX|E~+d`MyN9BJl6%j5 zl#V}m9p;lbGNB{(t*!4}7tjKl;mhT5ATI$VhbIENyM=r)&Hlj=Tz{`i3O(;9hsGUk zqmZYc^XbxD*uwBUItul;NQIrj7yW{L@9>LcBsAEi)rg3WI>f z6+4eI?1t1uED6hIOW2Jovs~Mrl3d-ss1>zL(K^cqaMJ&-_;~)5{5Hl-DC+ z7015Dseg9J#Dtql^HZ*M`%QwvGjfl2eu>8_9p4r=W^NOHWQ&X{IftZ{(hM*QkEl|@ z^|#bk#^hq__qZBc)N=hm?)BP76)OSA2{ULdU$qhm3Biwkm7wfKF}nihKo9YMiWYBg z)goI!f=lv59nSZLXb{iVe)kmRF#|Lan`=_ClA<{F$7?$Hmx*xa){8N1RAWTy##OIa zkKC$E4T<2{M+wJqqc|>_lp|Su~Z- z3k@;bbM*EuKn5cfiE)wWiluxPk^aSn&QLF@wQg=|nOUwXlUf}bbs`jA=3me6*L#7g zwWvW8ZnyFFuD`fuVvuy6W^zvuXR4@aJ@>c`7Zfx9a#?)z(NZzf17JBdLAfcGC5C8pmzzk<{8^^ebFAi}!SYi0 z1;H+3heB-Ljp2FsYtKK=bGm%>R{TZhw>%;&Hn;!AZ_k1!d9+rGpsi|va~y~wc3XKa z&Nw%p;2;&`tviJ*Vg~~ukH3;bH&!lV9QHI!AI10rD2D->hzhz8E4<-B-Zs5jk!FPl zSQndD3fE$^GQbhK!TT~f#!_;LaI1vMeC0`@&H)fdY@Gnyhe0d;F`YiLc|Iy86ham5 z^HKT0la+Hh>UxeC0E!JDE7_G0wG0PCKx-HAMqua)v^wv^VP1_#oZ%$BVT+i}O zmsyhGAJd`{QxVy%)lyQvPEr8^f4W9}x@61A2KNd=VHZt`Hk$wBvBPfhX9HzwLjGbRS6-X96>nWUMH=n|}JmbW|o z-T?_Tj2fZJk+JhLLIZze>aC!CM;s;t%NRHh&mhoRQN0v#q1o_U(N{k@{ry7Cu#zy7 zD$#_y=X9)hL5c>8{J$YGQ85PNpOFFe-@n=a=4QhhHvbL4zjO2qxW4p3<11cLUEgMT zY*xs(0*0U=sy_N8o2FDT*uxtVzuxh8jHQ&ihUl5F>Zr~o1>Cy4t|hIS@H7h*ByLV5 zY6T&dsW=Y$pv51CM_cF?o&uDxG)iuG3O#tc5v+4Z0RVNvf|vvEm%5+kH9rim(vSFS>PtQ93SUf_8Anid<#%9RXMC@Kkp7`%h~ z>wH)p`NE4BB5r;G2F+dx;~wf);4qi+0eyQ{@}#A(Z&gD<1yc7nBWcz(_WsxgLC1n< zW@{NO4|{G#!i_2|i3w_|Uc4*`Bm&37o>fu;o&2J3_!Wbg35hP5FK z;7^y`nfvcGXYaZz<*P7IT>MmYS*y7^m|Vn>knRpz3`eVuW_fn59;CRQ#COR`YvC(m z;-z)1hz)u{orPV~r#ze5uZID#fPHX6zjN6*@;(;pjVK?z0p4UUo0}HAB|~<1INGFb;G%oVzCp2v%~q*nLx&xbB4V+P|a z?8^mJ>+lKH@N;~?f~+{ncum&2{J-1GhAu+Kjg6yU%4rLPt*ow_OKe1g0PUMuyM7L2 zp-EVZGgP{Ck|IR=IR^nDS3r`<_l&0rWK_zB_QR!#ACWA>2+)($@J~w(c+DZFE8qHK zBlxBpAxz6`ONRrYXT&Z!`y8Y=p>g?E?*?UA|ANWD&0FV}pE^fZ64&TrLWzzo)QmBn znmaC}W5=JUvEbR_Vk4;jfMao6%GsdHa&N2_@B7sXT0XR(Hjo?t2KhBiRSj~{j2o0G zVPPoPoZOk(Rx$O3%ULKV@{iqbnpGU+(eMkxK*E@0rr|pabq^7i!#TyglDq z4bx@*DTWe*X*N%a;|~hGYUy-e*Hm}BU~_e7TQ#>CG~?_N8(^;a1Sii58sd7BG{gJ0 zjdbg**dJ<%kCe(wftVYA5?AgRiOC;4T?s~%F`VKe!f7HBk@i#ACI{Z~l54dC5j@G@ePZrZJ(KKRSWH~Lzv zr19Vs+(3GdvA}TaBqRr$CtJF^mz1E*_3~|t{>^@-k+BBC&GfKmtpX==N3+9(Odher;cDF`O>ci9qnuI)MENF2UFHa{|C zmzIJ`0qDFRtfTp4%)?f8;paZX&JMFpX$h=Yj;oQ;BN>moT={btq%(6yGaHYOZkJeX z&bKs3UwsBCM#f#)_B%k&)^7Bup_n~&|7WEJNN}Yb7HlVq6f#4?6>6-=;Zl%FbP}E) zyf{mD1Vqv4aptb#pRJ{q*Tu<@WHJvLbJX>-T!5ojFgl6aco@qF_E~g1`!2&q37K$m z_eiYDdhciqzvvE>g8T1P+-{L;pCzceBEtldXPeO)tM z-ky9HyF@L6OxlIK!Jjz%u>#7f#7kaNQa>jK=^Htgp%T4Nrb9dliVM4a6jMlXI1i-7 zQpCi%b|Wh&WPjlWjr>?9eS02O)fSSR74+cMHBd5u^)I!Z3ok>8<>T0(oGLgdR-b%#6-aO<=NH}u_c4fsyAHR% zZ>H2V-_|^v-p+g6?or8g!kO43d7jS^V-zricajW+2KzPBb;OKoJ1*Ugd+U~3--kC^ zJz9J+Gwcx$LH$T9BxnTe6AZ-C)U+QDsz`LAn(vRyycu9&8S+cOb(@qf9BF<$LjGw% zrRCv*?z#LC$&}71i%L%}0piaTuNjZeca!vsQTIq@Ehv6*tBS?8amO_}xAT%RiAJ>7 z`JQW(vX~W`-1AvAb-aRr@KbDw%sZleeq9-**a$cR}ME_{os)AR_NgQ zz5RQ>DCv{w9HHjIls!JSr(iS`Ms*zXZx-bS=&# zwC?Frk!s_9+|%n4E`^RTDi;E8vI2AHZ6^B&6`LJYAlaqzeE`NFM-xn!?Mm>kx4rMT zp#k@lpTXo{h9gQ+w6)CpAF-_BW|PUM!Fs&HgvNvpOH{l7$pg4@mEQ74pK)?gj1<}J zu67GIOQlEg_m{)Z$48P&Ui6IhrZn+P$5o0?1GETc!K6bg9ZiLM_e3p)3F3|E4ooke zn7S99>8qoA9(O}B9dsDbx$=l}*J^SL(m>Sm+>z-YI;!D~LN-1s@+Xiq_AHgKwzi8% zzV#bq@cv`~`=#5LVaol?IoAkrjjXmn7j*5DpS|OgRczL$s{>zRLeE8}E8q}~bYXeW zVBVGOzKTDCd-Gz02>ppJ#;1#$=%C!+w3ku2LhB4AM#m>~*b zOw%Mx-Zl{U*1uzAglPRj$7)$Wa6*ty&x^u3$QP<&*M0jhim~{xGIt_V4xb)4@+DQb zXA)D!hP@MR{p4I0c=1#}JmLv~zaNTb2-rkoHd3-EJ)G*X_oen zplxL@! zC8v?NBImgjDn^kV-+YCyUZBbye^-%7DYgXY@!$=1$IXxgtk&E&yhbu|a}%bklxn~e z$KmhfD$OZaz8^UJH1JiVws;HihR$K6{egm`|EvSg62Wcs(+jyaV~nGx1I0mP{`JeL zU=xFF{bD?8Dc3G%kh|5g=Tm7Dv5VsiTuFae^WP=tUkemA7J>wnLKF}-*8jLAOsY%U zu8aKxXF>5P__preO#<;YNa7ZnrxPKs3D1LyR*|52Ij1yKqJCaytwM^fH4v|g{W!@z zbZ{|!T6g!7HmlX)h+sG4ub9%+4xS<+lspNJSTq&H4RP~n2^9(f%WhXcjNqp^qx;tW z1dG3wn7bF+BPTqGW5P7E7}f<`*4J4Ko;OI_kERvCr+uTR=rYV1c(No*S+Vy?7M-R4 zT-PBdgRyDF3?d2BF?v^-<}7b_=x*5TseNlhr|E9=`mI*oY$1S>bB0@^$@1~66!qOy zn5ao}j)ibUy!@N(*{o!MbOzZ%o2DW@sI??*Bx`z!djB_ww#Hn~8dH_A=y8k718;HAAOF@Ns(mH9rCBM#e3g&7L+isj@TC;-h7mY9&I}=w^A&&aDiA z{&WK6-2MBN2qlAcKvMr117uh5?#B_MpuZ}xajz*8k5gVYr0FD}RTYsRg`PuGp&!w9 zYUi=NVSjJ|y#6Gax(oKwP{K#!ttYIaSHGhVO3EGBdw2K#4W7%_nc%AAlM z@;H2-a-^35=mZOKD!iy({weTJR|F6suE?%Uiri5WC}ZL`Drj}~4yp0Id+5{e+WtRZ zC?3qt6?$`0uD=2R!LzA*oTa5vg>VcKd4(xOapjl!QxPWxw54;{%!cl9OA-unqLxZ*HI*LkmY`85ZUb9*ZOOrxiqv&l zrIKxf8sllcN;rh%H^vZfJZi#~w=kdcYGHa`qaLXNku;Ly_WSm^94rV_6_#lO6bO}73iX`AzZIDu7cL)qdccK4`?w8s-&t09if7LrIEXnO~7gr%SFl9f27N5u#<|19Aqokk;i~tjkDbJNV zhM#brul#lz%$y_D+*o`tG_FlLU`e+f8i6Vfr5@T&T$o4ZF%;P`3?H-^qojjwFBU0? zW`UJ9mLumv-9`nE<=^n-VR!MwK;z;zwEOl%`EL8{u!JO5bXJ&VZtJEGg?acyyo!B? z(2qg^fgX$!5;utwV~s-Ln z7Eazhxqx4eJ>(0i!IU@BeZHX8RwXwoq4Fy=rI2|SeXlh(V`uY{`mn9{UC4D{5^!w1G6;z%HB0zVg%-4 z6XG+&b_QCmI@;oyp8>1^!(ljpHvpcIz%wxG4vL$fT?;Cm$TL3g0z%)RhGLtq%5v_6K*d^Ek_`h>-A(_q=^Rt_7VfGr=o*h#v@wi~DKUQnEUt{Z}X`+jMcb2KBa@-by!{~!Z)r7Vl zOE)K3Yy@9}HXrE#jD1eK%-3LR(J@Y0jmr!^@vxpi&TpZhBX$ z_fip!=5@x#c#cVVOtbipg0@(j(?-eQoK&3d4{gt@?t3tz&6(`$hj-1IBd4CSv>+-{ zLTVB{Xd@Q)r`A7qk|T7y8FLX4AY2Jjehc-AVa9wXJz60GVq>P58Tu&D68Q}Ry|Ja} z5LNQZmZ+v9t5VwN)`_s~Z(g49pyTW*INnyQX%$5BfJF&Mz&+UCFU@mK*GL-DJK3OL5<>Gs`#I-M z%B>x$O^TcV2O$Q%lsCYZ7oIz^olx_wkBv|mF-K`Sd#%NNr!HB?a@E)0@vZj1?_)8G zo%v+6)MUR?oW48W9;YlGhA63Yz@vgXa&I^K@Z!NlafZEbM<@Lq%yR<|rPhRa#v?hX1k*a&y@3VZpptr{l+imr^S}iWDS|msQY*NF`m^t zVKU?ZNP5DPea64X^9ZIzE-Z~A&p1tgNQ??xT0&`;<7C4V_5hKWSxKk-ZgiD+w{ED; z`4Aihk2wBbSwA`_3h|E)Ra<;Yw>C){hmM^E28jWq=#6|u0Gr4{`10sfMa%Uba~jd! ziI&bN9qNpGlj7^N3hR+{FkFqEAC~~LR*7`{{V^<5~w<$@go8zO??qZ&x zU>vnwS_U~%t+2RsFMmFlbXb@QW;%Lv(Rm|WR{k0R`blb%8U)HO-abGgCBv}$fT=lc z1A;s=IS_dDeGh(>=JR&Ixq=n!&KCtDe8evy$EuJZUylm>UzTZ{|M|$*sj8K*#)j&1 ztY&@(#wt@yN5F9aH<@yBp9+ysecwz#sTHp+A=3i( z*JrAZi}KOa(&0Q%ypRoWYs&X#B(f`k#QWO}IT|Ev!R6tVT2T7s1+BMOJ%3orDFQ@F zFtDFf^toUg%lp&pCkWy?p}fDSfC3m6R59)|N`{qlY2~Xl{V#8C-UxGXTUsRK>L4Z|K7oq;!S>;bxlNzq0i0wuI74?1q5HzOYD~%Tw zPM;e=5{Tj`@#*HbB>Gsoj>TQYk2hq0x@4666!j6?f)#R?msPr=;UX=4~leaKMz6nk5KF`{)# z0W|KIOJ0P8rSi_~?&xz=g|G8+05!?jt>xq@LBGE?5$A@0n;%H0OGl!&l#-KmLsTTj z9|3>~o2#pBI9)I*s!wSM)ugSY;uIdiwOS|u@?N2EDt9VX$2prPs7^rS@_Xgf*dEbU z%B@XJyM!%pXXWnNB?OWR(wZOLOjj<1Lo%1*CpT4T@i zO+~r;2A8VRj^n>kQ^BEHD2C@RO#DjTlSv!8E^ zl;;rqj+~C^UUo+-98@e0oeuIX>533AU2$XU;A}Ijdp-SIR|`30jOB_xrhit-nYb+ivg257u<{;U^eQ1FB5S+by zj`wBsv1-0uD33^nBE!bH-_v;iiqJv3d=^dY!Qd%8(sWXQ?S;@fcB(v0JK>2Z3OQD7 zs)q}>VSjPB9=c#7k3_zZuU|q_zIz8V@3C*HJcZx&QSWxIgWx07w{(Wj3MzaSOFfTQ z6*?qu+AMV{EDx=bwabcsZ4S4$3m&Giolg=qXYlChy6yuu1pBWLJmSeqM!SI*;1QYs zJ!vHTYX8sYG8WDRK{3h%zDg*-yPA0-PGPjfJ)xrEAHKrqtUvoMJYnfLZ>fF~5<}4Um}XNQb!O88no>zpLSTVg1^eLPTqG5XBVF=I`OoeA_Xo@YcT_)ms=iO z+PR)zd*%&PVgMNj!LY(+e|yGH%STu%XfCZI!4vxA++X9tVJMui6VS(iWyz(u$H*FV z+6DfNJ58B>{W@OdhUBRFcK&R=VM+7~MbtMzoc#Pwp%#yoc|0)4E277G6XRXot5Aa0 z!o9_X2w>6rV$OGFD55o)P6}vwayi%~iQc7oic}nu{l*wAKKbx-OU*lrM478wN2BN4 z&UhP-TpVehfHByVFP=;QaT7NYM(Mqo`aSlGe9gwn9hlRHXYmXI{vB8w*mS<${hd4y z=!T`Id8&*#oz}ILT?OJ|I?TRvd#WSp=3e51jzOWM2{8$0v~n1h{9h!b+y*Jfa#uC> z^NLg1&}3Kg>M{(7Y=89U>a|AaC8PgNjgc}^+_k#g*fq%SP(>v`(`IGsioGrmHy){c ze^g+8w|U{Ps382#74&2cqkf}tAr1b-U0&W`eU#KE(pX$DGVjfIu_XwDupw>R$Xl5sK zk)uq8v0Itup&Hi&q*yLR5O>CrI!O<{VTL8`7hg?y(!dDyl_Xr&(tx`~qGd>V*i563 zr!Vh?UYR8TPyJYs&NPg2OH5?u4`VAXD2L=D3zv}ZXA4xQy@T)*>F6XR%ajEN=V?}L zla8(Mx&rSR*$ZW^4!la_VP6j9rMHE4{BNCD!lp@LemSjP-X%j0(@l9lxk0VaIy@<{ zBYLON6AnQgSqSxn8 z2*-zSf9oZWq}aS!#+%u z_gnCp@&hS_^s#le;Lp$~E!~bH) z_`I%w0!mt2{ema5jrYHZ6go#BGmd5NHMT1$6v*E{+}!la!FcJUNH-w*Eqj|A<;FbK zq9w14>V5%S=hS043ICeY5=%G6S(zmQ!u3eJT)W;;cUyr_t;3AHWuKIP1P5n*LKCrb zL9EoX@UxWglso`dIx-5^;$&FEa3-}Jnlc<2* zzsxEwD`Tdlq=;T=p=h^Hf8k1oQ-)ct@Qh0vzMM9tBKEndo@A$=cV5ct=qpdZKwU(1 z)Pn0K(!lBv>xVmH%@BPp@)MN8x-CAM*81YGLpoK%QtG?uxx~m*0EfR-p3Yv!{8cevTiH?v73qaKy{J}-x7~SvAJFrh z@J8{vM7?UJ$@KV;npFt3X_eYl!X|7%7qZEIaSsHS!tZoXTbM(`X6QC*`8cD%EV%0e z)N!iSdk#-sV&i$HrPpv>p|!riv*3?+%}6fR=@EDnJ3FV}D?I;|!EVRQ-->zYKPU;|aFOLei}IaU(H_t{4xqluesQjUYeNxm z_{AfI&N*&WZKaCOXKxE@X3N7t>2STZW!0e$l{|<%)A(%jIIOVo`kOX1UI`Y=%z~x^ zZVP6<&tjRHv!pv|ORZnpV&N$(-dkhS<#NXLQD*mCEiE++RwE9UzK7Kwq4jcE;izE5 z8Oi=iT00PMe$m{40x+rGAAo#)YIy$;O#;P5NWuxV9O}Ca%C!XIqlyny<|_Fj@PzZXTF8BKMk3o_*C#9cU7&<)%hI;_!`&8F2v`eF zIbBSqaQ0bbOpJsQjUg%AzerNzI9pEX5Q5PGM0`Y*e5~iCjOULZD)VbR@W?2{Z^H1wS zqcQsv5F>A?NWi<)<5=9%xkz`e=uCcd8SaDll<;ALfB=22GYE@+&AXK{pcw(UwIq?S z%Br~-gY*rYHZ%FvQgwkxC%KThZwM|IIGU+UGjg%oBMDt&HBejQD?Vg& zq+MYmb}cARr*>u9z6dob*}Y$Hx`r))FgvW>m~q8jCWpnGos-mk_{0vWkcui_6^|Le zRUI+&4Il&gh2fd~gFTmL8b5;82BEV_0my->F?nlNb7=>J1U8g^fv^+pOF$M*y}ip4 z>dUM|Rvj5FVNi{f_r$78(;S&$##qCPW+FkXX^NO}@wGn0Fx4dAZ0yzj#waDH}-i&bRqK0U#~mQ>z-fnAD$nHqKnBK z2avn&zs_#X9te_Py%wEs0wJ-;|N8X@_(c-$2%g({-(-8Vu8w{fToq5<5#RG#fJPFB zs;X19AM}iww+USIq!;(Q1F6+8&_BV!6^t|RiPsY3F&s4>=TlT5xcTP0f z4lPOzL={R;S8Hm>(PV);EOAgPzxf*EK@&zE-RNkNO+!0VM~sjJ_PzUAXpRGAf*It? zu)vm4$Rb6hzMYo&D}69aX;y0s>s+?qiS{7~E+OV! z3IPTY`hgoShyafK|KY@y06l~Y#>mLX@^_m?4RFlhK=pa9*8ed6(@5kuSd`^G!ZkYO zG-uUh|2FsJr@y*{Kv0cjzp2+PB!OWySlhn23k=L9e$1V6jgwpNlzTtC^SrvVM;4li zG2n;JQ6CgQ0QN;<*9Qc0;W=e><%Q`TH1lKLI=$BUHEvS!$S1=)*1v|B!w)JjZlR1s z9-wZEDd0WzXmv9UG)n3;a|MMMpbk^~x--sxGI2PJ82y1NJ|$*7nFSp$Mc$=tHr2mV zt-AfCvwLHY4(U&jNo7-#tjd%gja~x~o9zu%tv9zHi4ww-n3#c3W8Ek~<$)m)5+AJ>lDFsJD?EVLZo_5iUx;4cL z!_wI(5E!Q4CO^kAfG%dUwFmcoju{`5e2sw!B^`5%!8T>#@#bVz)J-J(Xz|CW`lrJ_ zgd5mY(>CfFCX{lfXSxw4##{b8bpC(Qv@GI%HY{G@LrKVIvnxW{EkmB<=9-pNm13=S3F`2ecSCIi{&}V3<*W;wpwrt!;Ph8_J{j3ZA(BCo8McPuz6vA9N8E%iA!V4>w#l z$z^BmmHk*|U-Z68Vt|@yn~PGeZ|Fh~k5O|`X;`qN@%PIf=w&m=M{{vwAFaOX<4Ov_4zX030+RchC#grYNL=RLfVj=Ae zkYK#97BS?q0!%^l&k>l|kM}MO(kiRbskQh7oIujnU;Tu~lXk)5tVznPWC}bak0%!S z;dHyJGu4SLoI{@Rb3c}omBIH}Eo?EKjTOmn%}-P%qt$*AZ4}s++CNDDhG0}we0~A6 zljoyEC5Hyx1~b}Ekg&!nrz<0~Z1|prB~q%;hQXz))QVKaQpe5<*;<6bHt74N!GR?G zaO~Z#1xb$f3l}?<4En;sQeIS-mx<3k8i9HIUq#Pr3u?;M8Xmph35o-P4ae&;?G=+J5 zu|z@G#D&# zy(K|Ng2AfIM}Sg_WWd5A&K0C(Br@;8LIJHE)k%<|Sc8ueRA6C2y+pFo4@U)zILeC< z2=b!&vs!{ef^WuQjLgCq0j*PKC6L%c4a@Dv~Ll~j_5L$lP^s$V|Emzmv_&EsZAtlnbQ&r;As zU_*vUnYQW>yMyv_`eBuZfH3z!iSbK)_NKX5pT)>g6_*3Nkv|%a<86;`G!}tQ*Hbt^DcOMF0Ef z!(m8witzVyLOp(lz}B{o>@#3^!6Ie~@%w^BjM zDLLfTZcPCF{6orXxw}6A*vI4ciKd%ZgYV19iwgkwvidT0d2_UyO%Lm`vP~^{?iIRX zh3#PIbSzVW4U0_{TfzgFDt&ikz$JJTJ^ayKzmQu@; zZF|B!4R=GK8f0u0UsFuMdB+Nu$8ld|nwp0y&#l*%UQfxHy1xS)Y+7Yiw_6Y?)(r`U zn$1FWW`}qQQ>Ns*IulUt)j&Q}7i+LIr7JIPIywldC3l&-kt3WF? zo-S&#EtLqNCYl6Xa+Zj$pyLEASpLbFN|0ssuk?UrpP`*#J3wjzP$;Mx>lO5bOH2n1 z`C+y%on6KRoy+-mx)qHEt6^QAB)zR-H+uV2)umI&s{UFlPr*Wsm*}>K1a zcV%HwusI4Y@*QL<3=|}qm*|S*rQA2eYA8#KOxYgR^qD)lP?d<%Q5i9cF4s6JR)v3$IW6t&qd7$uTvKMrvJJATLNLO4AK%y>I{j#v}NgTL19M1w1FApf|HaWE_gi&&7PVj)z_0czT68{rYHo619~9wOE|y*(%b zJg`!%X@_Eg*+NA+w8D8ytade{TNgCg?w;QX_sf?Z9$J93f%CatDtNyxba3j=@1GN z;kU0Z>AJd`-nNG4U2)$RK~1sMD-XLah3u$PN!FV-tgtx{QsLjOP%5si3VasDZh7^a zUp4@0a8dN=?~&8~eKLD*8o>>!oJ@}RSC8ti+yiEVr!pw`TDbyVZQ-!u5B9OKx_X>= z^rqtD8man>-B{WC@6+l&dVRV#o-OmI&p=J#6VBt4L#j1W<6Gu9>YCHC;$;fl3$by( z?Zh!x*SvkxAojo2kyF@-s^r%vGxm*k`1pCK{3dw$wuSukl{Vrs+`%F$*tJ2nPFPsJ z8%WbuaIGlHJ+wf-A@4v7yZ_w+Q*xR?{$tGy%EIuE_VaI?nd-lYwM1Cf zA`G6Fi3Uji45vNJWkot!CfvY4iV68bso3Z&VSpz(qGBO!>r@aBdW5%E`-;v1DuRPg zPFA&R)J!U08K}-4ZJrjK&`8%^rtKIu=ZX*i3ivXO5P)(Rkkix&2)E zJIU)GYIJE7B3C7L(*mm!2Zf(U&qw=7am*^%Vm_Gzxp?mu7@C!&>nSwcRVz1IgZSS= zVjlhI98R!y4aocuW_rqK@N{h4s$F8}?iy;Ta<_r0-~eB<*cZaT3elHfcG%38ji}Z5#x^=vx)SVJ8&{N6;@>|Y*)%%WQ?T|Sg(=(y1q)t!9fc`G2h$F>7CGrjQ>6n2 zc(uSrI$IdY&%xn0gH_^9#$?LH)?v@1+RW;He5sp=>iOPP1rbEiHqCN(kW3qc)#wG?raW$8XVA}ttk%xdxyUJi;dEHLjmw+_|(^^)?K{FTk^Kl%it;HZKgek z2&GZC(`;3oO{h^D(rMgVHB6ls*;v7t`O)$tC2c+w6%Ox4VM8Eu9a?v!(`x4&lATpT zn*u_ntwc+@doMkcM6lYkGwYMRLBY9PVmXfUw{Dw|(;C#pN;gR;b^e5A2Cf7ji#1fD z;Q@NFXC_Wjb#nDI-`tC5fyZ>FJ$h(_(3n>`&<9=8B57jce^+CVQDFd)XN@Mc&%>j|{lQ>|aTpsHN^dhZ*Bj&WtWxN+@4eX3H-Pn6>{=H#Lx>Pe zRoX^Xds$NO?sAa^b0z1k-3721nEOrDuCx%M65?;CeKsa$cW=?6#D&As=YOldw-If^H5RYC$9MZ`SdF9lZ%AjQuo#j@ojJ=lElW z#?ia!7r&`a1o@Yh2!HrVdbu@Ms`=t2cHW&w;TVTw`N>&0rfA|-!kc9mCNw0soTDnX zLZgzYZ6c^+1X7ykJut>w{*!mVBOtDE7(P{}((HSJVM7oBZ-@&EC1<8*)TMq}FD{{< zF!a$PonxEzdN#v0v88qpp(THkvF9v1+5LpH~MFRD>si7O2je@H54Nv^wZjnIutZU)sb)SbP8v zsKkrhY2I|`Z#bS5lO6k=4wxtR*a>jH5x4i=zAH-s#brL$oQq3lpFsG_#LKTCV#BbF zYQ2`3K1h~r-JHoiIF{z>);HdF0O3oIaAKYt>~A14?d73=SLlCj zg_$|ymrz0e%RRR9uiz+y0jcv{?ZkWtWed z5Cr>z#pUe5kgsCX``Tg~#-B-K=J2H7izN%3Fx(Ec1vs6bNDAud1L)RQ|ESeGJAd7t z?7^Kg&#EK4#R`WS)6zakHR1i09Ex0PmoG0hB(^=QKmpKcEMnDo8Y!w}iQB$n@BTRz zm{|%rOJ!><1S>DB>`j0P+N?FRWA-#mxvOsuda)f;BOf zv}t(b!2iTikPt$;G)02-mLWzYjhMaU6{P%tcCJAWI#H{4^7ASg^+vpMbYgzHyQndT z&;e{`CGPYThk^q?_1Rg@RC~qnB7}SQ4b4KCzF% zQH0DgCSw2Y>|G-bK#0(u2I@dk$v;qBUhlH4=wgt2reL;`iPl*=%?s2m%|DyO*iR8@ zE-3ceXb_%H76SL#*59aAcVFl1S+vP@OD|ru*AHZ7Cw};!D(f`(jA0D8d z&h;~Q4MYY7yE@@xaQ26Q;$5^bKOPVMR)E}#_G=ty!Nr~ss5Kx<#wZ`82)bLzC`V8$y z`80AxfR&e6q+6Tr^%~rXg2wMwlUTG>z^3DlOh^$Xl&ZEhd9YpCy<4(PX8dj|%n(kz zNBWolPqrfF_57Pkx~bDVsjd7`rlB3?sT*c8pC~tQJ@sR+rGP>@480^y!>&q;-*Enj zdZ=N~M*uTh6|lEO4&?V(@}0q6nYL0t*s5yb1e8OfW(TCUl@0 zST>;lud;ZUMg$sRa{XhnJ^!aAW%`<+VMr*f9gKb<6x~qV3_>+FF$Jt7Agtxr>Vx3t z!6I48Mm|Xj+KTf#(Nt?g0VY~y4eX>>ME#&T|5NcT0wC=LClUn3jH}0Yh$0`YaGg%? zM!{_hrK&phv~B)fcm+zH(bR>__4`&R`^4meuJ^rC4Bh7ixZmxq81t*Ov&~`B(8y)k z>a5PQcd0E=c5uCeuEi)CdB}J{cR?t;qs_N)BQ)oV&Oc{WQ8^=C@1CprAfevq>Gr8} z3nh{O3~&-R8~DeD?w4~VEgQ8i;>nqFD+?xOO^D-i0>+5Zc*?PmlZb2LXsgD(P)Qk;gU%!HUo%x220l8`T9*0GHoxIyz;>vrT8U;u5arn*^hbh8 z&$oQz5*vGez#h9>-XCYgQucE0Ef=HJ>xd@v1%R$nc_ol(OT)|}l9DTrPy>BX!S3t9 z51}T7>)VlNj*V|u<3{j{M(74oH>b$uHv3R?ki;m=Mpx;069i>j3AMu^6Ag)@^0-aL zzS-HFEoa%rxQ-YHX-clXvfs*HF}yQZ@fXw1#X&0OzicoRD7%^NKUkl5_CIdDKbHQ#(HwTI*aO{YH9?3 z&*6NGw#`}_^Pe(eto32iYDgRLIasZyd4MI6ve`lY*$}rSqT8kT3YWiXlE1mYG_3Fq ztUvo}=kIj?yI(>MCGX-a-^?&;y503lhzXSJQuM}@PB7kTnMT9~&hIXb7Wk2I`>8^> zW?IDS9F5Yg6OVt9aLD1Gp9W|7Wwqw2mUPa#i5k>x?|e9-i9^ur5h=@NIZ;QUMgS4w zGt(+9?o7!7#n@x!0CJl zR{t(u3Dx^(u>X~x$jQq7-mBIPaQoFO5pEs_8a zJZtObgEf>)VEK&2{#9Ij2)gp=g1+6HJ2jLy^}3g`xOYGko)t)f9Fw`YW{`-&ABuyl zfbzDXaX4k>O8lsyQQTI-hVHCzI=+YB`cdZr>3OPeD}ad%VC1l2w>M3up$O*UgiYwx zL`3)0PPKIzFV$o^vq9k2I5lnX{QYa{!!8sHr#A40qbYi+ZDmyQ1z8z6j^qe;;TcKc z=W2}fbjVA$F00~aqj4VfebKP+*%&FJ&U?|^->4OqLdyU)+OdH6o3RVTAFXMDcm|IQ zO~XVe;b6e*0ItQ5BYuCcdVUb5WR3(C)#GWpJL>vnvFgf66BWx3h^Y)s=hg)_ZV9Mp zeI3^3(~e}eJmD}-w3mdYRoqSRl8JFr*71 z4Kghm$&j4Ve&LW=hjhk5*Hv%09XdPRlhqMe_5DVdq0Lu*p*7o zu2jfm4DI15v4@Aze^lkBK%PA4SnOt!7|hVNf!9^3kRgjJI5Ut2SGamwh`Pv(5i zb&M$Ll>Y(E-VX?~9_tC62IpZ2#a=6Ea>l&CV!zfz%cvZBQdT_LY}Ik4elC@AMbV6e z%ma=y2gER?Sr(r5*M!-A$+^BO^3jAA7~uufQ=E9hbfK`JiqRJ?e2&($F%L(5>g#c6 z;#>Q&iD2jbG&gF1)?E65IO7&6^hgHt>}Iw0%JuZ_oj3VHMde;Km$7YCtx3sJ)KdwC zu+3#*spo?Sc}i;dQXkXdRNZ@uJ=cDc67fEVK&-Pj z#m|^Jv>NmCJqOL@BsyekME>Dn<^wk+pQJlZrZl)!bBw2u(Ty2eP{kDK(3g4w^EX1Z z9B`?{SsBev5gG3p>k#{ryc=McH>Z`Md4EPmea_1@rIh9Jqx$Czr~OU?IGbWn<5hKhgDoPDGPtrLgkHqc8c(dpN1)IHE@cP@zX z<7ErZR^9@E4#5@srM$xR2Qu8;>Zp(I9;r?3U5k#j2cI7HW zb8-9Q=kFpMbY5UiJr*Pu8o*u-QgBvHerLwSs5~Q(ag1&Qk;-R={riCbYwZ7zu=&4X zW$gdBuvW+ zqfwMOW0`>?^}tpYI^+L7!)Y#>NI|y$(sw`Tdb6K2pRf51r(VmFiKuBB zqp)gVR|<7JPTo9w+B_5_8A2nH5&)*UM=#7x+5%K{&S#}74XLnK-g%qTnx)e}-O|T5a^cb{ zSudO4N7nyIvz?Fk*QY37FgMWd3+Aj`it$8%Is-4)YLk3)aqWSsR?4=48sIGH0Udca zwgXw%3WbgfuuoeuNsp_IoAg$7X`O6{!w#%N75vzWFbG}2LyGtt8>1)-&9M5!F%Ga; zW&*7OA&hS}UPnJUj*fTnYH6M@E!1ewx28{$IsoN>tzXa&1g>1m35*hXE!kTI?mdR2 zN`o)i-@xJq!M^UrvKF)`nYyC8guI~_nqjkGE`j1O*$zEqH*F1t^5+RVzQaQ(uIL6V z*~?M!YSuk=6y``sUSo`#iIWP2`vXi-li7tsd){b2S%CVN5GmydSuMW$^`#r>G*tLX z@W^S4b2EHUE2zxn%47ga_WD-vmG5&GRB}spc8+iCm{4bn(7nQ<%~=PP>J@~U=7B}*A2IE0{Hw_d3Z9#njZk!%q z!nG4gg7IebhRem2NDiJwssMeXsysmxVh)+AWwI&-G31YN;T=u%dD zy9eNH9$T!Z={%o{4<=yHtJFMV&*G_u*i)8tPIXsoM++}Gc6b^b3^hzYX$6L}B^S=g z9k?nqr(-roV!Ew2J+jUF{lxFDw3KObAa(~@@S?E>ZGbN87pS6%*jW$?s>>GrgePO? zfAL8m>{pj5e)=vNr{SlVQ7(`qo+uj(Oe+_Yk8sk>5{JZo0D!2;awrny@BShSDU*c2 ze1Jt2S=-G2!`C}TM*@b~y0NW}ZQHhO+ji1PDz@FRZQJbFHaoU)Gc)JhGk48d_g_{0 zuJ^<$S82=MdqLfxMTad{Bo$wBb3;~lZ_( z-y8vVaBK}~*r$$E@YdV?ci0??pFZI#4CupRM-8%@Kb@OVcH#M2Tz1#GEnGR*D!_bE zXp)5e{uFlYROvAr7zDURe)KU5R;WN> z<57*eQnyk?MBs%_fAD_nsS@3yA{t#RlrmHYPTh4|`GJNr#K;ErgKjo?1FTYubnrTV zZ^V?!78Oz{vJ=y<_%ukAtw6Z%mOSbwNU}Rrt?!{>?*&s zYTt6x-5>P<_i_WT22cnxJb7S(@&wkgW*xn-qcy~uR<3Oa_|Sl*{a{cPMEatYbvzLo zh?Q*A?CU8j<4TSohQ=DT0hS)GiC|x@M*{#Q>dL<#sJNqxns+H^0@ltk#5RH@Epqyu zN!8c)RiF`fy3B#;be7k%=g9!S6CJV*jJfT|?C8!ajqp1cwKEBIrBq`1WD`j>#!vls zt5C2ucArrw?AU}ksK7{Ptuhu84Q7^kd9x9-fZOC$HVyi@0{VM#f<#c7?{zC-AU_&HjBo(kifB$i~ z&1k99EqVH8i-setS)>u{;#;IgF{)(4_LpIc5wGA)WC8$1VJ=Bk8q_X4w-8bo^jPHF z6def5=N-zah7|}t&I(8{<{&5B12?2bAp_oajh!%5!6g!7AnOpJI2bXmcA!g5jZD3< za-G$5?Mt8(J9@j~IsQgrBj$4+lq@Qoj|oZX2$x2V0x_%p&&niDFFjqPw{i@HC~~dN@!oHT~S5d zcC?H-I*M#P_9_Gg8b~*Mo-y^BM-RF1k0(;GWg2j2t(40=yzS{19F1Ek4{`sooiVeL z%l{AY#t=v<_r0E;jx~n?R^K|oAaW1=O6S5IJ3mcNufR%p{SaTLU*V$l$;ceZ7QaNm zv&4PYo74xgbTH5fmx~-n?TOr3iP~P;W?F8A%vG05hlc8JyIyT{n7QhBYYqXaXscCq z);l1({?;+z?75<0S^b{plM7~)#m{2MVq!Btoz`RA#$B|2ObmA5Zd0^~>%Ajpp)Bfo z{10e^f=K0}`(3XW)m)j(m#oV3yEDb!=%w0^SZ%}lLLkTOg9E|pADr0BgB|!IPA0CH zudpoiq3?|I&F}_}AhI*>xthMShJ6lnqXT$G5zh;*S2PVSApf9{k}=8_2FXTH++Cs( zE-h5!z_Qe|(LSWJ=9^GtSe4AL$5^+iz&n(OW?Qe*n>Oz@l=E(`%o25k9D<{o{m$Vj z-4!ES!H*fK`zN>4aKUyOg=O1HV>2P$j7NwUQ;2nq-$9Oab#3^!0Wy~ZtuQu*E*BuH z-YoLHZoJ$qFAx9x2M#jRy1OfbW*XvahGKD-)60nbV$SogncR+(b$rHE-_COE?Cbv= zF;-@d|2AU(e_UyH&i`Y}VdDImK@@cgz?7z(11<;L&sI0fFdJ!r0*%Sl6yN|J$Qsrn zjv(GZ2?OSC#3T52{oV%uQ&wK2-hf3I_86bVK`h3noS4$yR6r{Rk4Tr0fu5-Pn^bElPez0E;V56&w z19pi7B|KXqLzKwM2o}Z@62e6XlMfjTm%8g@I%_4kxQ>)FP>_KUhJ^J~tovh*42oso z>IW5MgX0bS+lQl&1_7Bv505~shh4`s&kVyM4U4kiO#@1z#1f5z1V_4UV{daQF2uWl^NlF}0ECn|#VaAQ;J!vawLi;t(QD z?IOuhY+|RxSJkjme7iz>G4VvpqIlZBx0^0^j!3a!hqVE$8AUcwgs9@<0I}%OWK|fj zsbmZ(edB*m=TO{Yq;n{Naij(k^B^)+e}bcxKxQiYFw5G(c)8ol*v+P8q zlqA%vFF_fhGJ;CT&@Gp}wLt+8eo!IGgi=u=H$#F(^6&=C7}xv8jlTLd$sol~4Yq*y z&p1*aF=d%FeP}a}`>(A|z)GgY%-1hC@1=kyg#ab>W)d%YfYh3>e%VFrm z%O(7C2&a049g=+oK;3WS&sBk#3tE_|o)PR^JCI~JR~EAjWRg_Xt}z*)^tT;YA%IF7 z{__pOYv_`}ZNh=9;}&|ZI$O%M(5ryJm>^KS#(Ylmo_5W5fzM@(4_tImo9s^Png^G+RqlQ0~_p(bG7wHVDoBTyfIin&BoP4TD}9Mt_-EK{{9~FWe1oy4hlU zJxDrlYxOuIAhGB3ejt4fRK2+N9on}$SIU6k{(*0ZUuuWUkzh?>6nnQzhYrspwQre+ z{w9e8=dnU2q#jH?EAhUUeusdzO`n!+M~wD>+L#IQIH1~HR$M5S&Fa>q+0DjP`4{rZ zlGs?c>`9p!?K%}5GovqZmP8?wCju?rpYtY&wmk$J z7flRZto6e_Lz^jpJ%8Xg_+F1j*8f@f(u5#@{}aRo%=W*c9}_>-a%ex-eNJa{YY$Se zT^Z97{USfoDNYvqf~F`^Sj=G4pRzyyWZUO+7a<@Np#}L(DGe~-%~7srpf*lT2u@G7 zH(!2lzZ`R+*gIC)pjTo-%tA`}AgxFxl#u=|D1Q7@XD^~2LU+-`K_2zLZoc#xg){dY zhS5ADOymH|)PR#^YT1WWTqbz7!u61{`a|D9>AwV6q$5~CX~39Y#^4rBK~uoC#Spo56m$9ghgND18{tM` zdIY=gWgte6#mH z<^#~^YF`F=^dw5bs!LpME@pljLMt?FL0w=lkNU-MRT1+Tr@f+;RTwQA_nMK&Dxs9o z=by(b)e-U)jA~1nm7awx%qS5GwS?;)37I1&qO({mWN%R{l!hlnLPmiMXx|oCNxtf`pUNQoZ>Y_+2A?L) zo;|5HI*(;cVk(1+v@I95RZr%61`B}f+`FT=7^weLW4QN_(2%I&i2v9>4}r8xg2sAK z50u1O4n0IBsZt2sU3nW_#3}Ddnc);WTBd`Z>cE5|Q%Bt%CfACB!{50;=woS+QPh?J zIgUag1+}p#$!OzUtt3;tN3ho(%wc3}RiEuKseX55)H-c2&_3${PFbL2hwnqXERyT|Wk|M#D-OXouMvYsvSSYLpVEnanJVS726!N73!P_GZrViY78B1K0%7Z2a5K@~73 z(x4vQxCk2gzweEqB&@DnDO(3$`AXQfyRr_|E~F~p3xVyC+}Xrt#7sM4``WU%$H+mR z8^$44ajNjUQr0W54C_R3fnq0se}w*d;tW#6yq*b_#`zS`+f!@GoFRb?TQXk!BmA;k zW!nE)r2ga6e-y5;m5C!x5LO-o$9g zr$jm*X0+`_Ct^SKcW!qXSD~scgNdr96>8LO>FJs({3;*FwOcgQ2N8j-dD0Nq?E(T zj+hpwez)&)texCg7ShlN0b}tjtCProR#cwI@T!gC|H%vk>9Hrh$y8G3$|yKofaX_qb&sX~ zT(67sxMxyaTH=E`13>`I!4tUNS2eR(=g6g`x+@FTt6LdU82Dm)t}g=kG_H701F=#* zhP~^SOHNwMTG|~{>y?(w|J8zkSS`wB(2TuVce`c?nV=h`-llg`uNsK4`&N z8JM0^nJcz##R4EWGFySLwbaWg9Oxu@o|w}5QR$V=hO+FST7Fnwwc;}(7lru&ZpUMV@*33? z-r|VAvJjR>f%?GdPP>HMUaAK!$ydtzJbiZFp4YA`Q-F%Yt6rT8zgrF5mal^lLP18V zjRD>DF@U3a7FoAEl*Rhp5AAklLjp96d7lSoN5+gm;|PEKn`{DMI@6dG)cxa>@vo}h z3{+JxjvOO^=eq@&>!AC{Wt~@R<_~?#r{-YDP>P$1d<|WgJJM2Xz9M}cTo~RH3sc{t zB!X&RJ@X0KP(pI|RDv!g+?wM|h8;gbA4GEOno|3x#8Id0$_a-N7`_NoJXruO(?UqZ zE3r%mX-Tl2Oa-<;#ol$qYez@BwtKFI#z@WgWGE;_UvFWb8ub5Vyjg$XCPipTXg$<` zON}20ALoBU_)hat>dYmT7EK(s+#3Z02v?V*_?q}AQS4ka5Yq~h9(Jy8h&Gz=$mruY zhy__u!dP~EShDh+>R=piMlV{2FV489flqtVIlj#nMMJRr`TKwUbC=WXmKmyK)BNIp$E(l`;#R%@h&?iYG>w9r%Db{ zR@ie(d=^}UF0JXx9u;P3%~cL~4_Gy>8znIqe$94zHLI@d7y&v;>iwvF4uDg`zHH)r za$XiP>^mp{H5I$`L-wx=eoF>7QpDpTK{S@mPd(Ps2r&UiaE2x*x7p%T(bk42>#56u zsVR#0BmPJ&P4$#h>4ViO{k7)Q^K9XWem{)tPd^(}I-TQs6GD-vE7BwJ#iGTxTpM4C2|)wBZbyv^-}tsFoS{-J@)0uF5xe zl3_!TrEAvK89Ry|hb?(nw*|zFxztm%wA27|!6#2ouMC^S16-vu|1Y*=8b5ZP(zQF9 zcS;>@IRmD_mNp^cq$`!qb8VALGo6aus(3wL94o4cWu;rf#r0D8C&2nz5Q!$mG*r2- z=5i6`H8%f;w<~8iA>k5}kkh_)!l`vWsxP2vR0O}2axK>)%{r|STl5zF08`p*;Bs>< zJqeA8GixM~D&V(@MRo>Qyin4FIM7y0H>kr1pcl82ioHa$tyb7qF!tOUyU^{xh&7W= zDD#Qu4Pa)l-S?r(JcXEFB>i0I+LG#@;OX+Ynj zVV+ik)Ct*vv{tNG@v+eQZOV~u5nSb|q_!Q_$)u#Z9-PHA9RS5-cG>`yo0FZaoNVzb zV{u~2!LKl+G!TV}jHyZQ!{^ju-Nn-Mo0*h=T@WM}QElxefly|;#{$=V&YUM>?ipjl zKJ&Ou>-z1soeOwvX;t4sz1s_Q3TtG~!aA2uPOhs$3TeV!?S8q! z^DA+%fm^CSA5dQ;$d#|svMUODm)!m?c6PJ^x7i8sEcUC<2z?k&c&NO2xr?eX||hEOyB>)nx>m9|4J$r+^7L=U;El_@K8?n*6#rJUT&DlXSsA6 z1+AbLG&7gSeL6N>kCk+1!@Fi6%p<T(Y2g8yOLs!A3Ss^Dnc=}hsK%q&t~6xoPZNenXK+5Kx68I$<&PPTWlNf3=@UH<-bTqa)bDr$|hVuC08 zD)Lo5F(!(1D)Y=pqeF~~l<;hy2o=+3M#GF%b|rBu;bTro01c>H=6KpkJ0@~yI5ib^ zpO;#u7RI3(W>mPl>Mu{)e8p&H=Y#eEc?Mut6RRGYwuyQ5mIepOR@B9hgK+n@+oly4 z9g#EkZqxVUG`2skk|o!lspZwQdUgF=7WZYmN+FLUD{etb%^vN;L-?KNWwqU<`cZlQ zuV~t$g1b%zf};*o9Io~R@D*3}!&*mi?J#4bgU@N$6|F|dS|>_QIDiF9kYXg1R&GBB97p83m6&GK;h`WFd&s% zH77`eV4?aFApqQud}fRD=W3_PbC9*a_=V#QjdY^6lsv(4c%3`^&wnr*`+uC3(LlMF z{wriLrKuCQ$%^K;V}Kk1X+AU(CC}d(ERU>arYr;sbd4IJ+44a5^(3jrv?|*XCNhmqZ$oNBK<(<8xBs zSo4d{VwmIEYw2Q$?0ofZYe{DHIHn~8pG*n>!@T4zkR&tB%X_p@+4yXM7MdgS4EaI? zo$d46{d3v{=H+2N08#5~vphtHqKJ?g&QO=jVcL&%{#YS|D0~F7OkzKtJ0dNf5gyT) zkvPXEZFbx**OUrxwktGSW+ko*{Az_EB)LGm(j7}Y%Di%C+dId=iEIakcba&=bdCxz zi#|lzm`)W-f)Z3AJtsqd*RttmrlPQWX(VqYjh9wZ_o+!j0exGZFIFQ#y&8<~vDBoq z?1rm#{*ovj6}Od+Uofn|*q(?PfBnW3ahS||MA5&z8F@^Q|NC5QyQ1m^(RN}c&Hm6U z%1-6x?96X;52v}Df{c2JnC|Y}U8)-}+_7`lff`rw(q zBGkoBfGeDj_v3x>8Prbo=vo?$tf4!9REaq~AuD$6uW)wci|2i@jPh15W~>2tO;noy zlZfgx!==06$Fj~I<@Xv7h?2$)ua7umQ8BQSE|*7QQ1{KQ6jXB%p#_hKBulR!Mv;xX zfO8m`W;AzW8asPyX^~!FNN+P--2583m-i0(6=d(j(2VXWs)))td@6f+1Pk0`PbPs z*L+LLs@53FE6|1_{U;3oqJLrt9_^mS{~Bp5vZAW_OIF?M>*JBCV(^yZI{}Yha#(8# z(NbVL8I+oJbgN{NBb3~Wze?%URWpJp;jaBvKHndGSWZhMd;0ZC6638Vz!-9^3%jeg z>b`>ErRjQAhEEbiau$@@e3uKSP9(nhxwHtriWT0|3?3%OTC)(KvOPvzbGevWg+qJ9 zmtRw_&ty0fz&+oC=TiD_2LiN4ru{fbcj`Q;;Ul(rzbze9|DKCK99`t?h1e15c@P8r zE)3`%6U8xqd1BG`^dL0zPdC@xxt>X@*(u%hsC?NWXn(35=u1K(Pk2*`&};gL^nLa;L0W}eaq4|rg(fa zet;W+Ed}0Ih>5P%?3vK^soaNLJ?Zr!J&IWo$&<7&9iqm7!{hDm%l=(9zK=J{1DW?5 zB468=n3}up!$nGs@UONLoV?xu;fN@KZskXiogAvl38ig-kKnyNue($MFf_?2Z@)S) zo1F8*Y6vZvk?q%-?m0r5+BH7U@X~Kxm@Ur-4tcNTyJuhMJO=&~s@zZ&)}VQ%B~;|I z*1&5{QV6ZxrBUw(oLxkjI%?}%0zvi_yy#pP<(XNcYj zC<1I~wx8}1Bd*#HT?BGJdJ1vB8jNL5&HId2?%(4pC<>-;^$Mr=o-JF$ASkol!=`%e zo^KaHw9>yY^!KAl1GK)#L^Z^jI;M}N5<#G9_A!p_Mu(}So;7+iv^x1o}PCmOq^j+;a^Wfn3&M?w>{s`Lvltv+E9uog>S6uyF$XNf(ZiOdZ zV7xhUz(_#?6$pyPoV@#o@C_oGzlD(umP2&Hz=LEKZCmwgZ0S?5j!^?izl<7l+*b44 zVcqcHaZfmTBYXO(AGpRCh4gDt#n#k}RPGs{*d`j_@0$zeXXw|(p5A1jyIw?2I+lo~ zI{EGn@FjBW9!h`uG5A^W0aO11oB0B>8=fS|Cy=WSkHs8WKiG}Hr|?2RRfUD{#6kNB zbl52(xxyzM=(|0D#Zd{e`i0LiI$zan=PVpMmbj5;jVS5*} zCR8-t3G?_K;k>^j%&3tnDp|{GUG<)i*9&9 zAe*9PhkChPk#oo(K*itTTt|VkU!&<}Dlt}o2s}zWjatmH8Hkhd%_g8X26J(Y?QnbX zy1Cy`H@QJ!{x3T<#}9&}2o0F^Kk4(;8WZ*#oM>C`G+-Vkpy(pXh%(>}r$tf$LOP}y zuIzR{x9q=j(XBIlr$mN2dSwPmhihq$L$LBJnUqiePi6 zwTm!{=MZp5Ar!J`5E{*r(cCz+0HpItlvuQ-E z6?a)D79_qUpAI7}g|W?Ombd;f-oAXfGf2e_&-kS_7%WuA+{wgYL!MZ&dz{{Uyy#_T z*=k%Zt05uw-Z)QdV0bM>16B#haISRw+fvhRsrl5GXRgCy(_whcO2u$W1c^omHCr&o zvAduwFE{y)=0o7MO@ElHY3xe}X!fU*sME{M8w=w^4csSWylKV^S~oFsfJ(43~qY4*50kcxcfhJi*>$L+?Xv(@3+B0cXgJ%~9nDg-Vh5rq5H zE7TG!yk%R?#Xb^iCO(=EAmSRf zr@-qJc2WM}mR~DTN|X>wVVV0#D#5a5pL(cPhBkm=h)Fd&`n%J=$(%7f(t=6DDgPHj048@jcM_QA&G=FJy)W}=KFX`o@G>z>H%H&w|=sqz}qhGGNX zw9wqpVv`hxJr-jk?iue#lr1SJyClU`=ME^j#S2MFq)q%glo9wz@1naxYR*gu9LAogihv7U}wx zjr_)>%tI19@^_;YpLDX|H=E-5x&w;z{>{2yY?4~F>rqi~m(fXOo}L@NvYTtwugKdC zJ(klQ^bc_ad*Q^3&dfU-r~$ssJv9@q2^Y^~J+#&fVw{2>Nppv}U%`X;WHuO5c(zM? zcvVW`G%KR^!<^8l3_pRdBt1++!I)adNl%x;jDrQ&W2m-;;L?lsYTyf>`PYp4B{sfa zT5p#1^o1yj(ZZt$#e+0-OMo-*1$9?MQaAbFX0jN|q{<|g5TTGoVm=^8n9^V~A} z36KT@LHpi-pNFzq5||o4&%9G)?^{MDg9O9BOM)wKVsmVjC){?5pbSOsbA7#-p62OP zzy@fA@3Dm7Yfx8O%bx=T#&Q=qB_N=%jz1(=#){&IEGPI&;p1RF=G~TM|}2qqL%08_v;EzNg^<_o^DHIX&KekMe!T9 z|6K{^J~?mL9=;h1VDH2k$esD%6kUjVq?InQNtCI8c-Kmo9iNOtVXbb;#%gTNHc9!8 zaWwZklKpd?LUN2ILp%UbWm<))EyVQ2pwzIWe zaa~E)R944=^RDje;@M!%;OR3&j*#V@5(i&-!4Kof0jxpg{r_cvS@pM(n|nv@eeoS_6wz6znlE0fYqkwsiJf|o=9njKk7vd+)ZKa7n}ae`I9a{JD+}P|oXua2 zIlcue8~?>m@&a&-wp^xzZ}xcS23p|RI^AUkLcv|r4suAqAA^??uj;n!VWV%bUAjn= zn>Ufe5DwX~vVfY?&O-k7OGTWcoE#3NOzG*fi{)Br*dzV@1G7I!7|LV}Dd^4nn4k4W z14g#zn}4D$VKSgH4{2PdfdJ!lB^1SLeoMz%76am|I_?L!^`T0h4{vOYL z{N=t{R}GL+Pl06F2jkyTT2(9;MYLRFx=Ufv!IDWvvfC#W-tOhRe`-$&%EmLg5q|- zA8dQ5p#W^X$1F57e8)hhQ&Hw&x{6_v>uFh$nE_5f|Ag?(l+m!(q##1&kTOMA0M|Hr zA*rrfH4{c3M{1cL=iyOnLAt>piZy4r4(SL?b?E?UlM9?qmzks8HaaqW1}h%64vAoq zvZEv=?E*UwvTFMOeT8;ri{RVa!-&GrLNaqdcOiC`x7orZAnJsKDN75?uYf$l7_Mey z83NE~6-BI2H%*~I8+8_4zO47I*(koJu^7pQeh_uVQY zx@l!t_VL+0>F>gObuqp(DQSz?Vx?VYJO#7a0opXEOVpi&!3+MCthHl)(cnhy-adz? zi8yttcdyRrNXb^FUa|MfQ~oh%Rkgo#3kM_xmYJ%`vz}Dhx~H%$;v#pBz*9}hNjahM zes!2CEYA!$XsI#VCmd6^|$lO`WfMG!+(rcLKb^g_Z zf18*StOO3SD}c+@u8P^3{BT7!El&(q+I@mV|0==kR2E{8+Q>s+I}@d%#rd>?w*cg& zoXUx^J0n{=|>VFVg1bE**Ip zf&{>ih2SoGS9B3g&@ej@zzNT#Va;TG6Ym-Z$6;~dFmg9PDXOGHGSV+Dd~G8>i!@zXUD2Spa8mbquQwzZl(7bt#%d4xwLr2cj>3y0PVm=4YRAN{ax{Yqe+&+9#2_MnD<|~vs5X`l2FzuR;weZ}a@xom?^lzhpOtdF58%iHbDc5vg0Wyo zG0-SEbGP;=h7y8q%cHP`Est-gOUlDkUc_gEF~L{#0A@DNq*Vd|3mU^+9p<{y#z9b6 z4L+|x>a<-`$hTL-xFUgkT(bMUNJ2TkTD(pFMOf!amMYTLqfTaX79VKoy;RTZxzvrT zAdj&j5QQhXLah#fdc;&MN*6nW)MNgTJd54!aonnKE@v#G&NR0@e^Z)&mlxA(>zVqM z+kA{D0+=^+XxOIshiGrGk@oZA*B!2Gx@YnUuIQJ14s-4y1VF5WkI{0Hzr8_=K}3>2 zCJKa5VM4e}lTY>X!=^nAvJ|XCX&Y-?`!MD8#?@1X`vI3n)xfdj0S*bBSMf2Qzxm!* zi_96{B@Tm>3wufV6!=f6;#1FzILAkO%(s7y0^||b>jNiYsGrGzAL%XlE&z1U9%FLZ zOu#C#3N*sBgfXwm$Zt0Fk%k~OaH!p+r7w;JhJiCgC&|~Sbmr|Rz zc;4*V>cYs9K0<|KWGPTBGanfUH?8t5$n@eWteF36+Hj*`vPkQ zH*VC@h6tPlI$7GVu&-Q*JvyIctXg`FHvyA-MpuzDYBDlI1VN?E6wV7&+hcCL z)<7niMwku=(G5~CW=}V+3>!k?Emi#kZ!JrGx;i1?{y&ZZLhQRarxz zHuwK}8InVS52`*!<}f8Tf(*TpzWYJx2~2Z#=knJANllv(56pDpFSt`bI)CTf8LW2UigU|`kRxD?u%X=`O zB7D@+({U?jRokp~tJ#r~k-Y4BRAwaZy56@FU8;=Ct-~8}o&>esFigB`j*A|OxWaft z;rZoabEnQLY zhO0fOkt#zyP{*X*LEYYL(GIm5Y1bI%ju<1Y5~D`EdOq4=_rSTEi~mmIV13$NOqim> z7&|p<9O{T3{|$OJv}tYW8_?UABypGfX?J})-kLvBWsxz!O%apms8KDuBiQ^}(F93o z3j)+TqfG<4f@QxxKPGDPn<;l4s8EpK>$Bv^FwFqe-e#AeDiKy!A5#HN-9VdI+;U{z zows*}n`XC6*SSN+dz+bp(5hXhS5K{vq~9+_uP2N>T6(<(x(ccDuP>i3gPxw^ zNxOg^J!2KiUxl7Kn$EJ@YW?}gb7P7)hP9=FJ+KEJl?!Tu_&r>&zE}(z6TKKK=L<`F zCli%RqnU+KkHf9_HEC|rLff_US`nu@IhTnnlI^`iTcg{(sw}toeSV-Ti~q#QV`LX0 z#TC%2U5tdv;1R?5{FjW;|A8I|p_e}f7K;NMSieVGo9)<>T5MRXbXb$vR|u5vRUY?O zqXTtM+PGll+kTNg2i%fJr*ij4M)8$)Kr((694|wTY_O)bvoOP&M<%7dnfYy3fx_^!48#YqCW)P#8PlM-ETVo9%8N|mRb7R%sq zYTQ+w6LEzI8X~CfFj@L7*!F8za{`A3*QSGHG~?0bg8zx2avPUZBU0Ilzz})1_aH+y_PHexJ6sP>S>H`@0q&A0OShC1^Mp=kun&lvA|(KgyruC!)6^;_2>k8Ze4yM=St-q-UPYt!!Xx%2%t{vy zEDW{oKT@}4r9$Jm3&1fsc^mrIAn)B9tun!Dm#!hMj5dOKk+_+oL|)amAWC3#6|$9k4MHec;IH1mexohIopG<)U^9hvY4z;*^tmBRy2r) z@hOGH4^@{5V5V(58EHH+R4l_|FiSe!XwxD}z(FAYb18Xr41;3c^lb{Ch(R+mvN(!` zO|ba*?KP!QaVh%6P`;#5>&Ffly!bdf9j_tuW@aL7Yp17B z1yMqNH!k_EOklh$-ZXYjiDe;72uX!RGn>A`fKtS?DZ>Up*JZnKCG9p> zRU@yMRI0*+HXH(hJ&8}=E*V=;0IFBmQ)~abQ1nv7V0ox(n<&;VC-1N=yB?vzY@h>w z?zL61j-=~QH-?>okD5?6a$Mlu3j!y*1SNqcFyRbORbL>ZYNNP;-62xhQTpaN<*O3o zh7Aj!)v;mQ`0f0s)_#|rPT78rDp<9g8=}g@9gu!rTBU<`itNx>Bh2gIUqys=4<(Veb)` zyv8SIbq|jlpd6a^`DeHymP5cPB&oDJSh)D={heHTaT(To+?%bzFUx!OQ$#80sCmRq zaz5smsJM$I%Hm>3)gliF3^Mie3nP#awVEGF&+5li5smF4CVTxZpi2ygwa zm3ftv!ZCu2lLvcEJTc=CMJpt{saCRdf{(^aI?|0sADxl<)8s!?mlzB|=m%e9F*OJ# z|J2ERQMf8_oe`Yi{*I-O{ z){QBKrn68pjF%!ZOL>_{M)q!{6DcviP>&{dOE&JAk*s@Yl8~lsY8MJ^a+qL=vDd1uytc`TX3{bmxX*LVxr zGb56UZ7s3!N+zmWyNMCEPVXopy`8gLPA{ zu(`|HlQx7GXcGlLyJTeL1qf@=N|nTJ_;39xS)$07mozNwr$8(`q(Ak5Pp?r3AcYtU zkv_4>80JVvg({WTWXAY$^4lB>fKJ?;5FBBX5gcGO;POP7)LnrP60=tpR%ph}?Pv-z zKxZHaE^EV5w#L36Yq-z`nrP53b=dy9ZjTPk;DC;x_1r<$Pdlf(_0q8pHfn1Otb`|0 z0R%^!tKSFXdo_F?KYW>zpJ-AVU{$_EmSa^3i`jef;fX(c92=5+VVu&Zh+b}ya6(%5 zj}o1DE8spl?OmPpRK8xSQObM$2fLX1;B}jPpE!5}oBdq;%G?B*f3$?zVB&n){>b$7 zi+jwV0+&IG>QyJonNb%_kH<7uq`H>0a=UfE&nES7CjJhUD~0wbs=aug_l&rzlKfz8z#LI4XmQNMUYpl?ns^J2C3o)hVog|Z$?9tk$ ztuOZ~p51YDK8qip8rhqWBBQ0F@r#tXrjaccmSd3#M$d;&{Jt|F#1|2U-i?x+5{?Z6 z?!xN1JJx9!Z;^vQ7d%WFV3{wTm-9|`pt{#Ss1o9yY7F{#;W%nbV$8=&X*H{>2dlhp>Y>W^0hw@F^O))9fK%cC|YcNz!cEio`PkVE3v{ zfU`g)z5s`e2J#wO;b?ngKT3Pu0vN(5RsVlQ@ifE>U~pj0Rtyc`Db=*F8xZ(3nKoeP zR@xe1TIjUM+yDBG`GYv+O3UE|!2o4u<4EeiqySXAnW<)Nq|$+Tc+hNaZ3XgxL0>5< zDz-s*z@lslLtR~6VbHd9c7lbCa>Aqv*MSAn0wq#ccrJ{S8ZjiX^zSga*b6 zN(nMWdy!3d3Y=<40dz_L>5sL#jr*cuGYz1<*4&>4LiKM93c_z#`~7_Kg8S@RtQ_JQ*x8&**PCmbB+}b-~}F%f0Sm)7vO;h8FK(TboOJ0>1Vb z@&Lr}tJ>^*0ELk;LJOo9$Rr&tvKAnvpZ=N**!7zyMeEC#_#21xs}<_QA>sL3VH2=) z+N-z!z4QK2J3C)P7~c@F^$zlJ5ChyLz)b$+|Lg&g2laBE@6`O>t1NrrPdM|fG2bh0 zqw^6|4Tfp@Rm;!yE9p5Qd_$*uVqj$836W%03;Wc_s0PNBsS!dm!+-nau@#`Vu)R3| z4c64^x$=0O0Fu78w)!>vJdSN?Zu6Z6wE69*wVL@&^XXCkMLt7KQCwYKHTfdITLXZs z=wS$$pil_&u>YQmL|OglMF8|mO8!3pQb4W0fIR@-%H@PKcj}&F6n8 z`8N>zKhH`gE>1uXfZluGZ0vt`{~y19f1V8f1xCu=3~c__+Gx0#*qgs^+J71Ta+|q2 zIlT+~_vL@@`ajQq@4SVDhlLs9;vCpaFxVzFBh94>@B6^mN4=gdcBp|6hr-%VdAa@- z;7-5P@D2V_MM+v}5gP@ADbOb!c54Hm%*wF*S9=f@fHg@m5YJ`13n@e@eGpe{8Bh4ye9nDK)V; zZRm9nm{mWIj%mIf-2I{L8y+0!@4STR-XUVljzyprG{N&tIwDVW@icb2sWp3rd357- zfY2OvbXb>%7_ov{anrr33 zbhV5lbYoxNED1zyTsnC%%%f&p*Ii7#3v}4<-XFwCUN&ylDj0drvZ^M!2&*ovh(icw zGUy@&53aajFJTVuq=~$MYExfs0S#Le*r^irm#!- zIweBzmt-+gb*=NR_`hiV!cwyZ6m$5Oyy!00hD--jp>i-`#cl-S6X=I^zLsy83g8Xp z|DpK#y!KsyxnlBQ$p*m_5pNv0G>4tGyOykTV^zky`X)^DHXlU5GWq~XJd;1A$aqTj zDvc&-QOXf$bj$W6B}`HRe@0Pr7-itMTIL4m@xfz$GjvpFgq`HC@5bw0#m$D?1k(H* zOi9f-O-Vf@onh(5k*Q&Dc~at10nTA2Yx=_DCq{i!S7z<+iq#$f-6C?7XKGvuH=a>!e_CD48z{?Zc#2@S z8kY*1e48?m^=#~`3KER7`Ta-Q{3D@Y3`?n&oRP8qw4-LyE$ri;?x1BBzFat$xGd+R zR!d}r9{bKQk;NJNgQxXB5C*ThUvJ{;zhuT$u3PfTAo-7Ol(K%z>ldxbIJ}IqW(YBQ zwd@>Xbx0{2u}d$wf2qAytG`@5<6zbxyc=nu0Y7n>m46}n9ZbGt3~O48?#}4WubtC_ zH;L2Yffk>=&>LbBM{i7$d|Jfmo?t^HEXq*jbhkuECDzm_p|Qkz=$!3P=+{AhE6ML^ z#Q6t81KxiFAq5g_znU5NS+*oZkMl+Eu?A}H+soT_4}Pa1f9`soxlcT^@%6ZnfmR9| z)LV+Ri~M-uE*Pm;qzi7r|H1>NBkB5`WKSV#iUFq1AwxS2nKt=*j?bj&f6|SH)3POI;hx$O<@cJ1QVBBx6 zea%lWmJwd3EWP=`+t%oo4=+76J&^KIpoj&gCABh?f9ZoKb85$0J1y_wi-hAZRRUpM zg#l`xIda_a1o9%96F`~dk=vTv>UUqla*lfiR>Ml6?B{Zv^`i}&A{lrZJoRgx^`#jl zzv+wUbAFs<$=Wyq>7#-r9HJRlGtopBYmX(h5d=;k@(5q>KX~29JW|3yw-`x_kQ+ z=Sj)Om`F|HJo~0ecVfTy^csYa9!CBS6+i@ue@O(^ULu5Be8IzI{860jAg$7$3h4rL zMm8CtIzOn4jngViRC2eODn+MDT?tj5*qBSoQo}x~#KjzT7|9)$p(ox%y>Yz_soBFx z17WleDJ&jQQ#sRfw|Mhg=WpPiKic)e`y`_E%^U=Zuhtn^$U83Ewlx^aw19x*HQ(ncQDQBF+{ zoOyb@m$;PouCgF{sbAW{BwA(b9Dn&EfAR*wk_w*6ca|-heb34+lXUB6V+rplV;yyS zU2(x*CP}X{!f*xTU^qt|wX^HF<@VN!xhN zbx|8$pGL(CRpu+=CM0h{!_AgJnu$r_1A;=Ho|w?m#3#Kzyxral|3+W&BF^7df48C# zl`h5p>asA^99nZ+p$UDyDK$E(tk6B*Llub@U2KeV;1y@(I4V%k!pjp$zU{>kxz;U0 zalt<_0wAmx%0J*6hD9FWSQ?^vmY!`pUDk9l5R)RS57}Fe`vi{CcUyVwf0uqIW#U3uxj{S2E7|ArSyKNjhD02NzY5B0g>Syt z;O!X;MN&PH5TR6;KzCy>dBO>)xj1$C6c2lRp0l)C&hLSk)7_pDYyA=W$?Wo?)Aky) z&xQuUbPB~R7CE%KVbrvq6e}5d5DuFE11M7ZTzFc1?@u?b&z&SYKAk=#f5fCP<3-eh zRWQ~JW zVPng2<@ro=(Z3v^WWnRB$dKNeYe+Sk{?Xn;aPj?I<7znt{S*OReRc&vJ;T` zIe*}FST2W``27KsOc!u(vj4HSIw(j3c^JO^z!E??|M}+EXN%Iff3t`}+Vu9aI81>k ztGx=u1V)YWQy$w{_tcBLw1KZF`;%ky1?8L3T|JC&aj8;0Ijv5&gF}Ih zou0PsoJN}C$%XA@h?KzVx@he>)YwHs@O#@Gd}~Dh5tm=fI5~uzWPm!t4j6=?(S79NtzhOjDwPjds@<=uz$~+x;)UO*sSOag$TVk zbF~@LO$8tAiG&-$6iGXv#y<#|JFm-z7#vHDVQ1N*fB$ffb_@7y0G;q54c{Kf4#M^o zm%R~99q-N((dAfM@w>V%OF8O>qfDE4|6}JOQPUP)pz7H<<9aL>S$QWgDDr*wYd+dLhhf-N25t4isI2S(@YJZ+^EGuKuH1i zS<$F)v3eVqTrErUx|aMT!U4)2cmvHG=MsG=e^Da8*H|7G1$hjt|HvRw1+Jvq_f3hr zMxCgRBYz>XmlctZ2)2~_7DrZ-eAeg^kM+@-Ymlh|jN!?ctgn4Chkpm@6jpSEVHmSw zcE8_*!jAGx94>Gq!TyaICTnMDA>(#9vtI2XYnj@LLwYygjj0&@f${A4=qpB?xfrQc zf5PNI3f;l(=QG}EHxp=dfL>ghS;K`@XQO?^=QWcdJ%Y0ejm8Xjv6wG@*Q1NynCW)_ zK0)$hiNCIxh zO6IzcNi2?P9PF-*VRme|9$h)-`w$5$C0P|}J=ITRxxa9QSLowzng8tSfG5l(e~7HJ zE3nc@3)xL(j31ZeHd!%aO5yp_mXDk)pHE%f33Kt@JX!O zWj^vvcBGK9sc~=kj-bPoii1+dAIk^^N5#V9Q$?%uk-PJ1pgY8)=UC9a;0^# z-oQ}A%8kyokpRtO1!;;zeH}79 zv2KOm0~WY`9F$7EZF6a`zS(c9QPTmo1P&7kS|*_1-uO1sv3Q@Ze@(WHOnSqRSfD01 zATUG5q-BUY+PQ07ubtXk+~8Ci9$-QS^=CBB zn3ypxPo#p3lIEJYe-i6HC?-CBqHC8mVxE1P!@OOW+cscc&p1@~PPh4VDuHq2Kvog! zu76GKf_TJzL<)+!kg1u^)v5MtLcnUCDT^3a_V`WhhyD()Sb~fsEJIs~t1#`mBc+F* zdZ?J3XR}Qwur}$^ltOJOE89Y38KS!fKGJFnUOHOpp&8)0qxhaiRDJ z@Vxz94w6-jZ<3TSD-Je)%{Z|^lpA@>j&L3&AKlXvnSk6@wcN#S;ZX(oM7P(mtkmJ9 z>LEGiSbKo3@d!qChc9ngz{A>l|D(Kw%ntB}7P)hVe?3X_EoOMCO9U#rC)@gu$n_@T zuZ?<0PXf$rq*tZ3CvSltRGgQfZVyGz(XU`sfX*Q<*ncbe)TaFBFHl#5Rkn z%DPv|e;Yl5oQ*jXQupIZ3!UWVw3utEc|M+D5ccCy<&w6Pu`^vlP6r|@#1r*5jik^7 z1|ED&FsRW>m#6*S+Sj-0v_m~Z!f3eBd!fx^6{Foz*u|Z8luf?k;ib~?37mnj*+!MH z;H{`cH^_p&!w*s`vlrvcXe=O88@oIz-`O@Mf7GFu(JIy3GFXizS#f3B5R|;XHN}tROPU5~RDv7@)P-DKKt)02GKMWn z5oKZHwtvhOwXzb3rjMD;hktYbpyw8_obo$VHW=SB&Wk=j$z{m4O-@}ue=k`)YuOp3 zf9(BrWN>DWiksV2gXHLYnaB=E`GgW`?Xpj^5VgA!A&RBTTAR1aoB`}(1pAX}qT5yR z)hsk%d_2dVSCXYL5qrMc~)K4 z1xI{diafZxK6SZIwAr)a(`zYzuazxwDYTpw?l5uK^2x-Dncbh!ae=zbm za(A~e&RRkuYL!4g9bz#@S3hWHSP?Q$Fx@|KX9eGGuu$>1Eq<{fuA&QlE)!u|VC>b$ z_)xrs;XS_AeMDa!a)!f8Zm(! zPH)_^21X8%cc28ng{8NltOhSEl9e(~%(9luD4%@O9P>R;yED_QWsf*&dR<2$D&mlCr6`10mT^l!WfC)JEk)b~|QHS99)9a-|N^gUJXgib;SzmZ}; zN^T_@dqvx+P33@wPLD-he^Fu2y<~97d12BskG>r%;;BZiayFc2^SpiQnaBJCpFE5x zHhQh#+=z$cb!EHQMU7ThHK($6H001g$S^b5f>Ji6O4_sQlE1{0eNXUn78(D`9pk9s za)S1KaJaU`?ftTer*@+fAL!m_e+ZW74xytzL7I_-U%IkqcT4^ge5U4%?~)9V3tM5r*y(@Mj_B3|+0O|)XE-OI^?+c;0E`@h5^E5* zF4cZ=HTLPr$)SDwe}dIG468*K>>#C_ex=i;p@WmsknKuy9YZ_oxJGtZgyp4Oo#53W zc?NM?X8L<>Wc2o{J^2sLF5Ug()7!5;+kFgS6Gve^3;MFzypypJ2MQ$0tzP@YU2jVR zOmJdky_#Z@qeZ;BdO;t~!?NS9lr&{}4CuaX8|ESA-BMOAf4?2MOoeE;;#OBk%)^SG zl}AWMSKKYVn!Lnk1+9m)sI>ArFGWHy1c3;ezWsWEBetNIf{ylM7;IwRbzJh^Uy=!r zbA2ugnUbP3COP58P3Gh2yA8+M@JW-&+PV-4*g80WiV$+p7)A>#D&Y5LJvlA=b>1_+h{f?- z?0cFYd+hR~@Ub1oCZU7B`676CbMwi1(+-HU?O6RiD?vii0j2qh4I6#O?X>z9)@B@V z=3S<%fBC@-Wi7K{1GhvG7kSwn_h{FWvt$SKV+Kp3#T~UQXy+}ZhB`i_Y=RIq9FPK3 z$~B>6+64%aD3P!ARF;oyi-Zw3*7k5{I0WN_lmU5-*bFAdTd6Urvuy~C&oFwrok{G* zjuMAW-xR<4>5m<<66DcsnDD}3e+5-~D%e544W&!c6jmXPIzhf(RC5s_SL|W-4;;7U6Bj1vG-NedI5nR>e8H_uUj$8)<6Y)<`kDI9_~hz1 zR%lARYDIq}DhTM@->dntr^Eo#4E2`$Ves}iz8S+1GERq)TI3E&ts9TJCNudKdkNZu ze`m_mQcBOXZ`9X4%97i@|B?Oey5ZEO)2QXkGr1bhQ`X%<#*y-3Cr(n@IRrlw(t?qBgZ6s4?7erVop z3xR1M-Z$tjJA9Q1fbttklCjxj({z6`fB$oIb_)#$`W{@Blw~u`#@Us+{bU-kTQ=Il z@Y9QJQ#k)-a3?$))pD8?C|fc%0M#Hua|C0ZxI}#vmqR|RgiYDf2hmY6L6O%VbFZ%; zk5$?`X?bVtQB5iE*hzOGkQSDT@ESma^@G;-IRdzpMuFx;nX7bX(unz@(E>oAhji~*kF@lu$Dirz@ae<{7VM*!0$Ur2YNg=2B^V?|7y9VjrNS>3+-b{ zF_MAPMl4wzIWfU5n%pmx9on4{s}m5q@WUryuZX`?e*+7=o1vBa zS{_~#-aNuZG&h#S+KXvg%;UVg3&%SyS*^P(ydxv$4)Xnd8 zZlxcAO|)k2yNyk!`!-)Qed6iBxkp0p>h60jC`bM4M6% zVq4{HZDQO8^sGPQ)rcjse+5ro_7Od1S4#?K;C)>=v>$M$?t{rq>hUAf5ViGdu|lL(J#4u z>lBR?L-J~au=ZN*==e3hDs<45rVz>SNrfZA7~|}Zb)bJrfBOgkJu-`!Sxj>Eya9pX z(=?V-4vbo%IfGoDL}vC;+XCVck6S(QC}xRaE_S(3jVQt$f$uplsy{@h+ZF$ANzN5~ z91A8a>@Ul0s257NWnEA}pZQK*{S!KUH~1j$TE^)t`a4W2IC8}!fiQxAV4|@H9!Jfj zy8L82b}Lf+e}IYyp&0hirnY}5S;^*N(5#T8GCVHdx4GTyu0T5($fWmS>E-kBuMp^4 zKeSV+1QhuaMzD#N3U8bO*x=dOf5%yLuma61UcL>w0XE7|b@2edL>bC=T`{A3(P%1i zem+355~Zh#m7a^gcEGs&Yi89CV*Q@-cy*<5&kSq5e~1~#EVvqQOJ$7M^W0)Bc}Q`i zJS``*ZP;79QUfo-e$CvL{Hkd5o`DV!87)dO?_rYs9{j|SgT#<>YC3lR0Nw4=gEv?_ zVyt*CMnsoM`05@oOM2e>!>D((dJh}lG+{<*%m(YqE`t!Z1wSMz%^I=2ZFcXVP&ie35Y-EL77W#R&1MB7DxVgr({W`K(+tgS4C~aXs7t+%hOH@zB zRoTr|-WL~P>tyvR2&QcADw#rOikOGQu65;Zf5g=1(oad~uuWb=zj$RgG*#@!f1{Xw z`7=15nCskspZaB;#%bNutq5lQ34zC*L6LRhdCL>Px-Mj zf6Am7^ZR+&avD@Gz4lKIl?t$&*_ZXh$ywkoG2^0-G!3MBgzzAOcqtSH9H|B4>~4@r zb^P66mneymj4ZeA-Hr0=h^-<)Wej)Hk}tRYqcTS;F0c0MpD%X!myVnHDs@zjusF-{ z1P2@OiTMwautl;(X`DIdClf)Q;$4e|f11yqmq^5O+UpEl$t6H{6+M}G;ff|D?&t|X1Pv`#H+#|$!LZLSf85&p zDF!IreI7PNszKT|e@F#JLBEjeI5~c{`t;q>P>KC9V$$!sw_|a1RzkP=`U!^Kub-dm zgJAmY6LHnHsr00u1x+3SA2F7{Wp_S?Pqni9J~ePH%8U?r6Cfd@2hAmSJ<>J-p=G=% zdU@^8DbTvd3tVO`dF$Y;QZaKPe-Nu8Sje*-bbS#$ZTS-NVu!^IgJPUsglmfi4e^{l zUn{bdZ;+96Gm>(s;Gx$*I~;u;FlobB{G5QJzWynDI{-d<#muWbS%j6#ne+V9A3SHK+ zclV$adu(CNk*gc=439SzSf69+0`tD#l=2z5>ZV|Q^YEDhT2F z5bAohhTLxNkEULSIF>8UmWNZDyP8l;^vsQbNX%w8*t!BzK7Wq1 z7lwYN-xK7cQBUzR!x3sNe^5^*`VK7nvu@2K)vn;0x$K*ME@6BYE*xcL&3ky9x5HR; zZ6PTThepy{d~py-!vO@Uie=`+nhL_D02ka({9;5`aBmUf;bVn2u@1~v9~IfrqN>Wt z{(OD82cbyf-H_kH^$>}bK7HBKr2A^`rTC-(A0k6?ZIBJK$j7@O*-+a) zl7VY*d!ZJ3a=KzpEt@YE>PLYU=GGVP1VW5PPIz;VW zX(z5tYEL$_9QWOV8%xW0z>ML{WgWNTYY=R^3^{)0cy;koem zC^s9wIxCy(rt6@FoY-7|($`b;mvFxA%7>iOiNTE&&GgiBcH=io>N;Ch;Z(TJ#-uyz z2ZrVa%Qr&XmWA!p7E9v3Fm3^s-fY&3a!Q2S#X2F|eY~t$#>%ho!cCXtr&jt1*bs$H zDHPRO%W~ALe=LMjIg>wVskv_F$&dHbP06hAKD3z=&J<60XqWb)o2y8FQc6H3=j@kk zYveM9a1#^p%?6R{`Xwaq!42BnMvckQnN(@hk+*JWx=onFS|T{Q+~-8MKR0|h>iiur z8JF0=_4rElxV5kSwbVxQ@__MMxnsz-BsGUw`k(tVf7nCpN+$9buhT`;@zYNDq0UKuViyHhT6RSB z*X5a&GfY@N6YBjhSg+(1!Ho33WFroq;q(>8u|oMZ1|m13C*;8cT-kOA1Q|b?9K3!Q zhdC`qe=RFN=8igqZPv{irX*8VBrC#_ z{knH;4ueEoO#5~H>_#rh-ud$@fP3QTvHZpe=5UD%>E~CIXt;>iiL~JTb!&_+Ix)|X ziDL12s2xLAhee2z-$M=Qj>~cz3 zBXsO(r)Jrq2On74vUHLZZxhi8EG?!mzkGI`bQ|;QNyh!YAfy`d5qz7ymX~4qP zQV*JiLQg8o%x9H*Ef)I=1HD zY^QS-LR7XAl36(?9?!a2cG`jl~fRa~EBRU?RMEeV4nW(~b$ zF`ycaAWtz~kRik+%e1!sO(%y}?ab>mTho+zC4`AE}TP%ly_}6o$W6#qoQQsm!9jcJdSM zzS#|F@@7?x^W+fG?uO}st%|cOBhtDS={Y}`rxJ&{wkmXS{b3-E3jcaCrT8*xRQIwW z09!i@L3bpZt8ZA<7=tilZI1_Ie^M=$hbXO|J)69>-Xi;n+?!19F6JLPMT8p`MEvO8D1snI4}M+V(wGE zNvd)AsZi(^d&oq{i5HwbT7Wz)b>1Hgeb_^XBu=`Cp_Be^wqc#PdK>#^e^*E-+7XeR zDTP>MN6w?ZWNP23XXahoV|cFD&>5`lUtFk&X{B&$Itp<-jUM)@Kg3bi4%9izmG1im zp7s=kU96i8g-18v_rT{ZS@Gz>dOrKY=_sk$3~xb^RhAk>nCtRt8W7ZIA)H8g1b_pR zDo7vs6%dWO(1r#fDSSqhe=7hdMRp=KmDVFT93DOTOJ~c00fKSl5=FJvCT7m=(+iR| zDuYEh?zO*lN-@1{pEuIAkmnCxV)W}mW}D2hH%`lWZy+x_Q3XoR^aC8DQx%4Ni0E55 zKqH$s(=;h)-840sf2s%7Xx{ktT26+E=;0!Z=n}SRY^ZM%>}i;sTu{2q{~ljOl8!E3 zvJN=KbuonfR!WaAva!XnC8R}9CAy`wzX6k%e2*iLH{ef@-g-#FCya5tA4xJ ztv;V-HEg8HeVcc|Td(O5NIT?2CuNaR7xeknr<3nafaNDCeXS<5vSTr7?nX<4e&~6 zQz(e|pNT{DdEp16A@$-&r)3Vo>MpaYFrF4fG`3Omk5g-H#Wd@O#%`-cAaeiA-C}s@ zt2M;_e#{5ue{s~0OT+*<)u4S=Ldmv=e`T1w$?iFv}`T$`u;#n}Oukx5XtqbUL4cFoe59IaoPboiiB zGAS~zTb^RLB~yG%c6!d0h+KM)nOR_GDB07oEztPRKS4Jhzb4x*<2KUXmlR$Eh_25s z^`Zmyf8gs|UX&`o#eH+{w8vxm7Dk82;7thDAe+yBbunX`OM;50yW!p{$iDdOs+g6s zQR;qycdGfspcC4=JQS3HoRvKBdRJ|p{k}3iaqS7$>B>gZnx68$7>I0I!Zb)u!<=7PD|nc-ew8PP=6sl%7ieOv0R- zq(ANoi7$Wh^19AYGi=tddDu+XHyAJW)b%7p$&5BGxh`Hq=-Ii~OGB~Vj4%!ffA&_S z=Qra3%=BH+S`6wq^%S<$zlw>bC-UJ-Ad+{2i3Ax-@OHOmpt z9~EWGD(gG9;_W4qn}Z0Ddj=R)S9Yw0={ zVbI8wbn`e?v1!;`J`7#~#u~{Se+=v0K`gzhgNkv^k2*m_4ud}3xz+^N??lSIM(skx zdf>iII@71{QnR1PCJZ5A;1$8VGo>#fnE=hHBcc|_uS&Zsvg042suikR)dPhoOiD6D z^XZ5xN^{BF=lDVlGxPe8g>o)@0UEbnZ$o4Nn8hYHlG`Uk&Ds0_QZL3pe-fFI^t6{c zk2Mmbma{j@wusdODdBnyXvzx~xc!LfxYXW)EA9%Sp99yQ^0npcNxs(!`bvNGnTy}_ z!`;)?)?W%$$LsWbz?9anLO2{dPL#{KgN?+XwuNTOa^SzLtA%+&CoXxO_5*?fh9cN0 z7%Y%V&_uTC78{vN6(0r%e>R+l-1hh~VqF}cE!W~*4-f->{BlY0ss6msa1&-Xyrm8v zorj~67FO4i-CpFeNA9AG2Lly7j}qLD{aQEuMLW3$zzq_Fu-{RGRWXZuA3RLKL*`ik zoh6m?HM12mwwKNl7Qqa-@iBqkEAp-4td3>k%}CEPUa^yH{<;vle~>?!ByFa;JmO=% zXB~M1;nTU_?P{#Iy$_WurWK&loeOB@;{xcD7fwmK9?;xTq4XVlR6i24-ifjCSarD&ee^(GTXQCvAU%tL;?}4p2S;a}v+fkbR%qJ_Tf)L6i-|to=QD_Ch ze!1+eQXmMbz39=~1U$EtzY^Yar>u=IxDK|a_|oxH5Mj#YsLR}7l#K(!ojBM1p*|Sn zk;zI)zG-8?pz^x9Fu=|^6o~P`mC;_;FJgbiB0545a(w>!FUoO@t4z0>c5RJZ6@GX# zR%QfiAnf@vjvd;{ctt0wzIb} zv333n@qg^7WMTqvHa7v7T3DL^gyiHkBxJ<^SV}U}R@&Z1GQNPPBiq1e^eW1^_2}6C;biZYJ(VCiefRr~&pSjy4uf zPJh1v7ES;&M*~~uzddla16bG^S-TkjlfYlOsolR4vUjxmYhm+O_ZLjw&dJ%y$kD>y z8Spo%ys+rM^K>>haQ-K@lf_>(z|QoqrLmon%ReRkOZOM%uh!YX!qy4kY~t?xPb@=! z6M(UWlfAWp$KTk0!R#F^{*{J{lZCC>e`P=oa5OP9a5T0yadP?#^B4P{?)+Dsfd8p_ z1ABXGkAHdF{mbeg1V-r(<7&=)y=f5EVSv1xLj{iR&0~-r# zkN=(5f45dM`FFbi8!!oHgTHMNur>Qj4LvRWzl9b~q89EZ#_|@6FbajI3<`A%W%JDid4d|6ajgy8e|vor0#Aq<}2d z|6;-Z%TWIBAUG>~*#FJ#e^eu5XZ)Xse_#X!?c4!gGz_fl02)SihQIgkZ$cc5%s&5% zkpBW=_^-2!fwQB9J3#Ai-SiB9|Em6f{Qm2t^WR`ZY>n)U{}~-6X9HW~zti@gf`8OT zE{=|WN&eRY_*?aVoc}fVCMNDCMlfqDc1B#mmg!j;&UF}hBU8d!1APpjBO&&`8kLI+ z{cG%c{nEpCIV$x(YC~w7W;nmvJ(kbyKMy4-kH-4Yt;u>*O|A=YeTXQ3`U{b_NITi6 zjsod)f5B&5s6~6-EJ^QxX|mF*9_>vjDC(AeK;X@EGC4xsJX81+xfc4P5kJ`@_!^}( z#Qo?(Y63#3D>}a*O*(ykA{!bX9U1Pu1Mfe?p~{VeCgC!`@J%@=yaQft#M6U&At#@*?^P@=dXvIhJpq8yh5bs|j7OV%oB5VPp*)k}thEwi~(D zP3ro9gy{_{3|V~3rip+vS|X3+!TTXax3yQRyC+?QB@lj*Pk;7gph>E956Yu)L_@si z3aCs9nm1N9-4&4CY>eP(F)G}>&DToxY0f{qQ-Sd&^RF<+u> z-kZxmI?-psyxlxtaJ|H{Un{OFllEZO`;af zCFM=kTPn69cHI}Ot@i3EQI00R`c?Swn%S1g zNzc~Z0-bp;TEOEzZo`bX-;xTN_fnzQ0Ezy4Z>hgP#Fn=j90zz@RwwsNIz;;cr|n4i zIP8AEJa08rb4j+HLI`0ovoBp&Qk$I?y@JMekc-2A?#!5hcvIbP8+vio?CfS+VjyTs z_>-wls`z~RDxmRX@wqQYRnr)yivA-upeLNL928StEemAk%RoEU`=`M#U#CZQTJ;)q zAfb}&k6&U4rBv~|q=*%d<(`hpbqSQ1o--6xmOI7SK6WhAl}Xi%DhzC_T!pur9iRMf zac^#aVi#G>c+qnPIESg2U6lhS?H4A=m( zR0s9OBgI9muzzs#koQRx>m1HyRw(>QhrmC1`Y?$M%B*4ZU>syX*oY_>x5mod=`*Ae z8P2_4;E=j)-1m_d!Oh;KYmz=U`V<9ixl@FHIFXDD=E*&NM~<{}WBQ$OhzH{H&+Er5 zgkxnZ)mpv8>mfH3C`?LFl4sz_R2CjP^mD8C0U{UkWfT&*Pow}mWnnWv6eG6_MrK$~ z9q&Qa4}pX`XjPI3-*u%w{TAA!)pIZq6pkHqR`tbO6OX@HUPgFK2~Y`#(9u_j zPI>#I@f_y`pI1Qh41NUb628-bm7Z`B-q;vKKGYqjq758`zBe`bj)4)eOM=-Ny6~pW z;KKf(G2Ij28xH5pEznRNG2Wbc_D`FCQT4whS?gUFYRoWSXjUJF6d@1ja2+4L*SvW5p1cC*)lc8&3sYL{p&129z*xw;ElMpeu9Rw+8C)F+#fw;z zwea&;8Pi+Sm53|;BZ+`FnLZm7o;Qfu)J9bqg5Dp#DZ($07cHKrS;AolTnA zG8*JU;S7q+&PzFiF6T24K0U*9VqQ<+xdP^@|3|G_DI;7Qa~ZHlrf0vGEu9DyHTP;8 z*j(faqfzzIBhID4>!$pVmn>9&s9%~mz@D4)2ys9Gu?D|siuY?>?=c)28WTiHeuW%f z{pyZlPF2C8CPHwAruU~0rU>!du+~@HK0hYPedd#Y=;`og_@Ip1?-6*!^ZBtRy1=() z>H2UiY^`#o$y?RVr|V*uTy&3*o|s4qyv#S{tH8D7iMy{;l*z@E$>kP*OC$b44_(uE zFX1a8ZQr7Zpz)>=HdDO%Xs)eLbTgW@2GT%zUxc3I*}6Cuc;_ZxY2yb0xnxrl)AYK= zZX?vJlAb5U5x43!@D(NRfL7}PivDNo!x2TV#M^gh%*Jlfs~o2)fA;*1u*RC>6WtT4 zi{oVc9{mBNj3|nK@n<%F=C=XD1GnNdp$vFB<%v7(WbZ<7gl-D#;z=5;;tI=cHlmNd zbem{k5k~#*Qj?buWbTFi_MSE53qHa3iR-0~%ItOO$0W{AkWUp7UcuEW@sgpNZj@yM zQ+P&Pk0zQNpT}4Bf^YHwPmpJ*qn%pCeuiejijfxsC}!&Y1G~@9kraE_9?@=`BO39)4ccAir}x!l_k`l!S}nZ>Ge-0 zi{`?GoRU_5z}_9GQT?nco4oF(;AQ!3lkN@Q#Uq#d$z`gO?3G+|%R>H0RV~JUN;H!- z4^yXY-n%y3x^z^gX{#T62NDs~TzM-TCc(W3yJiSw@ z)$U>j%8+-nxstDpyjepIloAXYU>b9lTecn)vIR;DZr!$jOC0#*haf}~QH=~!x$?1S zlD4lhl}io0X}E_h^Y8Z@OEkvxGowsm1tMjMT?V4m|7}Jkd#(Dcx2W@@fZa1I6EEa9 zEHVdwBZpfW91DINt>DreOB6e7O@bySXI$@SiJj@}R4krGI1mR%Q*_x51{*!_D#iI= zxcs~~){YuKIk8h(yp7LsL`LoB5Co@~@o0W2rR}H0XmzZ|7rJ#2FV>RI*(y(+u~Xd^ zM@~>i3?ocngTBgjonK>24l%MNoR&(a>%Pq0+48A4k z-r~kBHN4D^1|A%^rd_0IswRED58S>7-|r1zBg@>86v=jt!&(X z6V8)$78A!^ddTi3wM-GO4U%|-<a?+6tjr$<9Dn*LgSYRe^Xy>@vyX)dBruStk=SMLf(+AB_kJDeoYcv z{1$fQe4xv-iNM-IW2#!94=}$A#)JEzklsk~F3J;$+9mRisf}jMMIv4lAjg7hJ+W-C z{%9M*e*1*qk#J{D9ijGY#Y&0`U2&U7%i>R<)?#w?Q}YyM*fty3rVgO6%px(Hf9uWr z071=i9s%f+0$nZ$y%|yNFVpib2L0^^HS3YIn{@@IbFPl@y}AcZ0d6`)K?P}`N?K23 zC)ajH&&03!p_`q{1q8n$OfhdCF9cNt9kcK6mR0y^WV&Dp+{c4SNN^oEYzePj6Evb^ zxw_Gg8H(=@(b5Hvxz+m?LSJWDf3ZUqCPvE^11&cOQbj~svvv4nU8vI^M=e}hV}5YZ zo4BZqS+sX}+L|cW$6BjKJZCXv<-t*q_AVl-OwPr3K<;qCrQkz!hhpXMyVa>5iP`27n*=K&`?X$VsZ!(viOus*UNR^%y;ltj+8f1a?BaYiDr zbl3c&ITg;Fxovi=Ogw6`mOTRPNl@+Sncn*IN?nZ9-&-l-bfEXBZrLKne zgVrf2N(M|jX=~*&`+YXzf8*DmCwaF^NaKvdBu(Yy*T4fR>9MFxqe@?#hv-8<7XA!A zu0;6e=dII=$0>zwUQJMRXL}3E^8s7wI)+=5Pwx30%IiZA-4nO!_ef1o)06?%^`fzkv#p(ygo_F1$bRhs9+o9d{prK{dpSDfp8mHN<=J5a*X0cQqb1o!D=VT z;u`Qcd`TQ&8~*T5e?q(_LsV9wR`!{nxU!H(oWa2bE;W!+n~neAkb}T|nx3kN!_=yt zMVz2VZ>=aSb5gM+|;-`vzag_KbzF5|i*dfUyZp)LUN6r~4FTwMz6Ow13A zMM=ev%R0CmhJkj=)FGx?zOII0+?gAodTsTV&Vgc{7_KyPfALy7(=rE+3PDbaPgB>`I-%vOv(hj0Ae^0>*bl|m-aiQAdU2Vn zqQ~5~pux=+9i_YiJY!&ZcPQebH>d3cv)M64-6dimoXj>hIbwDTPHR_k-*mQ+ofLzFnz&yc_+e~g5)WjvM-rpi+E)OY#cLXgK(cr#|9bw2r^V2m5SHI zErRjB;eQ|{(#m?b|0V+0_|hzNrrxth2gll=)z@hsfB#To1MxoeOgW>uUwu9xis$E30{|f%+;gq(9UwGbMR~f)JA%Z%n#_Ygx^MRO=ep>xAONoF?x^9mm z1+6~0e}J^##5s(w;o;7*u@dSuP<@Qu_`@_AgXhuM&DGRZXouaaLwN-jCbci$;U5wl z%&@`{@Gs1iMHnX<=_hfJvY%vE5v^xr+hJu(l@C=o12tgND)H02K!VVC$4y0OO!UavJAir z!vJ;;wIQ-v4}F2XF8x%sGNrF(Ds)X`4o01lhBkoaie0B90iRpePj(8?wS@eA3RA`g zf9|10_q_r101W4WJ*7Qgo4c`QG!LrXNcCDa=Gg2uDYFA!RxKB$Pvk@!M- zI<%xf1iOj7u9p`ZRg^X^3jgy3c)g%mcBtLA?1{AFMVty~SZ(3prXEB)4DKNpt-5|s zwvJ=~{Fv4Tq0E4HotfD&AFkgEU)LpWxuHhN8rI1VHYx!zy$Wc%W^F5*C8DW$f4`9! z^Mmz7FOmHE^SqziN~zJZ)sF32Tt~9^fvi9g9(B0F$vf1I{T1P9T+vH@WVmBmU<$pY z;Uz)!hNkMA?AhR?H1%mCW)-=Sd8vqh=>sh`KL@; zXDwpLF?_pWJK?0HxUXitm6f7ke-q(%pL+EVI2oz>nC#tc>X zE~98nMlJdDI;j#i_2FBus`Vgt?X6;}AvZp(D*!SAdV#A3V{#vge_>WLGGCf~YKX6X z4mRq-$2a%Uj-H(WTVdTAst6?&vhT^pFH2pk#kL)4UH3(}*<59TwOsWGt|B|^7YNe+ zi5iyd+s1OMib82T3-s;yrZgP*d2 zF^uei@A2(;yAgy!e?{oF;bIsRHf(c^ckp2;jedd*1(8bMCr`Vx5_OvKsG&h3v}NU? zY)H8?D@fA1Wl8M(_Jd7Gt1`L{ea``b8@Bc!$c zUANyhrjGbq9hZ_j5l$uzmBC1Wx4wA@(;zsS=SuR1IF_{ct-!QJS?i#%U1;aIX9Q(nZX*7vT zSvh+#jL)VlMfOZ3?Nd@Yrep`DiqG}Bzuv4zm0=q<9UxS7R^od?e^Bz>31Tf8)gftD z{l>3Ifff7Af2{HS83{tz83k9~eB<)rUcuagLo{=6&L+0{StYVBgqpfcW~&1;Tlbngr_`6=Eezi^2OFP)Yc zm4ck+pzf{FMN%~y$qK>v9Ps0=;cSqgB1+B}1+aC=f7lhjXP`3rEV{)-`AiCy8%nAg z#u^M5_u~}MQR)TEfx#rg`HFNld<>a=Hk}@OF|RJ#+~8knDbvYd_TE=M%)$oC@>+bwSc0- z8v@UJe~@q{d$O{ct1hS91!YxS?hQJR?+XiuQRrqCq^{47wVnwsx?^Hu&rfM%AQlvV zr?2X=;Xn}BrDj6G3O8n7Ms+So8QQQ`>((!L!mpZu0kU@$0IFjD?jV|&@!c_1v(?n3 zYsRzqlazCGqQQAK(?*EQ@(Nx`8mn?Yt8!g`f8~CI_zQ4X&8t@ncDWLgMF#HVan`fK zW1Q3-J||<@;_n=o)rJ0=Uj5T$rAa|8Q22+Q zj<8MjvwH~E7t?R@=hUyee>Gkj1`zqDP#!WZ|3az#Zl5Ik9F(I$$mg*p zH+1^)S$ZhPDPWKuz&AZ32wsX~%IwPVK3&a^wWTNzS!=}Kcv9bXoB$`M{g$f?)V${g zOzl-R!I;AOSFaYB*As_t7T?r|oO+P`xfO;5!ad<1g#=(sGMoBk_ z75)*E7>pwBFTloN?M{{zsU69pw>GfouWD}fhlbdQ+v)edC z>(U#$g*IB9NGK6YlQA3Qy*lHBaAn>`C#KEX3k~TB#sHc@+*Ae+x z7q-}R6h)>6tZ*E`+#LQle=u3B=$x~3WcGwxzlRsx}UmwJ`P2;NVwU@MJG0_Q=Ygm^^Fsx4Mwc51l|_ViH?Ia>Av>F;PIn?!bAt$~Ki zz9h{F)l))Amo%Q4KL~Uq9&g~%xxayJPSoex)`iHP-5UtvahWPPe+pPu#-;g=N7>Zz zL$Vj5m?;Gu?RnmSKVR6&SsLV|412A8i<8a&EKUC9R**jN3{;bgA! zax!*%ycOFQ2>9oYzX4u`THK>@Eg>cbIj$X!hzhcBMZhAkrMoazB5N%`DYD=5#2=Ig zZuFV^s>DQi?gx=hf49!%H#S(*L=xI#zD6C}*oi3J^}zOg3AABbyLvRKC^~>WgI9W$ zK_TiUln#o#7T4TV^*gi3J!>$hJG{49QLy6CoS4B*UOSEgk79V zwq<2Tae;5e78W{0J{525Y^1l`i z_=$H}mP8|uM(J4}?4{6u5_)tYSMkxaTW+jYZ=t0!>0Q!4p6ywViOv#+i8rsbWYwxC z@KYVF*>7@$Q!}}6!QzYJDl=A${bnQ(?qCgI*${>%;UD{LkJ}gn&Aok}3~DAi z7MAH{SC|ppe`Da4hySvszBx^%(oD1xVppvHSXm1ME2Nsq?J&yb=i5zk(r^uA5FY6! z#vOd8MXr~$+Vj@)gvJbu5}rnG zm4$u2A^0$1CLnMuYD~?!0moX_Mmn%uMy}wOguz(SWQNKNf+y=xhf}aIWlWAjsb4fz zA8l@7hH7gJsTpgGf8y#PF#uP4T_!j_!2&Xpf9Ix7Foub&`h=9DpH-@>A&aOKV`D+A*E4Hn+Y5t!JHpF+^L_ z90z1$(<#Z%q$Sax4$PR`hbOWnC)bSC$Hd_WoJ!|-I3$0V%K(K`S?5N$)z>qMANJES zA{Dm9ZJSR)-D8llj01uS9*nvKxz=z?C4>Zp+c7f(IG zt)zBmeYdF|Z=mAd)kgZZVR%N6=#};$N>Hc5WnOYPZKo(CEL8lP`wNVGiEfJw*4qEEzo*{e++zm*>n;KS4ymkZ1#cExJmDVtG3{3BoqZ% zFqJBhAdWdUrpQbfzk=5aSXpakdyFV+>tXDJrCbjWy67oN$!Lzx^0wkI@M0h?1CK;>1e~>Wr zkc2#ljFywmI3NcjwpNELW8>CO>oTkY30mI899$Mt8I?o)pSoS)5rLTaFTyTM5I z`b!joeN%+G)qhfT0$*110@KC+g070N7a%F#WBvT|+U6eaG1Wcy*(i|cO5O4_<}ZlL ztoGTL!|ox}GNon1_tInDIb29Ge=S3T?F0yNz*3fz!aFAznFGX%SvF=B%Yd&I*>_Hh z$#Kwqg;0-?6v&QP&s}jJ$=wi>2=PU>$v7#J2~cYieSvg>5_|nIa3*Zr&S?4pTOC8r zk)hVTG^jkYL9L1tk6cXs^JeWR@PuNbg7aRfzI;G>qRj=5E?&zju-yoce?CZR>d_Qe zl49@dsg+IDN1M!MDcR1QXYDmG3H_u!ENhb$ZHW}R(Bt%A$s#UM7t}X!j|v0_)*fyd zL=3fGb=rF)ERsJz1*9=G)H^LBWKFj(h@{if{5KoxHM#S}66t{#WnDI*qF=(}J-mu- ziX9dijIhcoo*Bq z8}Z({V59E{vjcUNueKq_+0yc>PW~4ORoVRVqVccFh!3dov0e7k0Fb2PFL@jc3J$3 zZ70&86@dwiD}=zPe`|DWI?Q_S0Pn3so`=9?0+Aj;NL&4HUTkIo2y^3yjUP|YPT-!^ z{WB>!8paW$sl+v{fihY!779;QCCZ7p?<6D!U1~3oMIUlO6h(oK+TQytAWcTt=%yOE zw=GY^43KiPm>h>6@tujAReD!Yn+l=v_nCsZ@z?KM_zx8mf4z}CLB74aATPSZDVpxq zgA4;}*Ip)Vgff{EJyUc;hOSE|mTQQ;*04XP%)pn7K~#sR`S*CMDN|tFG8UVD_|4BYDkB+P*=);a zk225vFhza$&>J#e%x-%)w0NBt_$b7Pzgk1@In^rcq$pwMG!f1)n^m@mYb(RrW@$gKd7{S ze`cS!qtLs*#Ips&Aj*$bGrwm&aAj z?s2^#e|QbBClgu43F5|&bJWS(Xte;AZ4J}dxf;W^$J^BpJGu8K5pMfLgkI^Om>g+`ifn}#Srfrf9N|7-Tg_%Mh%neY5*L90&9%t=fYl27j_(V-CO6ql-&s73Xx_(W&#h~Nn zf2c8!O(&Tv7rC>XE1}^V3C~T*2P<1;WiA1<5M_fg_JHX>$pej0=5q>!wbp#ku2&wZ z!x#C3Y$Q1Lo3cFv98%*f+RN$oZNq+az86+uUJ35eaHNpv5+Ce-?cMoY}tQnImqnW?t<~L-|X3$-)4m^OJqN)LhxWxaj>bJ-Aj}~kx{?sTc>}CV0&za?*M0sl&~*Cg z#AE-wi95Mkb|ubUhle05sR?PUGa@bWp2C|gh48`xlUnf?|08NVU!^ETmD@k-e=ZAI z!(lI>2LvY=W7U%ZltwpLVSN>yvE?-qrQMjQVFThFI5M6Su91Y*nOt=weh!S*%_;=yTG zygfAJORoZo47n}X@L{bnrPn?<5WTELd>Cdv1)~!fqv&?`i zRg_NDn#Pdw3QFmP(K3^DkR=B(nmMo9FRGiTRKCgJBf{ea4&3Ybf5WeCcCVFsc zO?>Peu~ZLEv6WCbf2|oKwd94xc?eitPkV_nBzSJ#R&_|@Nj*X79GN;zliFfnP<|nG z>tPY7z{IhE2j;&x0}+q* zmKBBot;(5;<_HeAhMoDsnV?TM?S-&&@8W&wo$t7e`r+`qe_Ml{=CkX6mNUlL!h?H~ zY4*>jj5n}>B~Bo*e-&Fn8>MUxV>8!hnw8@Bok5JhAI;VGjqYzTLOjWGUy+)@T+gLJ zu)i{wL&Ob+Z`bP_sNNjk9RYT4AK}Q4rKisVO>h?^gQ4FkArJZVq=S(1y@k7EYZEdq z^pw%|#|`=Wf6^fiWgObFJ=@)I6w6eu+?O;Lv&eYc&6o>yU3iJrPH>62*MPLF!lqfi zXxW~Q2Kj9kz)=ytx%SDdT(V;Q2PH+bFif89lc;d1rvhGnMW7&(J3HvdapA1&2;Ha_ zyEX1~nRoBP8J8B^z}-Dq22);O9yVOel7V&@5cNs(e>LLs)O|b(U%A=*y0$5Y%s{BC zO$b>jsXJwnJy1gCMwsz#-VJibt&XsbSlL^l8loj*3_OuIUzo1TD7sw<59}lxBI6cs znULtl6gc13>`a1cA>f2jYG0FZ^&ba;M6_#^QIQ@sF`E@8umz8b*yoW~lSxFdlA$5gKkx~7BY$q8q@ zV6DCy+Urdft^LXZm|z?uSGgOF#7Ta!A7o_h&k0>EZN)n~`pFTNSbAEEl!D;_8;)M7 zJS~waP#E<)L}Cohlw6EjCrj>MN?bo4lJtMef7*#F1l)AWo6^k9xuuuEi0JdFFo_o# z84B}eFCe2k6yPZ<$@%NlJFsty{?R^+Y8O_Qg^ACn;(F1tqcPCk!rKbQC10~M#eq|^ zMV#OR;R|%K>Xge}GsvVc98u}A=fBR=eTWn(O^%ct0NI6SY+#tYkAW#M64PiVvp`an zf3&qQd-Hgid67&%zl%YbLk&|}FqJCZKy^_f3|YtbioyHfqSYk`P;;7lU1H>-^@!<2 zNuN|)f7E9=u_$M2uw{CLdd4P-q|OLL8g?fi8o2yR zoA<|x$lPhBF`DIZecAFW2uLk0$Zf7)l~{+=J^N&7*hmY$+pw_~xWWii-%IL5mnBak z#eW=JTyCqqBNk(h96Uc9wkx~8JwL4k@Vn6RGg{UzjHw%X6b3jg>V)^#ZG|4xt&t9VQOH>B|p!wpdb8b|c=VF2G`r5;{N@__Q@}!#E!glW*At4=9jEQ?^x}p$y2m_ne zQUX*cys^Kkya{+=64g#xVfN#3>x)ql)$HP9M@D<4@q%rQo*VOCUCn>le>dUGw}Qr_ z$5P78RyZx)_4X`@lDo{b;lVT5cl#Aegyz)_h6GQg8wi5T@`@D@l-Mv8vMydOja$RD z^L*nL?{MGTjPCht2}@e<1TPqBDB3aR9ijEaf9On>@4ZpR0f)%RRodOx-y2mGTjWe+{wdy`N1hYT-8Z zjW;GFLZL(nCWu1tP>B%Vl?q?KjAR2x)huN3GYqj-pvkR3*2^>4FgNgE7bzM7Ka|>a zOL;~(O>SEwO#^E}mXqvS08-L{E38BDs~Bu)`l&TU-+7Lvajlky>ym%q7I8yBWUHBwCG7?zOa_#s5h{OgckgzQmSRf&pTU6xURCc&Z%Bi)e-MFhOR)z3OW{9Xjs~n~ z^yUs{F>t7&gXVtrk(rPz= ziTX>Un@&iW#q*5cG5QC;>K?dR%eQiSyI6!ydxs1;?P~U(na(czQ?Oe?-#3Z26E~=*qOBojF2|37v*l z^ZCFH5zzyJzpui`OX#0ANR}8a13k>hWTW|$B;lypl4q5|6wjeH~7I>vClWi`Va8cf0EM)}<7^^7b0a@3_ zeeRbwyd<2x`!YJvYsT@cF`cLH?8i%$nUGEp-?RuJs9Z5Z6nrfw&$!DpxNQ{34xvA> zuG&yyA;`;9Rp9&l5>!}S*5=ne?ep-Tj+vm~e`;ik*jyxN$&bkkGv|I=)%+4+uh;Lt z`ukWIGrO!JdW*iGdh)4K!oe#NK-rE2&QGAcA0D9H&^Dz!UX_6VEpkkPEcQsDN;CYAokV&)@5bl*pqseZ{UU ze=lJ|7STc@lxz@8UQ3#U3lq-F53r^M;^y`;48`S!k-EVw7_S)6lxG}~% z-tn&0RsHL_*vINolcO9hARtIg`Pji_gmW49?h;ZX6*a*!OvGSBP%i<|`wlWvniD}G zI{XBAbccmKC>gDRwh>^F#3d^XA#1eDK`=b<*ud|D0VD-d|G?Q z?Eu6-V%D0T4C)WJIWpyWak^TBENuKuQL7eNl_6i4j<06fR>q7x*r9qZ*b4R00@Ads z7t8u~dO@%_pPu0y$ImKyS*~*KG*`sg88bp_?zB7OrUz!+<61F&YWMbRz;rtEf2O>G zl_rgFNxIqVBn#@`-=c(H#6t4PQ<)WOzPWrJVbf5nmO-uV@573W-<3L2%Z<_OY(;F<}V z|6M#uFoHNUolNWXhu$gk-y=4ezu2aZD^Lf5+rbRlIs6e+=H(+p(YL zZ89>-^Tfpu5NNPy>X**F2tVJ)vWg&1d5FYqile*m2hhs-qKSg|AJr!Yb0B5_ni#-<~mFeR{=7mH?wO2Pdx@(DClb);IRmql79XX*UR=H& zo4a$W@JfNG@F(n{aLt-2aDz)HZtwxZDCaIhniiTPruAG~-2k{if0Sm8O3>oj8|mxd zIoh&M<|9Ja^N;RG8juIzKxf_CN;;{|Dl>y5dq&>0tP@s?(w0wGrcPl^QZwz&TX5sRSJDSQE39A9 zF(#ZTbw0vtr!}mA4{s0qkywGlI+_bts90H#!MpAw`PF=+A4>0U|g{Z zwwCVU^f-1Wa@29S+;9B#iPO5yAUE)RjsJl{-q(R_2Kp=ZVyHQy;#UuEgGiNk$pz7% zFvJha1uL7%Uf7!O5OK72yYVtYGmdIvG%IqX;J7EbfA6k9W$xZ3Koix#;|o=1#e z75nTwsyExF!CLVIB;{BxJiFCofnAEG4(dMBPP>Mxt}$bfLZ*7RSF~}Njws)Zb;(*; zdtb*Ab~NM03@$c7Zcgwzeucjosr-E6LNMQge`>dhxKi7A+PpU(39)|{B?TqZ>sZvZ zUYRD~T>&cMgZ?ngv-8#P6N#AxKl)3QC)CTI5xfJG=%xyF8ipRHhTLk~L#P@N@_Bsf z|J3-=&??(XkZ9HWn{6Teq}+uv-JSTT>3)J9*@jG()p0H=;(9t2*}Ni*lo9ghyJ!Ge%qQ!LTU(@8yJx*nR@$? z5G#$-=TCjZABsc0f$vpqA|O1QTO!cDlTKGiY}EbyK7NBn97|b>)u#s=7dNP;a2bSLmdWYLM=-D%f-Q2m?kNO_8cJhF-Oea{>&$MS%lb$pGRzNt z#H^bQiO!n z@Rro}`20OX6;PY^5Z76PVB!Pie`~Z7TE}WG*3{M~4eg8DZ3unqnV2w&<*}XUDyR5l z4lklVC*I15WT%Hm>Uc7@N7(P=*SqqkwQOE>{30Z_K~i_(PlgEhe=lT34yNe zTR?A-+k_vvl^U~AUhJ_T*!6JHJKawj0T6i=Sp^N&%Lke=vR9GRz5E-Ue^Bxe{FjX3 zu-kd7q_eTUz6k_#eHdE+N@HOTi?|2^)_VroAX86b&Ec9+@_oi?YC?$gXD8Yqw|-;C zDpmFZhXQIOc0!l@_#e-pvz}EUJp6(lJ-V4`emK#t?IaGd1}G+To8ul1d3t!SN#p7O znkY~)RT?}L{h zMO54^_|&*K5+p3aXw8Q02sE7%%pG6F(+P6b-xX=SPf4;27gaWA0^`*NBqfH4$-HS(9tmZb z+06E|93d9(f_#e*rF&_i7CFIrBZPdpGxV9QaQwKtth8ywtX#{T?~_}f#hnlI2Q&r& z;?xu2AV`($N}w9!e^5ZiQYwZVr#oCi>h(kpO>(R9-(1u0JO^iqZ4&VL!MWGZfr2x|B14Exr?DeIGpmG`%CQIq7-LG7Q@;^-@-qx=Y!)>k@4sA%zJrKJR#L026JM|A)g*pbwX_} z&Ia8drQ;p#l4;w`z@fq9o|GH+g|!W{uGt`ZEo{X$agDSfbIl5(z~%h<)!0aW^;(@ViWm(HTzVU zc3E6qF3EZ4NeY+Pm%XRg)IvkTb_7R~St6IXP>6J&Jg)}Cv}Q!)7%Yv6;xegr&KV(v z1WrU~nx`(&9Dll@DJ3_twp>1sQzPr#)QC)1; z>+>^nCf^Hm|2JL_6O5GmV9SxOql-F(>CrpbSE0av+O?NWnTu~XFSn#AT3G9p=uMsn zUF_|yn3nV;8*r*ygJ4AC3B`)>^H)r|lKhJL5~IBjUo*p^eEpo=&>K4!>m%*)@^%7G zVRlT1e+m|?KNYNb&?OC7Edfpq?Iq^4K2~{k<*9Tk27>}N{X?CIM9ydg`hulrYWe6@ zc%j67oW}GT4j+o3L4s}JW%S`+9QqZbhe?}VRzaVdvSn=+S>5RFX8h{X zwvo>Y%v(`tpQW%0bk{lV(HdRY6RV|ZUmX2%e~og=e4J-$N=J+^zFY!mI{wnHEU9la zem-b-*Ki*io;A?nB-Q#as6bS2dTZ*;(810-3ob7R)G=uzKQB%wF;)CFI2Oj&k42B> zn9`ck(-NsK`WP7=9}ozh(WLWEH{*VFbG0-Y=8_OrrI`;8w-&HEVu=4@+hnMpdpl{`4i3=f9(0gLu4@;Zlg)2gF;X4x{&39J^sdLL?iw0 z>)%|xNW%;`{9I@lvI)}pjHGO#vD$Tn$o0X|qZ6%#b;@m6Jk~m12rY7e`e?G zK(yj6tkHC?8HSUKfOHR-GZ;Z*LyDeS5|lgcBU?x}aJL`T9#+QG?4J=sle= zztlpvXxe|A{nbm|jDLhk;TJGK-3DZ>?ia$X;qsYZIf328n6_nGnX5WnIn{7OA#}L8Mb7o0{*OBRT3~?ut z;8E1@TqxFCe7l^dhbDCTVXJXZ4|vs?5xg`=^=2bS(6R@bloSMCRC>SKUKGW;My_N| z2IIt8YU$hbkE!eUBhUeID(tsiJnxowF6!SQ59V{Dj>3lHekl4exbcH8f2wb;nW%IR z&hVUX|GM1Trtj8($=Prxr;eeC{9m9Jr$S7(yYgHNef&i4LzVOXG(4F~?s1DwUwyYK z5#5LS;ZncWRX2nlNx9N;aX7eBcC?sn389qO`R}T%-gSjE#GF1G!F_937*<#jb$Lj@ zH+@;DvHR2{PsI(8qn`@Me^Xxvy13g{ls)N*<}%JVW^O1T9Gr+>Bfw>BJ0alga%u*j zE=tRJ+ZiStUmJ(kEg-&IQdFmfP;`s(rw2x!sTdxlG$3!SOge^=(>&P*Jl53_)e zB0%4OF+wtY;j^<2@6-UKy%lfO(Wf1k#0@U&J4y_;wWMisfyT&>nkL27Q$HE?ZrXe= z6l<9@E87Kt=)=s)zR12tuy<%?EVB|>)nGce54qGlqvTV&VXc(}HAuw95#v)TZt6>u zEx@H;v=z)kR}!Swe>oAIq$_#}hpQr}A;?3!D{<+0%-E!EF;J}#?l~njVOQ-Gk#8#y zOoiRlyG0(`ekJ_CfVQ|x~!6InU;YQ;dN=z z`5&Bh!+T9Su})MaX2&!eBt(oPG8+me^&R_s82FF2ymhH8ZPdF zql$xzCnF7c*)ttMMS_KT>@9x7-)i(9Q7Ef2pzBk9znDLnu@bMal0{gG@cj_Ce)?oM zslTc?c(dK|<165XUanxiwqd6~h73*A;iNX*CpXZtkjk=Dza0WT6nCGJ1_Zc6DJlSQ zi83u@SC!tNe{jy`o8L3sb_~td>Vn1O;eNi+h5d?JhQ%a z9ICE=BXhiFi)iI?7a?m#xgX5|Ys-3e*n17_wbVMoe|zz$KpAhU$C=1wqczodh=F`M zV;M*wSbFsB!Ww@aI@{pV`tV$x$}~U2Z>%o*^F)2`Yg@r47}$S#M^=(AWnJp6)&`<>E#JEeLC54pyrOYiI8qbM)7 zO-`jsf723A!En2?50Zpgx%k9y+&{9~YHDCsrG=2TuYs>kK#8EjQ=lKcqs-)~s2I?R zNri7-N++NQZG^G2V||i@Oe@QAri|FUZ_y)=FaPHe~w`OKqCE>8C38Z$O=Txaf320VOw3X zKJM{HRY4~LQnV@Ww$>W5d`bc)oiGk;)3OXai7PrU-!|xT#>6o*6k9M60O&vu$us=^(I=n3H(NAPGyE(33*LI(tTYko%zwK?c`1FW-}z)Jm;8R ze_wTyEjg*L9|#JWJUn!V;>Wf+ct5T3xZpxsR2kn@liN8DF* zJuD2mEl5NrJ2HSN&$O`^z8tdauOr#Ce+J!%S1{#pqa`X9lvpLpMSJ>|`y(=7?I>|7 znkx7lPPLVoCrrFKh)ozqF&`dPk@^Bx=|RvjjmD1$%&>#u3VU1e-c>0iyalq(Z!z18^%{J(3x_RD6c~blt)OjlvC~+70+SQY zTCUzLwAV_;nJ!6#O(A>l^S5wdsM9}JO=j&mng7gu{dbFL#!+-e|El+RLtms)r>!#d z9AK4$yMCDi?5;^J>mTK+!HMnce=k${Ib^OZ_A9v&{>-0cEDR(~x?0PRDp&UbGMdJn zL3dW7-rI_BE)Z+NV{jo|(;SjsELhN}9kD z6^k_Bwzrm#+ulOfmynj5P}AFGM|(dbERJY;q%&iE0JnlSCKkA9@Tcbh6M+FZFENG$ zuBrMb4VZdnaH||~mjUbn69PFjmq54y6_<@X0uBQ;H87W+JOUO2G%+xf!R;r1t#oBr zoZYe|ZVB!d8h3{P!6kTbcj*Qi4>ax?+%*K3;7)?OTjLfWxJz({A>WyM?>uK_{>0%)`VNe4#{C$Oaz1i+xFrp?IA%<^BB zzgGZe9{+*7dOCwG?E!SJKdvBK2S+=QJ>-?*|JhL;1Oh;;KmZG{EeIf~tfDKYBm-cO zQPKp+fb2m|rnUeT7c*P1IY1F?4zhO!F#;?coB+1}IsnWa?1A9Fr8%>Iy>f{=155$V zjv#aJs~gDO9OU>HVgWdUob15P&aeLfurt8Y$jM0nz^mQD;h%&Y zog7|o*u7$}WGW8M5NC5Iup^RiVSt0h>rJ48xy#>@{=r^p zUQviC*xnfc0l7o|#xetc0f1m+RVUzosovDl(bnT1Z-;+w{bvqfh%?C6f(?z6>oul1*dC4j@2tq# zTQ~qXIsRn_x;Xv^<_dE9r$G#VXNK`L2~(hhy{!iT2(mz9S8{-VyoLlY{J*Kp_TMM+ ze}lyTEdu|y$ou~%?!RmFzdYjq-}n6Q)Y2}two0aUuLJO}9Rqk>GN$%`*F6JJ1pHkz zwx&-1n~$j-*w*9!=JoHlwL$+%_y0mB2QhtZi@3ezt2C?vY&`rN0{;TQ&eC9a5KsjS zF}DI(nA*Pf?H{{;rachkWDB+jz3Tf-E1pkMK^S{oYOd(EScYr_?Wi?*^R!VrypuZd7aKE{zlMy&!M%wKB}r_ zRP=~MKHkFZgmQYr=uhpM=Z{Bo?TF!Po?07=--=ZagHxSA%CWqLZS*(KF$(PVKFtcn`MlBGZe|IRt?JyM@X+1TWhbpZ7!eDsTXwDtCh|AAH9AaX+)}c&?QP;@#Y9%}| zq8maaa49SG1QMlV*5y)L*i~){C!4g~_rzbYWmoL#DLzEWWz$}GUnCp- z?9gv(Py5Ilh(0Z90^RMdS14LX@u=(9m2E$UDONxge~D4b@#RU@JAA^JF{|pUuV>MZ z+%s4!BmLGak&@97@qQyokURr$eab_yLFX!}nVT|<9_k)pgE1Y`SB)b-1bb!7ZpmT0 zFJGyHS_=?t(TgO~x2V0%jreE>7i+e#?x*-Twu~(K0H@^#msIAqoYUkONk{9riR$g@ znlT%ff0JE-PrcdpZuTkIrL(~+8J19Yve3Y>F5Ph%>WcL3S4x~!ftk&qc_q1a3IZ&y z#+XQ(YJ)s!iF>xIyN1o`wcud34$Cee zwAeVry~bG!>)O>l$Pth8Do=%597YB3L*P;ee@hDULj1Tu`?i7#7cqhx3=32vG7iq# zP!&Uh1Li0#`64t{9bYFXv*uLXNo}3**mFA@+q;7ac-EuDJcpP`5jM)0wHI2gE7oc#H{X z52GxBCsNVQfE#}{HHh)1GX3uBe8tbEQ%L|LS-AT6T?V6wIc|*(v-GOO(@CQ`o{7kF zoUz>ccfmIw2i~!=#0oA=PQLeod4HChf1kweWAEK$4l^3a$6y&rJDs`lIe#r5_|z(X zg@+pow0j118$)(%O@ldEDP(7a%OB2q(naou}^M26AXSQdsr=}?4O_w<% z40&;Xppz1<`F-}GyAv~^#Jy_*e{K#4d%v^AR$W*ll#yFxlQfd&s|mp)4D&rJJ>;13Kd z`vkVA-gXLcIYy*h@Kd6crDM+ug!4|b@WNRc%-QCF1~*2LZpNQk%`%IY2`)2b$Ej%k z(bW)JkRLV^L!Y6&yFEocE2R~2-jGRhS~@5z=geS?2(A3$pDfl32WUh0A-)kg0qDuN z8(s9O@7#EzRA$H7TU%Bme-WY7ltyGLed!N0A*pj;-eeYRsCNXiiE0}w<~J>6v38$c zersb+xat$Zq6709u%ot5dmerWD@F6}W}iN?78wsCC^axqK`(U43>(H*QKcNG$gt%E z=&bI~ME>bZ%gFh#XGWVG)Nxy;SR-xf@(tT_Y!T?FyY_TQme)!De*oLQn(YWF+pP31 zZ@eOW;Dp~U4~uDv7HjK9{yd+zM0wRBK1*1JVu2-K@*_4lKwAwTW@osjx^A_Zg=vT_ zgud~d5yK8Aa?Ro)6Y^Q4u+i_Re~wqBo#tSEJedBF)2&Otcxs)7G+o%Rhq?HYIWN^t#-t+HLl=>>3v!IoWbw59Y=|uFn4S*Eg<`u=Xj_)RbSpf>_&%QMM^m%P#TFb zY=}45HqIAM=xjo2IdS*bE$mnsh}CM}swCHv*|0cr zw2>ML@@y8pQJYhH38G1Ej_Jwfg9F5;{DZt`KWm}l5C1JL28|dPe{@saFP2Vh27MpT z1p0eL(zS$Bt%p7AH70o|qHY^Ghe+ch*@;w9L5(*lcS@|r-%aog#g;BuBTN+zz3jRZ zGUvV)Ts%_vf1{BtZ^jN4(ZXLu(WTL#b|w@|!ToyI(74scv2`6kEJnm|DZ_YkTYSD- zVjv-KgKE~Mle4gH|0Y~34W{cvT_AMFkHCJ7OQ@tCGrsj=nyi}IIJ^Exa{7o*;$I#XhYybV2Xpi4=Ucr_05ZRbMbh|^Q&F5Y^5ztt zr)+3HjUTHAFAeyx5lYik|MA=r^>s>FI}zEr&l^MReP1yy;`Mpnnv#l~H;JFCUiCa+ zHn8y9e{?aKCf7=d$HOJ_GS%W$&#ic$HHXQxh4EI=g)fo>vm%^IoI+8byx6sWjMK?HO)uw;Y;$7r#8G8sXTxo|jRc1J)wr{V#>L?1G z;pw%8#q(Y~*pk<(Y8*N7Ji-xc0=D8Nj)5S3f0K-#Ugo$G1@$1{&LUtiOKvqhzbXN` zcX%Yd^>kEDHW+8rRB-$70!nZNQB5l@nMG!nN3;Av`H$S zc>nI!gwUo47D@5!0KG=OVo$7+&NQqIf3#die0*|=qmata6{S1+DJ$grBfHIH+{j$Z?mx5B9D@tgR1?F zM72vLi~~kOOnYP0}js=xouqe?jfciSr&80iygiMpXd>O*$G)V9HZy5dpW=Jc7DF z8lr}Ahx_3nmCo=NDSEraJ<7pvotr5l)hzD60&2fyEl(p5;?l}kTFaTdlIIE!3oXLD+ggwL*RGc zV+4tf+T05}1%r{=h0X1F@m?StPO(%mBg;M-yjY8ub%&|fx2O!WqwF9UGXTkikh$D< zO%$$~SQPXamn7L-^hzHm&EIUZb)?92y6lDuU&i)*D*sE)(k2QHlLeHwS_U=pU`<&Wgx_f68 zlMopYSED?$DTJQ-=f)EJ3L8LVchKQ?Ico@z^n60xt8-W^_Pe`^|0?%VAlv&pp69^Y4%vrye5&rv-n z#u`G&{&9kP^a1VQoUF&Q!&A)UhXt=f<~h_neLgZheg#?&=qj#=T3BtsbsX za&av*2dl_>WYc0-@TC~O{!YlxE>$P?fg6KgBY<-jI@eghj4ib9Z;8e+k)eh|?G+wK zMbOfAe?*$pYc?ZWfe|3`#ea+MYv!hCWc*3zGHiOVUJ8c?bAm~3g{NuZW61u%=c^t zr8zfZ&QsbI`jkWt=WGM@*Eepao4dQK=@3}>Li$ivU%G~8sC z;*@Cp>c;DAGk0v!sL;9)dfRp{Uq;c%e?;XIX!^AGHWPE%wOvf6wl%MA&CIwq*o2tD zduZg6q(GnSvR0N=T3@GQpyKn8X=&I7#8A#axq&C1;aSx0=ry&CPgGuT0Dx+wpA%Xdjj7MIG`r zmXuYGh$S?-b#yPKH`#{gj3Ohj(9xL$rg44k75eF78<>`9sei@I{1y=EHs?0bzQPzO zcw#O;T2^ZPS)MG!vteh`mfCi-f0p0;P$DMIws4TJgRFD9hi^X6_Q`al(6y_yQ3)l) zC&;iTD6ESAvzEwu%t~O~pM;muC2X%E8cmY}0=H%+Dr(B6vn(ObrfC*0#%2Vl}lb=wX@KF3X542M894wmpIts;&Cg+yTyc-t`m-8CT z+L72M;kfZ(_+Z-a6dqLS1~3lJoKn z4vKHBJH4r_5pjYV(5x7O8os1)`I{Bz277d1tRKUh*z6SMwtj5(=&?5@;KO3@BRDbn z%G^}2iv6pWe>|}If8iF@(}Z?(3Maf9r#>U{XKcW;#4jTHyQKZoTYJ>E>VK$zCd9kH z*#s?DV!nMMBZeDh^E$z?H{rgF&#t)+X2g+@>-8J+I;UNfm*J2&){eQs+rVYyt7|ss zFtgOmmbZ`Yuc<_E%wX7z@vi!g)i6;&k$Rvfm%v@bn55H=e<~IaFS&z7$PA$!L~uZS z`^{>r*77*R!-Ii`Si7sw%FZh^+*|Wmc;ziTk96{Z5@#lju(Y;4TtUHIGWLOjH^C4c z>7oATg1&i;UH6zT1ftBr7}@jHZX)T=s;*LhJV+EUHou~j(lEw~*V)RVkNIpNO&1Jh zRfpfL0c(eye{v^;eOiC(;hc+q2rPq6g@DaxTLr@xX|0jeAukhrYla4ed6DIcSI8N% zBR?kAzkV0~R@+q%cOfVj3F|v}!u?Gafyj8yGiwt*748%cXMA`?%E)`@T<#C5C$dZm zty-A~a-kaRP-MH&OwcvOI~G|cpMiL4FPS5#HDYiue;aQjE&&=9VUo&Y0wBL>++JUL z@ry!&9%R<1Svg8foig&>`Kd#mV<90jb4wj`1m(EX^MiYS>b?#j&eM~EUh%W(R*;z6 zj_wZ=!)9*bPk6JJY8)~p?^G^60vC$D8`jrEUdWeuz~zhuEnl4KJSz@nQPrVOY}k*@ z8XeHJe@7S3+#;h}r>-&LWsJvNX)UUu+PQSKX&{`y%FSjWMxBN>X`Nk)qLB9l-qQG( z>#L(*jZ@6U(?x#Kep?wtwlV`ooQSA#sa|quesJOV@)L~V8rUSAP2tGnS)%Z}AcvB5 zy~62PPL(5C7h|i}IKs{*H>zw))Cm}u>n71|s%eqE`WW?QMBKk8MZ})(aZSOkXXSouPa_gPA zY}fkf;~x2{&3=fh>*YVK`FVxnr@l5hUyx@S@cZ~%<%lG0xm2g=`P~=^L^GZm8UHRH zkg}_yZupVi&yfs(2_S=Kr(45^u+m;c;NcA2X&iMY8RAu_D`B$^1zI+o4Fk>Ff9|#m ziy&KC7x6QhG4x}d`cdpSDW7ww_X>CWrW?;RUsg!w=SV9C`_cDr(|^&^3hKq-;aPsi zL7oU-dS)+H!5k1IP6)%vr2~9m<`ojk4x0|7BV^Gm5EAxV;0$i{7d5QILoMBD#VLEv zSxR<}Ypp!lJd9rt>{FeC=-GYDfBhi^<4?gM$Q?OJtKG+^;Zdf8JT8||WMS(dnM>)& zKXyO-xy?=Qu8#&!`B9)jrSEEial=QQeR}#*(4?KIS3)06PG($4USvPi6e#zMDsP;W zrkW#8ILp#Eoc@B6ou2Ip{nOm+JADnC4_uL6+&sNp%(})a5<{3O3s>?Pf8Fo7sN9Fn z?dxYa8{KeHV}@oCL3hh_b!Gv)``gBsWPwbI2vWkso)2l|#gUJa#+)uH2!Eb+JJ<`z zyTiwuGk=ok+PX>D)bk}4cf$G(pBBCFhta@dicYACNqN_$!+ZON&vH`Q=ijf@$cdh} z6R$wmmdJ*BLoR|?K4=j`e}Xp3^jU}e{3KFAv__bPHY;L*w44*nq6p*pIacczkM_Z4{;07}hctT8#qO-$49MXVu8H9MEkC^cItHWT><}d0+$$iQIe=BACyL zO?c>2$G<~=9lA(FVQTnC6S{5$BH26_P39XM>9_oY$YyS=EZA$Bf3>Y#{qt=L{xd+2 zNHMzf8Cry=?_h=nixf_7*cj+d5A_{r(d~F{$Tz^Kw<2qTixlihW+lp;_{xMw>=aNz zt5b08^HACgc{%zX>k5O4ES$yzt3?&if5uT>P(Q6WpZa-XP!TzeUC8YFL@>+~7##s7yxzZp^>Mb&lFIk_ z_`E*q{N<=WY06GxiltLxJ-D@7&Jgb%oq5b^mBhD)VuwcqjC4^bPI=#L4*_O=WllN_ z^GR$!T+7_?iNho@ON%^qQ*&rgaXRv6> zH6(`~{NpHQpqudu5B*IV53WF=%p1k<4aH2yF=vJpyf&4PnXEAcV13dUNdvIt!$=FR znpbVOEZp_lc3pKnixMMHq)XvrZCL(RPj`5ngpMI>A$U!^(HRh((K+x~>@rC?nqDqk;!jF*?fF#&T=pIu1cpix4>Cj{v%$bH_$&99hm^y9DlE~m95>@ z2jZgnq&fKWz~n?v4=E+aflwunFSAyW66n%nxZwwou#Ai;Z*%CJ@jVh9I>3_5$IXlQ zTBolNx!oZwp-qkxJ8|&BLri_f?WaTC8{A$cEUVnQe~yAs*@(9D329Yi?{4y`<1kO< zQ*E1-ztqjVQ=b{Dy0jdLkeuVfHyiP~?Ect&Et!OBP1u#OO|71fPTsihJt%2gReftE z`)VIZd8C)>sA&&uQndbP8VSsQ@C-~Lqn4YotN$dMmNOwnGK~*@bGM~e=FU{1-zQ05 zCZm|Ze-|25Cpq0>br&zx{(h9N3 zJY4fJ3anU5h=<7b`gEE1%&hT{cVOK;zUU-Hw#@P3=SKfRtHQ|l%;}lKeSdd6tsfar z?Dw9&aG0W?*|9s?RS&|-ReI*NV$6CYnot>SeZBifCC;NS+Po7x63# zsEWLd3nV#3`b=(bu|+AtZ!83v+qI!fC6(BN=JOXF8giGZ%`}2N zKglz!w-4)PYNg}Y+ZkLPmSlB$TpUR1!a95Y+#*xyIe`a=7 z(?`_-WPhKvX~#e2VCkd}9=G~A(h0&7B-2!V{_+kEctk3y-FnkMokjjg~L`8 z_i35WQ`8SV_1v7mzr$O}T;{Mf3DR|nXC;e_-}HJYns5|iQi2yVMWd&Yb9C_&qJ{SC zsc$?N`{%r)IF+eATZ`e=W+s`-<4; zN~4gesQs4Q7JPzpYabWB4-&W%YDdPg7!oGO$#7)MQQO$r5JDP8_0Y5RR2}~C{#@u#G|F&fA;=?&%13(*&y&P zepqb;6m+lX0BmD8atO*!o>yWjG$r=BoIZxaSr){cf1azbT+Ib$tDt)heI=8W?ZL`K z`kai9m@fQyTFSWU!D=v^u!p)fK<(eeu8?HyRmBrzP|nj8N*=zb1orco8#G=tl8Y_4 zl*b?+boZ&T7QRC**k2EPJrJ}yh z)Ygi4e|ZRcX-N{Y0@JRnlq^GQcvlrE?bb6}K?Lk5D^UY}a)B5y*yf1g(k@uE@#B0&@ z%TMVxo99chxRe7HQhRhaWvO_=qM(d~dnSbfSxk+N20;di?Z)3nbe`Yw{$7yW*@Nex z_rc=+Nv)rme@$2Th6y<|kN5-Wg?WgEO0IW!0&1GeAC;$M=0ga>i&Dp#z*2W1NZ>5)Xr2~;HZ8O3@LKBF-l^-9hXDNwL)^yLqRL5gS;n~ zS|ksW4UP!eCG!uQ@8cBthHZ1B^HX;SWlxb~D`_LLUQ+WlR~!r$g_47f9`EjB7GFF8 zW$BJke~CE^%jhNyizZHTs<)V)q|v2tg+{EyB29HHOmvj0V%qo)DerSj2$PMT2KxzK zSkVc(e5UI@#_J>_BjO#esd0a-4E61SXCwxCtJ#_=>daNR+7hJ8@1;RU_YElUm*PX~DnHPFMyu@vIzQ;Q5d%vJcR6g6|J9(#iQ5 z?aQNdtYz*g%yUcS{mq|*6V$-fk;Htq`zyB^0dFh&fQ?UY@e%b1A>Cu2w8y4N848)= ze>C(Xm}RNzOLtEAFYcN&x=dC+veURVxQl6;L;i$1Qgix+JphBy>k2v`o*1*HwSuUG zo1Y9j-^+U=ZGG7|IY+)|47|W`%yPWbE4AR+d0Hz? zVx6dphVQVVu;+Bvk)gv(&#|An)~!{v#7AKHMVARqS%vV$gyy)W_bb5|HaKzHt)070*Ab zRkMVFdidwX^JU~+PH6hIXVjssc#1dEl^LNtEw?a-?Kj5E6Ro?|H49rBni8|xH}Sbr zPUD2Gh;+u&{?$We?bprI#q=}mfA_FKutqWiw7Ob_xHv^Wpp@8&d|#~rrbrVm{6w2` zank1x(zU}+e+(wXA)Sh8GO{eP*lUq-OJNIy8E+6V4q?BaYgYc*Aw zak@!Auq@!KkH_1E?^IpdwlM|cC%<1=(P237kMU>Nf=ut1?v#8LWot3+fBU#Ak7eyD zxjkkzaIx|>p&GC2_RjYG;voX#X3Cus=kGJ*rpPE*Ti|6E(o$hsba+bj&$h*;uVxHQ zmQi$Wn<9rLU2wfHAFmL?wbXdGBlT|EFs#?5xrE+@mJ)0rrvBidzVDED??nLf7<*^a z8TR9MJLWeqlkvhOZ-dx9e@k61@*t7=f}^Mnl3!;Pr)kqDnGjBi*o&L1fq#pOY`{t! zt{*&CN;v}$x$tyUz7dkEuCV@ca;l0;)GAMdz#ma~-fMwz1XJAb@hxQeF3zN$yn-Q7 z@t7#A8(!B@UzX)H{uafvzU-f7I#&qRE&9w!^2mcS@eGbpEOz)%e+xnT&s~lIW5Hv` z-vU{o4twRH(zbG9T zI!WE_257NOMZ_owi&b!x;k}!V??1I<@$74rNN?Xq;dfl(`4!iqnA6Q}Ll8eseUN$O zZBW)Ca1PR^bvjAoQaY7dsJ%}HmbINm7P|2JOep4g1V@|ge}vw57f03_`)Z`GJP-?f zjvso758Fu@UQO=GW+@}S77`T2UVnpegVEuSut#kgTPw<<=?_YC|d- zTCy^l22!V}fBr*%gvM`I7TOziQl5&Kyr@ps+1jV|qlvokwQCwkTgPttS zu$V^7TIUfJPdz)4JMSeyZ-R=^g@N>pq|iV`Q;4Nse`4k1`OzGnt0dQa-4)zb3x)h# zwcUuYQP4E41dfDOwuaoK5+hm~m8QGCzz+$>O(S=Qg`Zz)=%X$=i{@Y@M};+wJa|oI z)h#aw;$B*GN$_ly1Hzi8@<9!C6B-1&=GU0-dK)L%=55RgO(cev4!gGqG{3YE&YbHt z9kmGof9;b#42Bbt`L!rIFmqeA-ws}-jOlBg=V#kg0smyzLSq+&1P;It{LzRi<+v;d z#CX@z(lALrs4Ye6P)i&UIJeex&yj&Y8}sEu8;_Jnpxgu11%e{_Ej?c}IY8YY0_F*|#oZ8a$-skxVR7XTE~6%%%!iM)Zf_0jLcWSaBd2l;!ZR1bgGLCPhC6X*!(y`1+DVzJs|&2c zlUNv&wPesMeHCr{OfdFds0dypjH|sFarJv}Cfwz?+Q}EX3f}CgN;-nf9(#~2s5zI) zN2}Q|9->tO9T896L-`E`cn2~EsaALUe*_$z1y_<4=M%!volgM1Z@-P(>axj`jmobo zIiXFYi8y19a0X?1V{GqMUbYc)svyA6a_XH>aQO74!>(ex__e#!%&E49lJCq+G1B7F zw;eYN&rLVbqDr(;nb8qij*BTK0W)Ni@6LwDnEk4n7CNazC+g!3=8IV@pGQ56e;;~- zHN!nDnkK)hvgMb-H2;_zIKs(_mV8%P|KW(^yZp`<1;b>UUh}@Q^B zC##3VSqV|t6c(!Xah|GQ>{xObWcWi-r+(`YKj>3^`3{P~v4mKfH+S&;TBs_v#$1Ig zt@Rf7jw~I-CXX%UTUWBE9z=-!#n8U69QbwI_G5-Tfarxl#Gc89;SuW8e^zWA0K>Cx zYfgnBNC!jd#^uwW^U@-}*PX+uFX4GA&aPX5&r&Yc{**ZO3-1$317&Z@Dy4A;Qg--& z7)2FKll>X&lWVdr$@bE z=|8?fr0kBSiytT%Q&?0`QZ^T9$a=BGub_wG=$F$G93W#+D1mh8e|mCL>HVS+5l>X} zTDf}rmgR;?_g8f9%-~-%34{(u(+_a5b?{!^@JOUtJ{4HRT;n|i4I3KTael!g*#!v0 zvUseAz5`yOzphMg9QTo3+YT+V$L+~?jq`rq%5_fJVv2iY&^tREW z3~5eg2wzPVWu}2VHN>~RsLT9_`Y1RHIAHLeNA$d`r0lF>_Zv)B=9gm=-6$3fkKn9s z%ld`{kU!sp`E$vcw|l!x?N~a+_{IX6K?3tMV+M>Y4rZ;;f4vr+dZAa-%$Mi{+Gq5X z$hMs&a-;Ic0b0mjgCj;hdb?gjTeSduuYZT@3=o*Nj>RMHt~bkk3c?ucvKqmTTE%IgA!{c*%m zvb&uCD-_tOfBbNRaG7LTSDTO-5%Wof^`rC^KxMF5GgNwPR5=YJEn3kkq)jxxspxt! z7s(5YwuFh)@Vd6L#ZArqxHy;Mn z;HE283M&_J?<@N@Hks6ybfs98ha7;rvhPar%hK|9g4>ynatHcHvhu#roj)MgHC094 zy{=e>iz!uG3J{`t=)%tujbE-W?Mw~r+bmgAQ#>*3prBDowz=^%B^y3+<1qkN2R`|F z90k1;f4;1=D0@)y;sO#bbT64i0R8gQE)$pg;@2!pMO&*R-0yJ`mun@d7!!Z&P9|*A zB5amZA!>~fJ_wsEPW5m(|2vMPgrZ#c3K}Mz=qHQig!b$YIW2BcPNl;1)z3F-Hzpxj zWN?i1^Ame|o{>>`w%e_eLe7jlW{0RDr_AFMe^V9oLjFaV%K57J=)Sx^Yf-(GKF>YK zNY#Jf{!)GGI@WCS=4W>0Z%@X>gksHhc!eTa^EOnoSVekx$o-FqJCaa<3V0ju3`-uwrt7oa#;AN zf6u_-0yC@xtLB6elyV$G6r!2T83{>)U)*T%gbd!NEasmqCAb0nIX1MS!SIS}RNHpr z!pn6kvs0yV3K}_f=%u<7rQ1yjgbc$F_k{Cwl)y7NO{Nj__1FP#(@`$=pwWdYxj`xW zYS(*`ovq6qSu`e2|DS7Aw{h;$uJh49NpNbEY<`MrbJY~~vV5d-(B*Mwp~FES-@1(0 zi5`VYO`D!1iQlW74EHy`)=PCGn?x;Eg&{}16aU^JHj>;V%3 zIX0I-xB(THU2y^q95XXH3NK7$ZfA68GaxVuFHB`_XLM*FF*PwcF_XdVCx5NCb9kj+ zvnCun9lO)nv8|46+v#Y>wr$(CosQkHZFX!Mli&N!nKReP}IiSk(QB;ffFEWW@X^yplD+yYr`Q;s|Yl4l5o_w1bktvaHOO{ z_CS3{GaGAReMcZCKn-XF5Pt?50+^Tpj2s*saHIes8(TMfGZRxs0ELR88YML~&3{_{ z*#a(j8{@B?MmB~{|CIDE z?2G0Lb<{Vrb^tg6U4I?_iDdu;7@0ZPTI#!f#r`6*wKw}$8cq&o)+Ya%0S&+&Xrga# zWC?U|_@epZ{^xZ5vrfSOR=vKht)<()ylwuq>wo27=I8*lG^T@NWcrF}==c@e#LOCw z{-1u4ur{^RWv^z`y4V;A_z6TLZpk z4L}<3&#wnZ> z{Wk=(Hu|qMeChVD3h0$p6y%i@sQ(Ys_FtRjzq-Ov+07OR_@9x~WNeK7*Ww>4K|vc= zfCnuj8wY@viJjr=GJai04ki|_|DUk`B4Yf{wT!-_y?>c2K#PHnfq@b5_5UBg|6J+( z7a9?3LmQ)i`bf!9-`eP__5PRPAK1{z-u_GRe@%n0%Ku~iuS);~x&jU1Ru*jxxdP2o zGtwMuv2q5-g|+&67{LdFY)cxH3-f)eZMuC@L$^69^xkTM=o%+EKU&=uPHf-zB&qg? zdoV4@yML2`7kS^kh$(yXQ8vih*{S#a>2*sG(@xbQJuc^^w;(jx7*zLn#uXHGi{GH| zC)=6rVJ;sjeTkj(ebGrCY`=LMrqst^bRai^pwy_w*C3C5|=>zPUo)>*KmdV)&l4NiC_8-s!CF zd*85}jOZy!Pr;miCgFOcpR1;?&SKikCAvzXxQ3qruk;}3r11O52Nyj)FKfwhd@ygi zJAaCxre3PIp~zZf#+(vo_9=sQ`6JmB!*+0~_?M1L14 z%Wa>X^oq2ceYXNaF)PK?Dr}h&X z_IR3cZa}5!<<9CnJx8KkQ9^h95zQx7;69hvZ5!Schp+Qg6BroYp{yl>(ikDeGdeb z9}4#`Up_M8)2w4rbFP%yjei(EdjOOxJfj;=zj`>YB$gZw)^*}xSw1X{yKza_V;II-U@hxYb$C{B1uicn(@d5^jnp_-xIx%?E13f9)FAO8mY0ep%8}> ztfePHk237|I%!u5qvdSY--RPdXlVPIbYoERas#5Dlc~@RS~N5WOn0c{B)uBt-vwhN z%4WL8A~nkHocTzNON!8ndkGZ1GvsqTqNi_#?L<(c+isefQz_C1@aG>(VXimW%X6de z?!Akpq=+2c{Em8c?tfMV0M!=Ff|AaSv4N|F`)SS)tw;D)x*&L1rOP5`L*Sn<3iCzG zMUp{gCeobce@07Lgqa?`IoCt4(a}ojEfxHA>$XQvONHccv^v$x*Sg29!)&oE zeOD=}39Sk`pwg;W4enRx)`)~>$S9dG5o3Iy+ToQ~IG}ZunSZ*&7AWT~y!3^XN=Rd` z%y##TIOs@q3^=^yL(70nb&o?H$A{o;K{O01=E;zH)4mOI#H@F9J8Z3efVr=Yzm%$) zW}p^+`lV2}hZTkQA~i5S3b&)#Tt_pF(^%u=uYus0y5CWJ`LHFDf7I?TM+Y7oR8BI~ z1w~W)J}eta#ecfj`JTjo_l*PlcNuVr)G2oOWh13Lh`*8B$2C2H%`<4{A&M+buQgmC zjsS1L(8&gi6aQhHaAh~QL8U%EVxx$YRKMO>G^YcY7dFsAEsbAe4v7N5KiYmZK!XX%16%vzp_&2J@-EY`(prl1ESy%)a)3thme| zj@W~0T7a<#BuMPxT^eL;oq9=MfaiEymvK0)S&*9)mwyZk_oykmbYHRKQ_GGs?be

DS!euujM@jU>6l({82fTC@(m@?+dp7pw76}s=St(VOS>?!M#M}Nh4#6A%oKcU0yWR+m>k}a56)aAUJ9jJZ; z>{A^NZcin(Z^&KCx>-)fj-}(IHkrv(pedrqKBtI%;v1#z1=dd{pkG+@LZxWxmktt+ zocCBK92ey^Sbz-zAs22Q5IPWpxRCNRWz^{^k6$#JH;r1q&4XPV9uow95+9#3ihrb+ z>mYRyAvpRwO+hwxNnvfQ2-9Kw%q#~>3<)v_pUNKHsIsp=HFbc=w`Fx(W{vg&3EVmM zG$y8Pa#DPKq!AoD%Pd~32n;Q8^_+ogPiOONi#(^Us)tuP!*cg;AoE#dg~|_A%~Web zelc(Qb#5+m;H_O7+>Mh^(HJRX|9@*NP;rCx2WM{*Xz=!$bK{~>LuQj6bhqb_jpws* zRtXqrswTzbHzF?{koReJ|DJMAj9yP$`idDotbwsDc~z8T}FLx0bFzwnnu z=^H)OP0LzbIf7k$vKgz~_%Rg?iau8&q%hw3GB*d7@yTryb$Be=Tv(M3vP}1#!V1}o zryfy@ikh9k6Kg3rqAWR%SI}_2+esCr1E{+^7`#%?b|g%hsFC}!(@;F(!0m7vVHgV1 zVDSw@lrG`Q(lwN+oQGh#Wq(Y?f0fyY9(e3c^>&4Y)l1bT;uynsz!z<6K}i2}X9bOa^2;hoE*^h?^X=^dz3(_O z{LMsvHu=-@{FHggMfNVdS`Mn*+nT6p5^WQwnow?DJk_$*1q?<-eSecQ=G0raa63lf zp1?tUO3JPJR4J={yGQx6b5Y(SdRt?cdGn(?4(c#wc+IS4i~JfiSb^-sczz9jrgt8R1|zkuvcU{RhpDwc zL$v#f2MYjX4Nsip^Cjfw>jAK%GYUe4#Ux)*vV6Z_siKQpjjHP@$%tNx28EqiYFMV@ z4-UpIR%^p_sV{DZ1?pVhl$%Zm2|z5NOLizPV}co&~ol(iZNJMAs-7n zLiy7>hdRvyA$GMEFgw>I_-}Waew7~X>jVk4dJWivZq2!CH>b3+6BF26rLUIT18|yB@zbRjNX*9 zhQ2JD7P*`mr|G1|7~yS!Yfli4n^{>4bEu*jnd9bF@0|K~^v?{uo z&jO@g&M+)umjodOw^oV8IU*&UzG*U+j`|m>PM?+oWenCg>N9sgXRC;aSRL$6xZ-Sw zhp|o*6=Qw5C+ul$AnyvMqw?2|g|b`r;tzdfmFQAlGZjIy^FhBKC^1ElZ8kB!OG})q z%SQK&fiEYea8$EkNYoHEVtYH4DOV((vqKniRx|=9hLoeLn%Y!#Tt%z+Ig; z=wk6lf++flKpsc&m%ayz#0#Uy)ZNbBNi%#fPx~3lSvhLDvy6!`nAwPAMd+;S_<+Ps zyDqHe8VGt2ze$}M`O4?i37M8)R~TMT9R{mSqcEf_&JEv}L@1)&;!xZjg-{^sj?2nZ z;=i~=R?;QB=Ktol$Mob?;1Qm58^N6UT+0gyyn;viiL0NJXo4oCNgizlgM4sJ6k5$F ztvrH`sJfNmC-R*(IRn})(<`E3!vNx(v&3dCcA$VCkRWa9>W4&-+qQ8g<*QyD;gAyO zUwXMweuEmMDZPsCyXm+=uDokLUZLAVvD|{7IkKy#jU5k*Z)ykL>^GD}z(Vez-_v9X zcB(7RCG8@U`h&CrQfyFnOYUDjJPwAqJS|-+|XCKesIXQ7EE55838S z?v`kLpamcmG@l#+6?9H|g*xP3bxF|I%D0J&P}?#_qgq!fD`cqevpiHIT$f27o!WHn z-vpu&M{c(5RQ2t;>Uo4i0ssW&EM^H-Gf>xCU=vjVS#^OtbO7)z=_O&nfvIBtT2uh?HA^ubq-rn3+2yPLrM@q_2?T5N@@B#;7i zzN_ZSJ4d<<&OhZvB+5&*!j^(h$8yqA9`ND!q39BwgmZqGH7Ao2w*W7Vf-O#eP@r7C z541~r$zN-KHR~ywnJKgW5Cr&)+?b;Tt5@$-zF=wb9hE3EN%aU76}aQi+f-(E-`L%5 zlhMjXhBQ?Tgg>X4qS#I4=U!u_a9^{zma%2iy26OcebT}TO{d&HA+ixMNIhK>u4UPqFp6y?lf#GpmU`a2 zeiDnK&Eq3`M!oZ+$C{a`91~J>REl05!;DD6WV1E~+4Tn!_3ktEw(#zO^zW3XcYflY z75ksP8`@udm?qK>`&F!R#<-C{cJ$o0u7I@$_n?MfP{{Qr#{!B$kd4>)eg}J67G>zd zXCrzTn(vg^>(upJCFxTt4l?YN@#Ip8Ip#`%L>;w9g%@cGqp>cDRM90ncnf zkD}3AQ{fN5$*uiFJyu2VXc2iSHHzyI@I@<8cwf|cBD+$Mx9Pp2a@>(uX02c&XtZ1d zxSrr06MFA`-va1i4$cI(TK^$(PT+Q2jlTg?A(Yn`JNQSTZA%rPF4YTJDkAOYHnuo; z*nB8MEg-plk!!dv!f}D<8$*Oe)6jxfxh#6wCnd{qX*L~Af6E-?6iYiWJ}@YF&CvQz z$RnBRx3v$5IP{<6r5pws^l*sAYx8dh#VKifB~W$B|j<>Xt@&KW)It}*g0SE z#h-+3{`je9Y=|u~69u0wFboRFxYm75dIf`ab5@@UjUEN7;2Bztc}l(WkA<&k#dnXN z%OlFRi(*txWLB&;&W*I(*oAsYQvh+wDjfZJZV>t-mv~*+ptjppEOO6NUCvP@10$rA zzC;xqP{7~)OHTRFNZAu)c|^HM_ENxF6rM4Gcj0B0-O0{k7r8;RnEE_xh#Xjghw4X< z4;{utK_}39WY;#*F(${*Pm1@qL9yM;;2cKR!0Xp}R3ny0GBqpBBp3K0q51^A8^SODEvvh*L{%z+@-+DjF5<=EpuL`ban zc&~gs2~hTN7>e(jLf!#G;J>ONxkhZ?5L7Q48Yt5#w>@|ab`EwOuSU$n#O;Ak&j@$&+VH0rLRsDv5OWkIl(XS znE^oyKtxFv5JC#yeuJ&}A_VodN5di1;-p(?GtowZ0W~tgCG46aM!oPj0g?cmHF|3& z2qdYJek~N|nMfe~3JuHIx?h>#ZRj)o!bw%kX>{QpRfB+g^|#QmF4i0oG|k+ zDd*XJni&VY=JQlWPDY4A2v0@Kb6EYqkANm>bE_0K7{+1MnFKLueg^2n*W?18@4nag z7YDn@#)x3Mxr{7-sTA*!tes0Ofdfcz3*RP@^`Qb)La1iKJ1wLJt6rnrE$$G+ocldz zlk-CCgf=i-V6IO(tD^SH*i7OV9Zdy5JY#h4SZ#U3Qi}GgV2F`kg$H&Lj{dIZzkJ!q z6p&IcN=|iByhbX}ySSZQ_@GXZUP~Dm<)!7SuplhF2s_4&#_#)|@(>xg0G*1qS21}k z5+&Kt)vptC6HYkJp3uHUn94uIA0Ng;XI`ay{13*HC)1nUL1KIzV!ua4x|d^|61db0 z(pQ+RqAW{>o7Rc{BDCwnIWFo!k^su$m3P^=c!Ba;;FB>xh}@*MxpJ;|F=&awxFrLv z?1rgT2(t9M+n0qc>_b*(QK{W)#%1k@ku|cUTyMoHSC>QfgV*-_)%V_RrjPVFW=s)K zZE+XJ!O;32maxX*r|-99Z#0IhQ~@6llBLW17{esROc=KcxVBrH;Z!z(CxD^?FIQm3 z^F2-ZhC$y066?zN~27{j*>^cfJ<&3Acj1E^W`Q_&60t1L&pLHd}6U z#n+51$i}qW(th#-s-_E6IpzZ7yL+K>i4I8zWIrylnD^wk#ZjmuLx50}lyeTF#R#EZ z=YC2OxTebaQ@ij^l(dN&B1b7@U^giw5v$o0ck^`WbDo0u^R@Ge?h^Wn(s=*pqGhv+ zdMz!MH(tsK``@C}1~oJlRlK|9b#9v&W5>kqLrqcUVnSgX=~-J!Tg7^^mDJ9Q`oub# zd&Mbef0@xYu$W!)2LTLAZ+>_~Qm5cjS=fD}_<0B=v3N7cGIu5ZRyMN;a--ppo5C^) z$m?b@Y?<^jOQ=MZCenz^Be1-~{D+@+CltItls)=#g>@8}5cu&rGBzR)wF*?!16#53 zT7rr}%{*VRd_JLVE3es9kZS~OEadQfD6CPRsn7Y|*H8;++kkBt^BXKY2p8(oJ;m@% z?%0>#4=$B>-6xmN=4*ny%~q3+lIp1<997i^0w|*7_CJQ}9NT($J~{HRC6f9jOFoie+Rh92!d$lf`P@6n;;bIoagl z+P2T}6MVwC$`li-y)20b;w4eAQ%CoSvEO~ap!VMYeFONs5Q)s&Nlj76D69)SBqwEwCFJQ|YC#59)O8WdEl`Q~(o@e?49Ap;`^*V3^7S3vYgm1DddQ{CG2`vjkPf}+-?42gL9+x7a)MP0w+IYC@!ML5 zE0juys(^M{Z*8Da(7lWA9?RK7uJ!ppR`wC9`$hGgOj7&>%nT_)gOrINw11FV&VspR z^1SIhvGwF+4K;B!#sK(p+PeeUs|?1P&diCvbx}>Dr^ZIj?pSqbh#1N=f;S}mlpHll zQ@pZU^a48p>rDAqMqSchYx1uVBY&+baVn=@83E`V@(6pFL9v536B3H@t`lDx?~%FT{z9zBG} zuST6vwAImbBk-fj(aMzFPj<1t#n@t&L5e?h(I@KMl5FV0+s0I%C`DZ@YCMJXp93m6 zfY|JW)~Gx?Anl=*|CAIohu=7-?b>7B!JI9Z!K$(G*F9^+mklx9RQDyi0s&@Wt#zaBP@VxZ36ZK zJCvtC?3oiwK#R56`eljl}ZHkIHjDs3@A2q4L(1Av+vO4F6z1U6GI5hST z6Nvdkv}$f85?OHwjdBwsgm-ys%ksaO5a?1GWLg zC#} zY|y28-wZGLr*@PoVz`QS!w6VN3J=zNzTV-yF26mw6T6o`yTsrjasWFXW538cBOLDt z8Ip_?WF>qlbEiB%z1FgdjZtKHDJ}m@$8d?}SiOKA!-_Imp2qTZE+yS%aw0h!i3owX z2r0oX>wwM?uy$pL;saS?aEhx5eVO@iVsH-+J8_zRg4T|wD|mMdgSH*96oR+IPc0MzfdeJSEhUpaCKdqX``Np%Z)Ym9{E`o>}yHkF1pQZu27GPsd3HDAzUPQ zN5Nbjc@cBnUecnVlHS25;2m+4rPr)xPljShPK|ibDo*D%)HkY;F>he380{yszFsP% z3N0E|VMXOF_1EK0Fzb{PShY?FDvxuBkELYR#VvuKO_2N_NdZG=_AI1*0)*S!a6<|CTr3!F|>(o0E-j<(#p()0#`-45N$fdA5X|(Kwk)<{1 zB=3q0T??NHbpoFM#=)Ao?o}vR3)HR!Y18X~chjkEksdhJ(cePZyMKIMwG8T~dyp~~ zo7Cwg$LzpDdh+_Xi>~SfTUoS?j|7 zaY`AXtJ#LKnM zP3dD=F#*u4yD61&9MVmj@hA_4gm^udX0|=MnEy<<{R*6mTP8~iX|a6dW^spp*tCS6Qd}njI+p z=;85Q6$m#GBLWL|G)sZARUP{<$HFeO-t{yRNCD`#7*DO3<%J6}dE6zQQEPEUcnGET zAfI7;D{i-lg~&tko?zwtnmU8uCvJ))l4fxBPC%RMTvB{!#FE|9YwtNSst2oUUqOI^ zVPgRtUHKmJ<4eL1#pe#AM<%%<@jMa@X`gnrbCDdrMKH8)INmy>F)pD^jOdb;Ut_1$ z=>m$z*=e4G7$3}=`SULf&sj1U@2!Kj#fOmm-4$C&SQ;9J3+jZzsZoLuZSX_&TucogRl(+Z4@%=KpX5K%8}=paTo72_x#(3bez_<5@%8yZ~uK#Pl{6Z%)z(B)HHJzqDv;3A>OBsI6;`-KU02O0VQN^feMo&r4*Q|?% zpLW6GR;^InI5=86WZvtbEna!!)Z=*(6xOm*M3@#u?M2m!;)HBGa>VFV`X;G}7f^Rp zAS4&wt;zeR+9QJMNRXeIU{Ysat*k<-D&VZIDrDVesEkk07H?T^kD}ijWPNOgKeW}qm1FZsPxQhaq92!Q1Bb#8$Eq4tDUL7s;8R;jrSWC8ipeodeZ5NvQDxN z)c0li%fEJTOTC4w;fj9Sga9{;7RjjEwt!=4LNMk&3mMU$% zmZ82XVp>2Kh`~ZWYTlnQv;WS_hJP5^g;k2&Ys7-=RTBJ1ki*2nsvA-mphH#bz3e-u z%RI%1AaKFcdjuUv3p&6*KB{Jhjgq3n?T_ZymC*=f3J|6AjowACogw~o*;&UIuoTub zO@`67pHh-G7*#jb+S7+mHNvS#w9OyO-&V=Ft7!)Fe4pB$Db^^A1I+STT@{s3wYJ>q zvu41P2*d2*wjNSDxm*s>sD`i`T}5Bf(_WXh=cKoVefWH9yt!E97NXe+j@#VF9XU>Q5Tsv@0 zzq@Anwfli!!||7ftbb{u4keB!ivLx4Aq<=~@5}>%Al*UT`-5#XOW$WNXzIS}c|q*- zx`+{$Ea&;zVa{S=4xbz$DznoMF^4(w`bI5sxzh{BrzW_80_ajiS73LYPW%Y;RIFNb z!VEf&x%Rol9+N#gkwO5rRQt2Fh|gk2%1g$%7I0vdjGoS$E!Gy9$P0RiCzQpgx^hg9 z%RFNilsYLwo7?a=x06Y8v#y$EdpGaU7EQZQobEg%*;uh1pX(~k4om`G`qrALA^wJ5 ze}LEX26^3h5>Vg7#ZE1tAf1lssz}(%Ra7f0W2bsXOgXKYJ29vsHEA8s!IATi2vlN?zy{6 zqWe!COQI#6{>U~ypSY4(WZyPpJH=CYajE_Qzg0}r{1(yfq$8GKT@l{pOwmO^NwmFM z2)b5CA0R0rojI$ST>Vf6xN&p2Sx|7S{EW6$%Pr@S$r;IKIQ<5z$KZY)8;^c$T@qcV{i23n*Q( zsc($q>k*I7)~F%%2&XR~K)2r%6;d&C1gOv>2GmT!WPr`~9}=ZVhr_;x@!$=736#Cc zNI>h3wyZ22>mFnglhjb=&$DLLaTc`(xVMns+b z_t*Qe4MM=tnSBD~%d&zQdyt^M6WB?LP4>uN!`=NQNrvAcq}y(w5;-;1X=)*5pM)xR za~H47QD-?G@~4mMj~$ry0iQ}}LWE+!GywexWI7nfcMoYW#vRdfIFoN&t8gn8BH!YW z>JMi%1D9+5I>~HQPqYxoE}4WQ3Vx#Q^alDAEXCB|hqWVIIdho=Z)n(Zs*C@85GTPF zI5d8})Qufe2DjoggEE71jA%AAOBJ*S=&i_Oa4J$lH&TpaUce9vHx~~rFNq-|m;qo7 z;qwaKFCik7Zx*l6NEC4?kK%(?^bEOCXdcxXcL#mBWdXygUFC`bK}akcQUgK@tA#CN z6Eh{uy6t%l8SNv|nKOKs^A6dg;3PxDZog=Xo6-^o$DFg%fVEG6B5Y}di0#|o)$)&E z4aI3iH{7}Fg=Dn}pKO9no z0}wb2!hK<48r9XreX^R{8X4J2OC8p`CPI{_mN~8nj@S&9WN32se8YRzoKga1Ekr78 z&kwE0%5kU`6^>wbZ*#o}?N?Yf$F&xgfj>*+h~nSI0`I_nojOMXp z5x?6Q-`aDBoGy2eKIE!=2Na+>{>nZK(fiZ<>S&Nt@km2`vn=NGS>*ckFjS4oy1&vTK^rCBZ=sjdau9(oN_4T%6UiVLaK zRFb641<5%47li89i6f@eRRN%D8TfamRhULQ^EvQoS~nH3ov>apb$zvU7MRE2j*40^ zo4Mh5I{AIYmOG2htq`Qi0F%pubK8Gvv(%P*o?u&MHT9)sOpR^Qx7%XmhM|JFhhs-TNQvp7ge61_I%s!|D_lgyP-3rYu;ER39UVRkiEPBIlDP~NAS=A}kI&5#w6p$no`PeaoZredmL6I!<1?$BnY4agQN>3&2 z2*nzIQ?$%Bv(E>mgaJSU%98F)3~iq!g4UkZkKLKpy))~c@871*n{0OtjsWy7D5*uy3Za<|naWxC?<1qZZjr z!Oru4T31UzcdRRZYk3?0k~-h;OLLl26;Au*b5MX**&I_62Lo{O*RooWFLsX}r7_rT zCzkwuc1`z(#2@cTr;Qj0j~a6M48e1s4nc?Xr&6+#?P`! z<$b~K@6a!3o>2gvA~J2Lt%>KOPu;|_YdQnYt36Uic&k}}d<_Zrc|;T|qfb3IE96$l zj-+zd{_ia=Zh)w29yXfLykfdHKfd;DlCPUASAliy$8doW7MyRICnCT3OH%%@PMTOY z6f0G&*|4&CWkRifldmRQD|F%+Chjd%q#IbO)goY-0--(q_=cAR?h0*PcOO0%m!mhfH)k4g$lLXldET*1Lnx8vpWDO>|5!ZB$B(?<|ws_F^f)uKDxbEZJFn*9By$k2i$7^%Ee zz6OB(9w{6azA&{uIB&XDi;71MGR94Rj|T0cuHErze|WVZax-8G(BX-&3&PNnacZ_mCW9k(vVU9aZvI?>Brmqd1UmVM6m;2 zC($|*ySt7imJn)Rpyy?x0$nP_rn2UrN(gQ*cov(qr zg&zCe^Y?rhR%n?NZ=Z*464I3jSmDdmjd{3#^>Q>|9gdIC%vQ81Y`PW+#+Xd`{PAzi zg9P0gr=lef_&TK)U4=+0xNXpp8g_T&2YD{iiOk<8el*xa>mjaCIr#&sB2|C|I54`e z^4%G6o;CAi6ehSg&H|TCbh|0TZfw7~3eP+rOv-?~9|?`<6|wXw6sH*?I};h-Rxla4 znH)(I1}tm?T0t%1>TW!tnmj8?ao{ba=L5WfNH;(&jH!ZDYpu#@+yLvN9g2^X%cR$I z!%P)vN{G82Y~6^y)x6U@(*}S=;!}4*g?;$DoHbQx*(`|*!(N~>;@(xF$9M{3Mgh$+ z3%`NXMoz+>NIEo5?d2)Czx(M~%;0VYv&7V!=nE!+$R33EwustEd|jX0xwrH8$Wt{I zveu874LIo|W%NZE6h!*(Nl5@nbUlQD+36E+P82=l1fyn^uBT<69vdK{UHH0`FF7o55H9nB;P|D1LKW2@W1L0|P$9Ee#4#NjVSqHQuNI*Z>he|NN* zWDTwwei0P8f_d(3V4@Ouz91n6JZ$;ab18}uAhB!SaEj@@wFgSj74MV|M>_Retxbu9 zVG2CX{uMBN$=TRO>Zt^LN{}BS6f-ipt9Y9~5#@CidChO#H*#=z>UPhFaY&sw(d6VX zz}TeKYNa)BQjkI8f`vWAyW_sB;ycmaIhz*g?EJ%GOl2-5dG|B zOnV^=TCIx{n?&iUh5X?cv#JGGDllV096 z^{R}Ql9$-(@iOssD-7>y&b>?F3XQW z@v!W0x%%jrpDzIsqETL~Zx0e4xQO({Zkh+KQx8*WZw<~Q-1ul^$^`j*@K~KkzBp10 zt$vM8mOD(HPT<5)P{*(Hh(RI`qT_OKUL&CB9RYsx>DJSJk#P@9%<)XH%DKPR`ts_G zSx9naUDV)M*_4A`L&5hoP+pKluGe6W zyAm{rJI+v%d932$5^zrwfxbVHV2aG=wK7|>IYog`T5?L|_-L<#*JaJF>Xp#IA9K@9 z7^5b`J7+(MX|siry8en^ubYt?<<(ZQI!mcW5dhUKcEvw>G9BsY#Hqr7rq9F>-3%3t zu6WW6fQtaeP+Fmd4{I9Dc^OD)-`y}9N}!RsPe)t^l3<#0t@3vTijV1(9fl6P3qAWg zA`~ia_&nQSU15>{zX@5Z2eBCOxE6`IvniPrQsmn`KP6g4C%TP*{@%GE5TBn6Z;u9g z$o-m20A{F(855z^G>A!zbg9&@*S6piV|GyF4~qjRn7ns>;g>4M2PgyAZuSv$wz4(x z7)nM-fLkYRX87FBg;M`(LbZ0e#Oz;3*fLx$9arlo6Ld}(O34!a@5qyhUP6V7H6+S>d?%T5lr@wPHvg%t^gxfYZoDNNkEw)hQ9QU?Gzt|ZV9}*h> zxb5=X*1L(M?eGe_2&uDh^OhkFr5eKUo&u$|U-R!+Rp6TUg5+n;EDoavpjmHN(*PLPa?Z9F#pK5Ny}#*q03h?$Pe{=CE*?-Bv_b^O0rM19lt#BE_$Xp3=XGa4U+o%FM%9P=iB z+Z$VD`QNGgy5(Dh9n+IK`ARZ8Tq%cEI40*gS<~pgHlK;`I!Hr4-fU4mzcoP4_u^kV?*w_)R+e zd@(0AY*?NTt)JBF=1R-;Uj^@KN8$plTQS8nS(C4)#D!wftGy?)Iy`pzvE0E!xb}8b z@pDO|^wtpZv|=C78-q%0yM+S`o43nq?f7ZD23bN7*IDE>rlbdmNME8&2lkN%{^~A< zoIdW!F#IIw4-d))#^G$U#BdPjFC984YZNCpJm>}I7EP2_PoH{c+G~8H`guAm-sra< zmBmio7wL_KqRXnBvNVreN?;F@$<9|)5lZ-t0RKq;;Q^CjQD!x!0QLgt{+@vBY9J}N zq#ktN%xWftwfvXuCxtnZ>MgUbU4w!$PTziu_>McdDt_B1?KRBMy(d3qrr60e*kRpb z;g|Vp1MP&?-tIvjC9V*-xF3}Dof7gRPL%yKJORFwVAhpXxy}~>YJwOsS^vAM+KW6jA9l+BS;j8h%yJ zJ>EFsLW_o66|8ij7JfYL#32M$*f)Ug6IxM~t1zD1q3K&E$FBs4{yR*yKj1@%4e$!! z(9pme+&WF0KcSHhBUkgIHnk*>qpVsvWx8LR0qQ=6PRn4DAT1M#ff#Il=qO0W=t`NB zQf76E1V4A5`KW5#iG0(yXsxDY=xAdB-ov5K-}yJ<{vgB}9BDw>m1)5Crjt_heKSYz zbMFZ)x;j)|&T#;=nLWG3${6Hdq}1G(mSNUJ2~W(Dl6(=uCow)Ym-i#(^nRcjzb`-d z8$l@63<}JQWj|?(gE25Ac1LF?Qzszyu6Gq>5=9#912+*#v(}!F_4{1e#-y1}@sh&U zjkGVO^Rii$U$}^fV-H*K2vesz4@Uu zpZR|M+M#&-5C6+f&rU#3U}tCv#mx;xr|e;GLO>^HXsP6E14SoGz(D^G0v5G!baEzO z=V1L`9+-)RgCh}9l^k%TWo3umiu6^Z*B?s*MYlsoKprQy)xjpC$Q9cnV4pvFpa`4ug6D>qx;TkFRV0LovmOE}@&cfN&dG729`~DXJVlZ0 zFY>bw#V=Ma+f_RYz+uNshlx8uc^5WPh?jTLQ__XH1_F$#Zc1{hLlxF_P{|}F`Qt5VR{U+8Mj3c zFw9kYeEd6zxey@Ie*tm4$OE$l9uSQ42!C%{vhSV!nemGay=T?LJaB}PNW zk_pc;d6A6%q6&*0SmfiEziJ2D^D{`gy;=uZ+$^2>igtHY0+6k@TzXW|Iy3AqE@=i=tp?9F&s-X>0w7CPUUR zjKyY;BcNo2k}nW+5;TK1$b-Wu4l|O6v>enum4Om_hTUyWDyrXAU_xZnhb{++I-3m; zpiV-%tC9rB33KNcmu8Ud^wCWR7IN~ZKu1UvN_fdfFyj>|>!VuEMiNtF1cXKTs^-N8 z?9=zC27<$beL{L!G5G0^MEyKI&>cc2hd@R-q5hJoB~5e-tnJ-iR}<5qFh9ZL#MXf{ zcPO2v?4Vr5C85HlESQzeM$D{$VAHzrX3wNu3j_y5;r~4?+J0OmY%ATJlo=?2NWiw& zb4(}!f{i1*X9~l0kHJEi)|)gdO!OSvX8hhCBRrtHkds=D`M95%z~Y19TLk{bz&Jm1 z{AZSa0RQUHou)G-_Vh=j#rY!i-I?2)`D1W<9#$IRJ#+#?Bls1r5cUMY|D)sV+nzI9 zV1EOEq6sY-hVu?_KNLtukLvF23 zNCo9K92TLCcCACWo4+$qG>tsmo86topnec}&}hMuu`*yH!<0Qks+SO;x?G@=*Q^>f zrjB=zW}nz$-Jj{v zA$o!*esKjm@A(BUL4_^eOncNprN~rTfHKaeso4H zXXe5AuaGl+@0?=Rz@2!MPCaAnK{~;tku!EL{XeBO>KRiH)`>=qoT+>36f;00cjnQ5 zYP1th8aWg9+9@XuUD8OJ(V2`B6Daw`?8&?n4;ndYK46$dQOS8-!sQW;q*Y7F@)VgB zapqfC#C~RO<{3iaWRsSiA zNP~m1WCB|t0)vFH??ej(G^pfFUeUsgzd#6Dz|^FJB0|787DgoKWBUX{v||d#ViYl; z2CEV0ph5#A_XcC`!gd=!=l*OzF zESlwL*n=TrZrD{uVavCm!5ap)}IRND=bRvLI zY@(Cl^xH_dKTc?H3*+4xhIpRviWVD&oP4GSTPRm56*4)N284{#&Q;&I7FsPI_=@T? z0uF3Fe1ks73j%&s&E3;R_itdz=+l<(GL1$2M#3{RL}-^I034#?2cp=hDoR)~G*}42 zQv}Z-isl2x1D+!rZdFZxMkgR?m=_qk_REjFGUd62QK7jqr6iB0mH18avG;2UP6EV) z@pq3uDJ!4g`IkQVb@?9Ba^*5#{S}Bxi+|h;KjbTgPl_dlfe6Wd4nMg+i;$5#aqAAeblj{Fq|QM*xGPq_yL_N*{)n0VmqWPHDX$9Q#(>ze_o*1`@xGj9EaDZ6E(= zV)T!#@|wJABHIu%-HSsU3xX3CAD}M&+0b3FSnDONazn+%qsXYE_}WR>IKvBUiO0)G zcIFM8_qyyy;5+O5JrA&Y1`*_%#Msuae=&yxO!dKt0w-<570k3U4RKMc!hn=5b5+GB zE4i+`j6PCqWp2r#IDfR{KCoPMKbFi~XUYXt`2^m0yY75Dd{sY+th>Km*OZ_Zyyeb` zkmWG{&TLMC2~l1-<6`~V@y;&YVZLYX5b_xe0i3x>7F#Q^RbU3z__f@O${FqRM$5kg zlqBvanA~(k;Ks<&w_-6;V}y#JA0C{$Xj;o<)&7E~6fKaY;qP5M)0kjQbhKo@&-vWf zSEUxQB|$*Y)C9y2lbg8NDwkGnzPzn9zr{~Ce*OuhSCml0Vj62GZ#w(ruNM};JGIgh zGa@*vKwOv$Sn74vWPKtmIOGZ@XMW2B2-lxM@N>pV^tlp5z!-|4AYKzgMc=xGD<;V> zj*GCL8QC*ZXBS>#^kQ@&1fy&r5v(NkLoqOhcYqL0rEqT1aY{V6)Hm~|5)@w|l?~-w ze5ZJzN9klcLxQH)5nnsw{OnlOuJqXnFMO< z5uPc5rcwj)=m+=NBZFA&e;7fIjH!FeOBcK>b--^U5o_n-BtQ$HD|@!-Qlh`gMI+7#CyQB*>;%f z?8+n{(F`_95;raTc611^?B~0WRckcydH0=HMl({>dcx{E_U=c2y1}qz_#Q-0+}qEh zd%O46UGaV!iPF2PqX{5u3#)~lkLZ7D?dYT$B4dM3j zdHkB&Q=1t^zo|td8#r4SjL|9wGQ@DrJ5B2CTc&39>JI_at)K-6C^pI;@=J94ll0f9 z8zx^j9J>1`?m3aVJWge*&EyGTwDI;Rl=rcb4W|{PVTsa2Ka0{yohaPg761CEa{Xs!%C^2DK?M zsj*;(l3Tcg4|oGSe}t|)bq2E)>7hpWCZCs0^3EQ0_ZwE2LZ>uNf=C6 zGh%A!Wr@>hy*5#-tMAKfMiZX$`Q{10~D8ypz}Cv<+OtEIo}xax@y^xRuzS&m7JKh!B@Z*8%I3O&SuN| z8{=4z4MpQ}}M`f~|;eDJ~D##ImL81^LN$ zYZ|a}MZJJS_ev~#>CEMmv>2U#rSVZ9)FYeq zK*426-zspmN&o0PXNck4i)Fs7XHOx+{!`P-)>Pk$hlDH}qBb5Zx{K#b7l)1xblTaB z>;k?VZp=v}$q;FoOkn z(9;ypK(<;vuDDq}a5a@|7KY%NXTTde(CaSVzEr%L!_d6=YzH6sVmbSn|D!cI{=Zt2 zo#p?uCNnGBf3)UMhMwIfE85V`7saD`tNG+lkzWD-%9eAZOk$txMyN=A+NzP*>RnVm zW~l_<*S63Ykz#5=qlZRbwQ1SJ#6WJ1`=~>5O0>E0Y_xNY0xh$q$Ga^SvUg#zC3Vf? z*4$EB%bjzxBn!}rDjSWC&IYTZyT?8#N#e3X%d9vFjSqnSv0q76thK4w-+qJq+yM29 zihNkU4mN>TzOE6)ntas?Y8eGb*y|4qXefVwM1Yo9|2VUxIh1OFf}&zw5ydEfx?x`vW z}OA7dRNa^CE05SknDxGAg8LGbpGJ)V9kF}2w#5#*X zw%82GJKR);crNRxB`~u=wbq0LRW1}+x{t~OUP+P0*`zynI?ifCg(w6O6oi3NH2XKp zo!iquGbn!-hsUxOG>7p~kwQw@Ah28!5@AwZaDJCzo?IE9TwlgT05yg^bU*)-Hzhvd zd=OxTQZtN^F)U9m6>CYnn!=lZttnNAi6ta8egiwMj0_ojUmO~ZhgOU|8#p}MUno{( zWhLA5aea7sRr=xL^z7Zrla-~z+r>3lYo7EkMoa5zrEMXr`|aeW7U2FhRe62AHSlfd z_F}ox^Z9J(^KpB1WZKO0sig=sLd;k5q6YAB1FSwhGHQAj)0K5!yo5fyRQ4#4nbD~o zm}MM~t=()r?S19owP6VU^mMQ5xNU3)tDw z6pl@ooP3(}Cm$`cA)UkddC)Nye}wciAqG>$e72eVVlKQIJ9KX3rl;NDi$Y9aOaV)^ zci|~hs~;!Vo;#mXo>fEWO^$DS=Zp4Fu5BTA>%(n)J;pFJAq?_0cNHTyqA+S)y4m0N z45HnhyW(B@Hq=G~Dlt1MA45hMJjV@zzDx~_z~863ZJLBV?l4qOae-*1?kocs%Q08B z)-Q4mjFCn`3?sMmtg>(q4%^(xN`OqGy(kI&e<>|{T$i3{edJv+YYdvO>6>uAx&Iwy}wCgtqwmBMv#bQBo6`zF&mbzvo*GFKtS%#FCPe`g5GhhbKzb3RiRhQ){n6+5-r4M&xpQac zH@9xi?%lmJZP!eOV`3XbpK`GWTt-VsZdJ5h(_PX?Zs;6}ITqkIQe*MCXdX$k;C6P|IWOpv9EZvt zKgNo7*@*C5E8@nSuLap z-O4&!vULsv3b0jC^V#Vvh6}%@sX`V4~W9bM9pWW z?;7WJ2Ugf6CFz*xNp5r|YUs0?OLcbh>1?GvvmH2P)T`l~mG#sqR%rI2n0~1l>V72_ zZIiCtxLkdvo3tsY>*@TvNz5@;BdY@ou6iADWx=DUpnw}@o00wW%CjFaUj|5918xmV z6sb)FDdZP&Xiv3%CQKrOFX1Z1tCW)-?Yu(Qd+s{^Tq2BJW>9>AQzLDt7PPUn&_7`B z`w|!@4!w?Z$g4~pL;0o&iEQoKDkWby`gP80Xj!jTahg9ta5J3BZq2+Y(i`x5F3)!+ z7cECnw-U)%_;o%mTZ z;sx(;tyLs#0JQI__9Q|e!ZyIE;J&gZ&y2&@w%9&X+qtBR+f3WnwSr+{fC|=lCOD93 zTH)h>Yd~G2)n<`z=4NK&hfTj>HMR+d-qMU0EpZ^NW*_l1PN@Zdv+Xgf#YL@G4}#=G z3#Qy{BWyBzS8|eU5*D|;efNIgt@z6%28(_y?0?zi5lR_8?yw{4DDp1loBE_<9dkHU zcuMt|p>z4}{ioYocG12K@c??BbG5y<#%r(QdB9NHI%!z}a{=PkOqPale&=Jzjdkhg zytRg?t}55T$c?c`_}hpT*K+dt)mZ?}pRA&3wcJ%SO+R`Rp6L{03K$(e;r*i2|TD4%ztG%+q?< zfIWLHlK^d;kbrw5@3Ho6^N8t1*DC1ojFWDQE?hvFm zoZl+sW@q2MPI$FqkY~nC?@O#pX1e*A-Qr?-+Z1$ZouKs`T5^7YdqqoNm;a~thgaI9 z50^GB?rpkbFLF)1dIqGGqZm(dy?0fUH}wAy{w=HNS;J9(>cPN913{6*#Vv`Nu?PG` zX9Yv6ribmf>7}~H^ol24?mP7lWRCG6(zKJuOH4nceibhDms3Idnlkuh8$Ub&wRNjlH>B|vb()u*A-QOANKI zYx5AO6-KtOtm%-I)p?Zv$+yvnn-})nLN7W6{&e%zVu&5)$EZnN@4Qm{h4i|`jn@#~ zZ%6E=hmE}Fsc$hb1Bu6wd~+Ok1#kO*ab4Pf#$V_Evi{NWAB#gfe!|N&gNq4o=~|-q z;uEKB1rc3)9sTKisz+F8v;vcB+BWnvYtBczBd|mc*pE7Y7bwPNb#5xBBL`%jqJaKh zxij?XwnYC7@nL@oo-?VY3ZtEz=#@WGAsXP%Ed1sQ%{(%L6>#G%0x->o&S?~$$>PYN zIhFb83a1zv$-T*44QBRoxug{muQz|5@KoqDNDh%tn=iMV2c5D>=<%-W7b+~)p-s^H zg8BGVh&N6Z8?8l~pz|e1^-*7l$j(F2Aki`b3;aMqC7npN2bFNPlEdv2Ker>wwiZQ} z>>J}(qt{;;TLX~}(Vy_5F?OW)(`BgQe*)Sg#e~rc`#5ZxT@QUvwA2(R!0t9&9$u*- zHF&pU@Z85cJx^6>G8CO%iQSlXKD{BAka5NWKB7rlbTA+nQ#RKj=Kuk8>0c=MIY*P-U#|jL^|kK>N&&m)KqU0@%|>a1nd|96`9r9Y*rQ) zC};J468ZMj!{XIf+uf>Y9U8};+t<@8GDJX*J=d6v6HQEo4^iBxSX45$M00Ti#nmR2 z^)3GPQepV;ck2R&i=Id&OLHf#??eX|x4n1M24kO{y^UC^!`!YpAmGYm#?S%V zo54zi<)UT5MB79&_Z8Z{_<3pYa#}F0oxa%O+nJL_$wvtBOdw20I8D`5B?$9&leUVq zS+WCGWb=r&xt~TO$l>klj!@XP9#e0~eAUNO+zuqB;U#C=h5W!Ap@cF$svO!W9Cb!& zGH5QvfGVdB)`2>tvy3m^JiZU?a<&-P9u@!L`ue6^cqKFY0z9M6Fw90zyA6ol+~{lP1#JvI)2W{cb;I{EB`yYwz-1FVeC3R?_Kd>+%S(@HNv` z6UCvTI~(b(sC`M-%=uFDqs+sdbuMXXcRYvJj9b4m)HqGQSO6vqBTna77ix;F@}g=2 z+^c(-Vu#AZkFKDHE*w&pa_I@nJ|V@$D!u8+3o*(Ssjo!ElwmCbzlZH3rHkK`&k$+F zEO`|P8N2dJA@3oRIcL#0cM=}7uOByr&<)1q|W03+Jf&eO{S zZG$CqdxD0!4{4%}0MphzgSLn-JV#-!5zuLQpp{D41& z6x;)k6tv&E4*v>AgDjzxn}YjCL+X(8D8|0OIEsfqn-YLH3Q1gb^m0M}(MQzCHaEzG z;?#xAQDSo=bDm@(MMwv_A?p4TQ>uZ2=!qn?|3A7Y#jPk=@xYnkFRT9q5wC}{Q@8O#gU_qWNkSz5R7q9XqJaQ^PZFYF6SRk?BhD2J6Nkc~ zQnHc=DVUg~IO1UT0G}sKC171gA2gWc2r2}2cC+!qc%p5_4WZe=U2Ep{#mfBQ1M?O2K~JibBAX?raGILCJ4OTNWMF*#5>S{(+`iru7jXtiqO? zsdOi==nT_<2@Q2{vkB+!9&5>B(?ij+h{jXBim;T&*13JcG9~9NZso<6ovrXl5jZhJ zt9`d2Em+?8^6Twr_ziP94RuY<%WO$vp+y`#9>RW49JN{fuS~}?rD()fK%xWhPK^s+ zx&<`LQ-8cW#ePe~)irwEp~01PVKq{%a&Bb#bH8YN!s|7AZa9UjsY6tIH_h za6G0!WUeT~KO$=4eK%hk!}?+AoTjdi-TS@+hU_PErwl8#iy|`MF5l*@+K)$6jh}llE_C%sC)QD5}R-}EIM=3^`9)jk(X6_pP1ZhlMAzRqvNGbA# zo19VyTPn!FAnKA(n1&imLldrcK}rpwaY6cmIvlEoP?yz^kx^Fy|5N9`RY*X8?=1j^ z%0QB+j|c$*sc)REG`J%i^poI@nV2AuqG$-Z0EzdB_4C1r-uXAEE#|GZrVpXM#9nl*Nf?LZs(;AEKCi zpOJN0p|!!9Z-lpsI%3mW*+Skzxs{#}g}CVxZ^Mq!%v4{r^`olF(aX(7`yH)%sHiF5 zTF!Fnf~A&x&l*G~bc>@Tb@H;|4VL>`4>lnR^l}6XfPs%scM$7|`VbEN zhrs5;(+-arzUH7*`r-RKj#Y0kDAI=y9f(!e_VYM{Sh0*HVGj^4RLi^>*Gw}NqYw%2 zdkr;F>XvH#SJ3Ma3w8OHwPTN8M7%Y|j1;gzqR&mRLSN97l3wX`jOl2Ss#3$0Fn2W5 zjcCJ%VTVg|vsImK{Afqj`x`q)EUg*!_JF=_w-ck9nJPwR-FSR~BF0XJX(dPOfl%H` zXaL4yH8^6sIqWrr6T{dMiC>G44hv$QZRW3fj$xbul^@~_6DVgkY2qAO>y^6g^h(%_ zmd+-ShQput{6LK=ok5dPxtfKLX_ui2L>FlvlfE*?XtSH}P-qZBH+&)N}9J3{sif+^p5}AN)~kk7URT8Kc{7y6cMq=3llojM1w<2dTtn zj^FD8QuAO8@kwvw*yGFTOt0(OZ{ti zke)(!LNd5rsf2BwfgS@PAb5du26%0PBo(UMy+CDCRg(@ zGx|IoGmx`2txJ-YfB&URjTKKEhq9kt^1HXDFnObJeI*I_nm}(jHFgpOocQEbNLxjH z_$|AS;F&X%mz}<@l%&@4JYv@uya0B`3ufudWS<8ec23Hm`y@Q?vb44`CcQ~@xjU&I@tfwxzj^Ep1J~M&rcBO4#5g z2jkV2=9^)M8Q59Rozm^6VgT4b+za*P`|%PJsI!w&E^1@mG6H9SNL=1LmXhDWA*N@! zwKC;U-%?w}x+XU1HA3TY+l91tINo>W1WZypwZZqkiDOh4&m&ks#*<>63CYHp2A3Lm zqR?Q#_U>v%M1Oj5j~%wXR+ldYDq(xA{e^CXefOKRRL2s@c8Af|V^jdG$0J{>{U?H? z%-UF7x=VLj>Qnh`>SKta4eqs-ObIC#l2dfxo1K&|VpEnTi=jC49`#qXxCtUW@J*7+ z*r7)BCU_^s{V#)n)B-QqJqK@|ESPx%=rfv(1C^N4y0^WucTTUhIX29kHPOr5f#Wk; z%C`C)*Rp3mY6oyv?JtMg+P1gH#@&eA!#v_wR2v1&^<9^G{6)jE_J<`yhDwRA^2@ss zsZV*A7+7-HPEiS$F{p}QXurDMp_k^R)}o&0N(f=iSswvm{HNUAXy&SvLH<T*u-^ z`e%n-slUy3YN@?ou~(t0#EVNJ0=D14uww{A`N#J{?#UIhBdIK{+18rbQeW(0Rr*sJ za6e5=MaH*v=bQ%is<*wXKkxhE7M;fSls|h{PsSKYe670~mY;#;L>2C%iTSK-oT!DQ zSdCQCdOLuaZ*e_HqI@oqk|gFUo%ovH_E3itRY4Z{;{7e9h}+ab?z>0lYz?f~i(lBy z2*ikQCg*bo@H|c@nC6_ZoUlBJFA*6oN?aBlINV2@x)5^9#j}xnKXj&lfwQU}RN|^y zWJ&mMR_(XgEJ-4wu~Z>=iGQ1~u+Nh5-&c4~FB=apKM&F+9STRlppuLN0vZOIjQ`+r4NvLb}+qB5T8v6C&?vdP{fdnc>xO(;cCR%K@Iku60=wiH=e+5T^2 z%eU|E+x7ok*XMe!Jm)^=exLii@B4M`_0UT22{3>dVHmW{pDNoiKorarrWytq92^u( z(iBXBrZT1!Onek{QaUD#nx@)1jGA_uMy6&K0{WJWAbJWeE(~oGtqlU`Z$i2Qqv*E> zz>b~SL`UDm@{f}vb|*hLaA$tjo?o+S>A-B|<#Id&C* zP+eF1z|8R7nYX^*osH$V+03=oEwy>9EKLQ?^|g4-O)V^Ls~hQSsaxusn(&&MSely} z?OzGZytC3@(C%;nK33+NGabF$uE_Te+MV}UiEokoNgUu^i60!eJO8l~-y{<=HIddf zQ#V)FFw&MV*EcoazhRJFp&vbbXD!IFa^EDD0G2VYO&pO@Q3lctNrJ5 zal``91LEHtvNI?2SSfGGVgK$xcjdeF_3m89NmfVS^7mVI%T!DIz!8P+$o0Um-MNpG z>MoJAzOj|j=Bu!uY1ocPj~ctP3hX#}>S|l^np&%y>jUqfu$IMv1$M-EVA$^5$4PH5 zk&K<0_JP^qJ2E^paA$t_agy91+me=qxv7r6k+!I*uBg7DwvoP`sj1ffM}hAM_;{+_ zm5-A{o#?jD;y{N4LT!JKngLl?J z{D+gUO)6z-b8v;dqTf4gckcfn>un-wOY=j<6tP#-`v>mM{~shRYofpT3Idv&*VNox z`>2L#bX}4eatb2w32a4Slk2?kW7Q!a_mimA}2du^Z zML^6u;@>xFXJQcZadJ1>eBu8Hr9jL(qCYfp&kDy$-&kASL=#!* zpvZQi*Vfm&a~+GW%(nLL&%y%l22%Ei>~y$oeSYyCbVZBloOuoTT>A2^_o_ zfOb*V!GXK;AB(R5xTN)G;11c5aL@KChh?#gzYY)Gv&M1Kw$?PY{__I6`0K#9-P!+$ zz4T4Av~3xg_ueW&upQ|NZ+yFFmOsc;2?X0X&{7mkz|*VjxuAmJyE})$B&uzqYpF*8 zVur&hHvhu_#v1|X9iRhDjW(aQCV*Zsfcve5C2+2cF>E`Z+%`1rg5$5osKuIQ+<$aF z@j>dHtAUx_ZItwqM7NqDw{v)3h5Q-N1AI2^JFej;jQ>50yR*S*FLj9Lm|^Dy~a|etEs1 zJ3}OUDSxClTCIfd!X4jq8p<}l(74dPJLlCiDSFBTSu1OXLRJUokmMRg?MDRgf}0iD zPO(3$l|Z3OsU#Kyd8eaY1oN>)M~_g&j43%6K{z|mjlw07)z~fyS8LWk>4lZw4CTw2 z@r*d9o^;m+B%x|Kks{>E>TMb?ldJdYCq~g=)X%D%n%nj~Cfbylxb;8GnLOIk@1E-% znouv4ep(SK&)Oewdt%&*H@Wb<{o_aFpQ-0bkXas^#hN-3!zM5dyNNvnpI1zAT;>dWbol(r}#=wwrp^Ex`ojY`t9P1vyA2< zW*Ih2Lv4QEN^d;|6v-Pd%99UZc+XB5eSLisqn}Vtrh|`RK@_5B=Q+(|@zqf=Q>8Za z@$CdH8LJx-ydNyXud_M6>hk{ltXAD^q9t^E2_g01Id832_k?KE1NS>m6F>1}r$ad( zGstEp*|sY6Cguv?1)EpoZ{9u$jaCXqi&H$qCI zU$7Qmn9l7<3r_m-c|`FO!>7cjtCX!VVb1BDA1!)ppoEq98Xqj#Xqwl}kg2Uri<;td z$|#`&h{zD4YLHkE86mN=n`+Y3HIC#drIU-Pi)Sjy7y~Mux;wAUGt`(``z?KqdZ)A0 zGZL}NE@4~m^f=De?%G1Hir@uPZD*hHRw6WV_*!1x_&9pdc%}NYJEP=sZBl$<4%Xh+ zR~l{fMU&qQ&)j%q{>z2p`M31?tVa-=fw}Q}3}}rn%7+bybmUSHv$W6EutCBS^QkAk znQ4tJyzA#^=QM0)Fg54AaMc%&)W+<#IP1zV>Muvc1*{s53*5R1-^lVBA@>{45ip+U z04XNL-MTw+0q!rUb#5S2bn=ztz|2>P({JRvxT>*Wf_=Il)Ud4beq54EA7&-%#He^` zIy*6)-I-j<1Y?P>pX+0Bvi^k4XpeKrZ(UGY?_&SL7f}c}==sk^i2_@1miNP_QIm!9 zzH8<#F6J`Bn;9ulXtU1u`na-`2L}^E^dENH%i$|W%h7<934Q4kN7B(5)B1^X^MB0Q zGoRv@#x7>+6uAHED_Kj_+q%F4^2Ghp1kAg`8a1>!M zZ8%o6O)M=awzQKJ29uPwg{hUfruN34HjF>;r&|EXQomtpOQEy@3}LJ=MlcJU0s#dv zB3M;0fSJsJDJVdjmmgp_kBNyXFryL$2)3cerGSYx=%grAHq_Y;OS?LLo25-c45k|Z zywNt_T#H$SNr*|9i5K_>hynzxC8e!tNudM+!x$lOFa-o)1q6dpfDv#;78nZ!lo`gz z0)+wNq^&eIKo=7L6AhVoI5;*Rnu$kq!*|6b%_J)&yzxJso~5Ok1sfBSuD+$7l?LEo zG-fi@)3VTK(){gl02toG^Um#+ApcVj5E5(LqSO5wGPSw`w0{#I94&T-hV-f&Z z0I_V`Poy?%FB9N}(3I8&&J1wk`2;AKWVCH9_Z>tqX!kO+YnDO4)%GvV@_6(ui|25n z>d7^H(uR|_-%!lA*|X?dr*}brWQ%?hA_7iZHWTAbyXl@+%m{yWMVb?J7l(WnHqIGbS7WA#aX&Pb zV*CMSP_ZRTi#cU_CpOOML1mq~V7aJorum*f-nfdgKWsQ__K?V7354W1aQ8bZzKbSz zAPwlj++C#MbME!h^M(%gc5KtHksgBdE?0GCjel@N#)%vWNqHt$jO22qkUxg%fg^?a z7s6cel7+VEVG(gBlq&O<;Cm6HpG55g5w+q{mpJK_ipYj68&^+MHw)Jksedn;BlmmN zt49}OuvRWrCrvx;6>PPdj7>@U(&N1}gBC0(>~=bHmD`7PhKiVW39vuv9f#}Zq;)aX zXvmDv=FakqX`tG1Yv~a2GM|{ftf2CfKdB|!RgI1^jGWJ%4Eu|-jGyXtsLQBFmOY9= z4NPvpH0Dk7sR#4%dP>1W8kb8^?^0c;`96ZU7a*}hao>NjA2sf&sWG)ccSm&q_*)fB zc%Yq`{B_;@a4-*r^vZU z97C{j)y$#=e5tBevvS^fo5#K&c;x!DZZUV^Ba1*7;Xra|t{t*#Kr8i_-%mc76`A;7 z#T^QDl`F~FuhH+e6xbxB_dGnKFRBVF4vcG&yA%cbfUuN$OK8?YI3+G%+$!*1ukg&v zTvXImeT5#gxf!FnVTA^Sf9U%4Y&1-52YQA!(>6Qm_FMg*%N*lnLkQ!8+#Jo`KfS7c z`KR0UFZhmBVFSs{*pfpnwn}0ou1tMhw6Xk@vxVdp4-x5ZHQq}pc#1DP8W2hk8Ev`T zjb`h_2yd-qXL(VVHUH$In>5Lgs`)tj1^HfLo&*PBWOni?kk$QO)uL7NRc+%zj>m`( zw%xw>n)(-Vu4RJ!&X`&6EDT0+ECi_~|dMim)e}JAcmVu|qv|hbTk#{)L`;t)i#?YZpp~?H43e zP|sbU5-Cg}Rk?Rk)nskuPF^|sOc5+1{NnutY1an3eic9G4tw*rs$~y8U!9>qR_Cj4 z(3k;Js4_V^q{9PDG6mJk`bM34di7hcebLEF&AZywZ9D&Iew4S(h@uYpjb*oG!SWO8 z3j!`@?Y?Dm1WnM1yAye|b6Cx|Puf1APt!ZkXpKF6i5ybI3~IU&!#DFPxY>no>Ll7b zC?-DAi=JD^AFQYvCLy$S^Vd>42eq>5W+k!xzGT0g9>$Itc`~VmvySu@U+czUBmf3& z`*wCs*a0N4r4aWa0WkBXs{J33z^2c50|{(+%r-tZykWrSrYCgca}#O+pBs0ijel?0 ztBubM)3fopb*BQc{6-X;9!lWvn;yuG&)@SRe$R{eJs;xte2Cxk0p@LUzD*C|2Ho%Z zShvgvh;_?yfHpmQ!1tS8yN%D^^RfP(Z_^RC@%P{JvHs?db!$HGrVCAq0=(%d+xXn# z56ry9A9&LVw(<9^`M}Iu{DGOb<^yj!unr)mJ%0BC=;Jrqq1c2wM+2yh=VIOgP%vgV zBM2~jEX)W-W-y!r27)j$1AD~+0)P|?1Q^G&X=nFFV9honi{Q=6@m@%@?E>9BPrqT@ z|CuQ`fa)NCfOeQ-hBAU78>sFNOhFDYwd-sBS33nqfEif<@5MG#a8?i_oE83Orl1Fz z+T-;9XH2mG*bB7F6ALQA|3k%q+(+g*e32UI6{S?i7d-@EOA)VBiEnc6kEsQ!wbC z_X)J+nA-F1Z7RoqwNYCPS7DOwG(Cg7pikpd@w*s!67U=Ou+yp z1wkBlrVeSTJt4jST}y2-1>AU90sFYUQ!o|;BVzNC{--kqJNWW#TK9h|K0r%Bfou2< zQyW@}`51K$I;1-{p~k;u3JL|z&@N9f2qO#p7p{8r3Yn&GQt60$qr9|mV$$h)90**-o3r;nr%yOJQKg`rW z*XK|`OThsFZ0{5l&{8nSG5Q>Q$Q*CpA^xrS04)XD13IB_7@$gz(dS1nwb#4#Z^Q>^ zDL8N;+}SBWO+jJD9P}fY`j?l6O^pBr)YOJUaEB=*VruHOg{3FW; z1=JL9(cR$*&{7bVWAynEJpD_2zO_++mSP5OxjRgOV2p@O|MMSIC-@M;+q?t+({m01 z)D#Se-0m<1s3|b(G4T8drvAA;2do}&gm$qogq0aE$A30_;6ng!(>d^OHww^F5Wq*W zy-^TAOM$`1=<_3(`sex_0)sQMLiR8PXel`2IMsOwb#A&%{_RcyS_%SqX?AuB&{81i zajNqmQ(Hcqf6EjE1O$I}p)dr{QgG(uROdk`yyZ~(w@d+A3Jls+oe)4x0a*#h9Q4CX z{d0W|U~%9K?Me^OQZVpws`DT`-}1Em(~SZHS_%Xt+3XxCX22zcI0g!X4>R@8^*I>O zQgFb#xXlz8&{ELj+%4dP_;S_+5{ z?`{;Jr64T-9a9_5*?-Fv6!01Ve%Br8!N7nuJ_ZUy4x-L2Pw~HH3cP{G_ec-I%*YHo zW~U$ru@rbGQ*y(#0fd{k!VW-A)L(>~!GO)(-R6VDI{{-D;Hd(R*uii!7_=7%{D~R_ zcyFM9pX(6yU#$E`TF_q0`p1=Nkk!kZD6Z87eNbMFmp0|*JcnQXd|Tn1#ZfdQx3 zMl|C$yBW|0$0=HtLwg?!$FUF| zRZqN*9X*~Wgk#i|@-Bh~RWZ&uJAFuK7Ntu~EtuDyU%|S7l|WBCuBPAYVy`2ls+6sy zl<7H(&xcly1Rl?H_e-T31USBuM6{*XO6jol-_p4T3>LiRQWw4IHI437EpDeU*_j&{ z(&S?!XFDROG(;)QD_w$T~Ehx-eiy$Vu8TIU1Mp}W%CFFq5%M5R{9N?_ILKrzMg8YO$ zkU1m!6U}EUtibVUwRcpe@WL+y;Dx(gS^ci~tGu2M#&=8u1w z=EG@aV*Rk#>3-d^>fwIPLY_taMZ~)`arTiFWy-QF!;?`1JoRM0``5_cELJ8~5X--I zakRU5FO0sYg7(yn-qQ5LOde?qV@tQHt01Qjkg!s5Cpr1~QHqrz(Y zoM)G7T;ZH$Z}eRy<2bz22Hp?l3Z}SE;9SJD9>A-P!RXX(BGF?$-5hpOiq>xCeXTR? zlL5CUjqz8=_@}>^$vUthBn1dQdorQ>qq{!vb4z!pxrfis$Ji818a!2&nBp^`YKr&mMf22+0e=2v`6T>Ax; z7P5761vYA**pr-DL^67d&4hP9`f^pR1tkrn-U~#Ka*m2jVuIz#uts0Wt{d`|PL5)K zNeGH`B_(o0dF^wB>DTFXKe?1p@t*j~2M_w$bp_H->UX8el#*5tt8oXY*evB+rjFs$ z-|N*%;F$uu-2j`|a1bWII<`pD1Aww8yxh>{&@{vDTL#bhC(P!F*()gj(H+di4q zBmISP3^~?>dBL*t7Y>!&1OH<82kc~PdN__hhLN;&mj@)#Fuo3a?=HpB&@Ebdb=F~J z9Ib^fC8s_UCmv()+nE^;i_v9!2AN!iXw$0=a}U(b&3s)}IwG^eG=4C*7?W`haQhNq zF)}sq1qd;Uc}?~xHJeveoLi@{_AjBpwElSZ%zDGUo4v~s{dsim0>0%EzwWtBSf<7r z_oC}{mw!n~Xt{R+$46h_h|o9S2iw(bTdt6Uq3=!Qw?Fi~nHK$DC&BId6*i#t?y?(Z zVUv%)w1v>UkmDfnjx7Xi3Jl0CJ7mqE$1S~04c|zfgCGu5!}g{M{Aq0%0zfd3BZ&9< zo&HD+APoc%@;=D;UK8}+(t>v~z_+o--u>QwXei5O0PxVt;62IVTgc@|YQVJ%20Zl# z`Q8Yf{aM!AYlGnc$OCdK4^i)A;BRogivjkT{e8J^0B^flaQn?ZGX;1v*M1W!{I?hY zNTu9;jBN}60Ym;41BA)lwAjD^Kjh4YNM8{Lp$G>BgXbv2#%ajj4OW@k3zn=)YoU|*UW5&rHWB6m6P0Xt zvE5BuuRPbzPrjgCW_FACa;w0I2phWQFPF%c1liX^#wsMlT1y16%+<13Mq~f*G-?Vw;c8@fFt>Wf+3!B19KT*u!pROfpRcVROQ3wUz-y%NmQ^N3(T{#@_ zStE7LTLa&g_I#jh|4p3JB6dj}yyH^(YN>Ofw*|fn1+o({NPGzN61XyV23BKMNv_$= zNyqQ+BYYx1oA$H6b4m&uBbiJc>-YRtAsJX^Rs|)!-i&}Hr|1e@)YTcEWlOn;9Ad3{ zX_S+NggDnC$%vt-DEwF2Y8;f+!_B{6_YLf7exeYhqU6dU_mnkoc^sGh)Ywge6Jw#3 zrZMB~tORj7vgMHoik4x~Rb=ToC6K+I(b*gC=^%OHk*Qc&SZ`iTT*wfgy`xZ)79*0w zL$rW~6?EEO&_Y>pelRLHA-1(0dXm(WBcoB_U5n>TIw8xc@vmpU+VU#J@Tfr{~iml?5H%gfiI>oJ61&@L@ao<*c`*JwEcj@Ce|K)RoXNVb)oa`Py9(0wl zXD@2?iNd{`St-?W`(+hz>s*}8`hf2bYqKQhE`fYqU%1~p@tddIDa{l_fRyDj&)fp{ z`WPg4wpiHZd>PYs9^P*UTQwjOms{>T8ljX+bQ;Fua1ur6t0WL#B-xxF79#jPIH42+3S3c9>1Ji*Ywbb2Pb-NvoN7gW=RD( zp3qenJu85t*S1FQNK-3#UYz|j*N?YaY$g7XoAamS%NYk?rcfW{&%) z!!%x(8|`G19o~Bu$y5w@WF=#FB9rqoBotf`s+QH2XE?GwR1HFVLvaSoso^h$eZE;J( z2}wHX>*sy>wK#1knQItUvHjGnTXJb9~~c+RHSM$`|*YN#C?OclEcgW3Ob6 z{x|}q>=YdBW(6EXDVyqfKS}|vdB9EZzfI8FgHm=12)C`~CLe!^QZ|#xw=b_72752@ zw%KF(6H3{v68KNla2CJ=2xJi)GMf8x^8d6p5Ox88#$kiKFB|f|B?j+H$onHTkV12K zVE_Z{F|q$G?cVgZKhgqjT_DbLc)t!pl%r&|0Z~|iM3O_)o9Ap>R=W^oA1c|8SN;r9 z{##VCuMA-um4Ja%v%mCAe3k1m8HD3FHOUcmJP^5FADGuXeTqM5SSkn2n}5J*^!#at z57~+eGW1uxmgm08hU3#35}sCk#&n*)0aLe;^kR!ydSporwr(#|6XWE-9Wbf|X!PP44>_^Lt*NP97zpdbnOUU0ugMV)gJG zpso;s$=}h^z^rc89d-F{^M|3Lc*Y!OztThzM_`k$=wrtIB8vLv@6AwGZ`+VV{Ni+? zVTL1SzVO!FW8pli&hZ!* zE^YM~J>wgT@$3n&AvuXd+r!XtJ*U{Sch)s)W6+wsYzJrjwKL@>t{RvvwsAC`app1* zOE;3lsFhaqim9INpE2$&C&-8&nGEptDflwW;k@K{k2@x9+V)P9Ps&;?UR$h|qoDVS zxV`cUchuwgkmCHjd!*Qfj6{-=_cZJ}ew7AgKlPvGoyW+%!$TM8wRT#^TlS}6cC8?l z2d>c6ij!g$?!!}1t(JQM;R{-dRqNb}16&O81674OmxB|CD(;_ku5>~!yp{1h{*}WL zyCas~^HZ_NeJ^^~@4NpRa`vRvRmv)!eyL7mASwI21X7!HxphsVDT};f8r9Bxkb?-tdX%U8PxoXn?MnX-YlvW zA2+>VL@<^%Pw;u9z|1DYz$tF579KSJs`s@a%A6Q}#l#rIr{8~3A5dX=ES+WX$+24| z4F8m@91eeHJ=;04hQ0!+GU^9uHZd2gJjnRXv-Nak$up&ERU5@q-@VkT{zz4a+5Q6B zwDQbzRF--9OJ{Wcc10BZoF6O>CvNa@ls9>gnyf(5H2@Y zIsZ;N%P=%5T1IQ|JL?dq54x`?JMmASK)Ley1fQ2C$>q2XhEFv_vJGmB=~6OX^g63)FVvYxd+?>Szyq zeht4G@k!uuc8-9#0c&R?oFV=a^#G;0HZiI&$N3pC*<$=<0@;!zIJ2KwV!zY z$Xu{3%kYVhRfB5PQWuZmj|=Kd=2p4{vZyzR_%izD{N~=8cZ}T*{ng4wy}T4gl=p3X zdW@;+$z!`C5C%|jynDMl+7Gg+YWE|I&Fba<1z`Z;yxnCttkxzUe~BV91geU+f$`Jr#vzY8ZQ3K_Zj6mk=p{4iLeDB)J{U&m+kN?lN z_&t~Xzw_j8)>LdWzHKjo=`mhiJFgLn5V=pjD>mATSkbsloIus zRQe})?Rx{i^O);gZ&-3^>m(py%GVNC+a^=}QnEZ!o?d!-J|sZywJE>#(79g4lxx0$ z<0Zm<)Lj-2vxHKY6S*CfS5|)3QlrG4TYzIA;ZO_V!OMGQBiEa+s7g12ctjemSAY45 z)Kv}K-A;0c;$=gXxM6cf6MPpVxhSw@p^g1sx)uXV{s;~2khD1V`Q}-<+x2H^=U(gf zKuyw#KUfR7iZQP1J#wtljx3%Jknf@~qQ*ph{*9>3V#Kh)|f5sN-}rdyR$d-*9tWnrj?5rM*LHa^{y1BhdG{431ZTw<&B7k zW_kR=<-5phM%C4SauDrWj9#}_UDvHxBcH2QR~|di>!(Z0&^bP36Nsehvsc!>%NvH7 zy@J{<<}u2uCEVv~qLCjfqrxKlB{SL(=Z7r<4^5Y!`ooJbOSpxy273)yxd zVTZb2IBh@+NfloLq*88PV@8`?CkgH49~H!O9`g!$c6O~2Vzey zFDJtZJa$aktNGFVdFbidvpAzUOU>Z3wSmBv{R1J9?Hpl;^;(2%? z3Q4Zi)LG*gc>|g{DXS8ifFFvwB{8|E_116Cj@pNF;|!c#D$?}#ZMI&O!1l#Y$(EBX z`0y&KtouDy+H+y?*lAEy3@>Y*P!o{{CgF3DJdLFH(c_r!BSX6~C@@MDIZVn*^*uPr zF)vS@YARVpQH$1Iv&pL$Ahl9vpMAdG^&x}m^u?$uO$pTIuk5d)Z6iP0UyDZLfqR*8 z$1|!8+)5N$qQ0{e#;egUOYMO zcrF>&mG72->I;V|i_f&IBiJ)fB#0eVF{%Rl@2%016EJ8;4`!2IjXJkT-hbMH3aTM` zhhQ{0wcT2oh>M}G_=!Bd4xJP`F4kiNO$Z$>R4m3Gf4O!(3^OP%}qi5ANWRElr(T`2KAS6Od;p`l(pNC8F1 z`+~~b88Q#~d>J8e&z@IEX*>)Sv)~d=k?Bz({twmgYip~S0Uu{C-1fZ^tNl^4fNlBf ze9OZJIukr*VKC2WNp86)zGYO@+63u?trU4Df2+P&>|pvg7D`KKjcS6SbgTrMUzdOdLI zGs#IJ(m53)-1d0t0qYSKYtEU1i`2|xp4F^_yeRDp2=B$^sP$%+FQ*z#{w%6uu*01b zV2ne!oJC5uRcU5R1g8y<%cm~kVBWs^ak-y}=9%A^Nyb2}40%qeWrT9>V}fp3SJQyE zBbQ{x@2~W9Bl&`t+;tD{-!lo&6aVcE4m9?YoWHnM)O&RIU7- z;qhFoIcIN_te>{hh4&m`XpgA)Ie3-ds(ag8br0SyqyO)!?)P5h54zre7uo$)@O`rY zZ`){W7}~wW+lCenT&Fim^A4H2&9c4!NDbu8Fau%w!_<4-&VO1P29)j~fNZnF)Ccj! zQJin&8Uu0q!^8(8B}Wm1fpjg%5#fqM2@C%XF?e4Y$e*4XC`{bU$vDLLzIu&6QUhrw zh@+x3JN@eRM;!jYT<7;?yKlo2ptRuc;fYc}Gy>nb>CN>SWT~I+F1ab0*dsFm-}2p-kuUYTc5e^9FRtNAKbw=ZUCM37_?Yzq;2n1Xtyu4&s9+Am1+`^z_X9d z>QF@1972sH@F0@x&45SFeGsG7Wl*z8wPlzY6Yx&3Gee_ z+O&W1zPbx9zQ@IfKNR@AwLJVBpT!GiPFx?e56b%_-qu3d-eX1krc-Cyu}HOd>70^A z9W6QrXA|| zo4z0%@T!Z5OHLpD<{@oBT|HOIWa=>}Ng{6;#U$d=E=JXke;_|h9i zMsfnA+fYKKPpxz7>K_UcNT|o6)mK9qESybfkJ%X_Kq-1{q6vR8zQ0S}BxJN;-G67hgvQb&a&Ae)^q$8r*I_ zDtz-Q1v3AA?B%khw@b?%^%G}WWyoCbv!?0cQ{0&{dZKtmQm{YXvg{+03(iAON~m4} zOUqAcB@oJk>Y#>M^BGPCzEoG7Y7C!L%ToqO>ubpi)7T}7lUuJuX2Ll7GKp{Fr1iewmtFKIaOIOm<#1Csm6&1pUg(FpRWrWnRx*vcLEbn-rL?yn&x4>i8H^VfCjr*hJLY6 zYwDRLCa=S!L|5O*w;p{GHQYMGH}1@=V+PpBjx2s{gPY zzE_6-tBM}JR$qd}krGoR4_3?l^+eBHrI)^He$t+jDcoGfyySgep=R%N`qj(W@X1Lv z25%v97MyYP@i07xETOYlrWUt3W}SYx-|!@*{G^tDCfrT#eT~HGD7}&8+#;mBt3dyj z8f?m~1e_@w2^xQgQJp|d{>|@HO7m4Yy0zPcH>Q11W6-f0+f)N;?Q1_I`AJB<95>^< zHK2KJR zoFWP{Oni}6hG}`lPz6#P`Dv9hJR(Yadeq2bBJZTZiXn?$0_3MgN60l!B{%N5WcBM4 zg&%&-q?sp%Cm;eBSqX+*kqu<*FX6w8CEd5{0a-k5Q+72+1P#}2#1l~f5H+I*F_pZjkdM|<2u`JM&}A5$0flTP5b1{-~nSV0?k-`3aq1qUUrJ zjY*b8c_S-bql3{t4}CG+=y-yjmVgU|OZ6GQyJop&C`L8C?HOD(m~X0oKxw^FK23AO z`8$5Y*bkPm(5dm~NNVYya(^(8T%L6bbwBBA_|0Ixy4?Ju?$aC0{`J2=-n_lSX5MJ% zPkpeby)jK)(?5|w%^^IheXB-7f2rUO&ZWk+qDy$5E|gwC0lh|!2P1lu(A zflFVIzaf@$Q+cUgm|T&HMdU0oI^_q!WFmj?M2qfhIc1;~?QBtTTCiBMp;n+f9i3Ud9T4BqSKNI*WTni@}{~tqn6z3N2`N5%$yi=3_VHUP=0Csm)kRr2oGc^ zwQslDC!|{cd!yZNt-Zp0?!XY4r(q3=4>Uijnx1U!kS>btOUvtxQq?7ii6AhpjO?~r zZ>R1>*LkO!k@xt;ovh>zvafYXiSFutxbvy=`QvRm;$u@rwz8_|dE;W}@$G6Y39hk(+aRH1uUfi=;u>>Y{ya=8ZCa!AjQ; zb9q;^(i&QsdKlmIblKpr63XT;2G5M*_7_lBj(&eBo}8SY#9(MYz@_n7D!Mu-&MFhd zLw$wzON!#FyQ)t!R194OQXZD3jol)gs?$=@QUP3%zHXT?9S(lUn7QGYuixFSEx^@- zrNC`3-Z@Ta+GH3m)pEw)5;qK{hl%U!ViFFz**fd>i_B8n@Gdr4Fi|8bzcR4)!=J5B z6&R)M?NH;gj=y99j!xiCbNX)ryy5%GK#POADww;n->U z5htZe=slQQ`FU9%)K%BFT(AD9Z}03LSMk)~N6mtxXW3NJ38S)Wtar}2pVX2?f?D8> zoM<(=8~rZYne-IH++*5+wURmVTx5lw*}|qMNTKt)s~DYDgJedZSgyERfljm!WXBEm z&B~gb9ipK?a(AnD9^t@#d3iZah$T+W6^WQ80Y@;J1rJ@+-u(0eea_U0&tGf^G?=L& z;o^O&4Kyz&TFs|57?%Y`1w;~|BWF%Mjf#mfPk3>P?v;+|E8XH|8eg08`&@o^tIj%r zyRb_7YoS0bXOaCT0{Y_!i54}boCFCB-?`vz#oMKkI)~Wh%qePk3 z7FrbK_!B2DCa3psd?pc*6CY2q3=G8AZvH@QaK_KgQ{w6g>!v2ApbKPYr3Hw|<3fL} z1<|?D05~=_A}oeCa1=)mpPGaJXW}RxX>6dDfZcNVcLFKA6T%OXEW$ljck=7uop5qlUG$8boPno<3!me-4$98W82MEr%ysf z;3dP{vUTFc%$KY8l}BYlIEHI%-1V$mxPzw$QJhx##l=@k@3NH&t|u;FFNP~N90AFW zs8KuM&Dm0%`@<$%je-6bNVZ`{_ICmT|HCqW2pkI33xO$sD)CJ-1_kQ-K|mTKe4|_j zdUPeqUqCS+S8#u@=XYbIzk)jZ>Lxef#$MuWtIe{}0}{e|*zO)Q`Tq?uWKU=Ft@O{M zsNq1LoeemA5HLVCyF6_h?LRRNhXC!2pohWAM(=<>@7eZaL%={+fg_%J^PFujy^9zA z?8(_5Xxh!i*jG&QSAizTPPg^FcmV<2F8(qxBUN5$qp>mI$zlG&)qefOs7a#AMa9b_ zd6`OqIUVI}&wTm1lxaUar(^GU)7yV5TdVS>FXeSU$p=F=CcUhg5P8hUrPU$W86hkY zu`EJkG}CdVMqFlO)$?w8%wDAIvxTMCNLD~1!~&$^`ZdH2)%O~m?JUr#y7=#(>j-)8 z#t?5y#V1DU7F`He(fWGkPec50 zl1|CKE7xdg3D$f+BkpmnDK!e^HcwexJCRatf^g+jEO{BAFD7?E_cUW^{P|alNy7#! z4d`TFpPiRy@f{oYD)%1B87jXhzT`#r;59DCc*m6!V}2!5lTm$Zey7;|gTI;5T>G`~ zN#Gnc%4ja?lYs|C;}7o7dn;B%;1nrXiSpSABl1-GL+i==E4#etnq>X&=Z?(D!I)8N z-aJkcR!%WzL;1{=WG9tmM{IeUy{D)2GWiYsrpi+?-;`ZYejYSv<F7iVtq5}t0r%zCJ;Bdnrh8-bmw`3fhP2~=8vJ9yp5<{_?3!a_%_ zgF`<-_4Qx_7G{s9-}{=E%S2OhlpXOB@5mCRSteeJc@N>9SF*dL-Sny4yjA+eZI%Ap zSO&cV7;&fuaoJ2sd=esH#&_Dok4W8TUcc6PMg){8=KX3IfB$FvMPN1G%hH#qXoa0a z%BLTs`>LhHdG^kl`T6?07^E-<<$mfUTLiiQ?G--dsw9DhG*q(_A9?fmzMgu%Oq$$* z!E;wa@~o+qFrvA?!b_kyRkYFSgoCOcJ5YY~;8(zBnjZ|&X=Jw?sb5+qLBoU3CB$`3 zQ}xE=sIuo=#iH>u3bI3e=I%x2kuPNOJ%JEC(}w45K!vaX!FNXE{t9XVk4bnK*ZfE2 zTQ?ierQ`Tz-&wK8Lazy^M-JURH(>+5!hXiZga+Ym@j!Qp&E%XIQ$4TV5G&6jDn{6dUYlO6Cm%ZL zdxlHn1r(l%S4*!kX=k3|6uKk5P#sW|{Om!w4M89N7s^3QpSnl=Hpb7_#W_!(`+BAp zP3^p3j|TqwxB(TrU+U#-)XdPX`Pxa}Y<2>B7Odiz`tyb8YJG2MZX>bCi{7tZzjNYNFIQQ*!()|8QLk5D z=ywQmWB<(hGk7#P%Q5!Xy_5W-Kb6l6y=qB+;r{7zZTNswquvKWKXj<3QqqNlQ4S}s z$-(UQtnwF>1`V?Q&zNBCF6A-3W~gc7#`HE~Iky*ljJUBYW$%a=-0te06FLzaRT66M zg;!vUlZ7u=h&8fGPvv=*zr+xghtkVxp?K-l1pPCc@7Ga2l=)JqSUhU_l>Gf?51i-w zi3bME6fbFj_TOi+&Nj+gd=K@$5LO>)pYw850gQp%y)=OEUwqU8(-?1xS@V23-38N; zC|AVuC#!8?G2{Gf?J7)?SwuMY9$U_g{*4|h)Gy_Gv%~EKrPNLXUimkmK}hEZlKP)f zZ5*e|Z@={OP`w$C_NYcwL?|8Guv~*TRdDFW33p>CT^&~#DMVJtrmexGNOeq4qs>*o zi~U0kceRDo=%AM5IX41oD&h(p#%w=>E1H!)wesUwJURpPGXma8B=6_1(CU8Exrty7 zsWECCLw_Y_NjpKZltU};o{EDMewx#P+6>iv5Oa~bCu@Pik-7fE6+!xoQE%;pX4njs zI^9WLfeA#uSXq9D7@-Q)i5b&Hc_TlvES%KtsEf4iU3=XYEXmD19>Y+W7&+fc+fOEU z-qR@$@lD{c5fyv~OLp&?N zDN^V})kpa}x5{XMr-1Fo{lZ@4`WX%DX(n-h#;(JNb|aLv3pkE+GH#jneTWvQ%-;Z{ z|933dolM(3I2>?V8fMhp%*dZvufYWiKzbG8&p#eU| zg(q!i!Dy*(tbM?Hx5e(iVGRld5@7%<8~w^*n;ivM0G5FMl-u(&LS3(S+ z&n@}>U4j+lU?%iF;%)E=g#hhG0DtWv;JdGf_Q9pMsW-a3fPrN1L)4omYI|pQvFl$Z zN$qib{T*E0=aAfXZ-IbcfcZ3i!@p*%@*qliKNHt*?i5Wcf_e7#?l?Wd$GE`%dXv_aN%yDtuq;zi3k08 zy^<-XD+uF`2gEnd#r{YAat@8{oZag1q7|Pw)XgQ9S^ZA+=nF+}0oCr8c3E%KyagUH zocVHb)}U~~iRaEkPIC@76gqSyCWiCm+?q^C{Uq3Y!eiYEtz~D>c}Qj6MmS8KFP@#R zQX>&E8@)(Llon`93c;T-^AEwf1ATj45-)_Yxxc-CoT5S@Hu}Y?RL(Sbmu}#2-0hfiJDSK-+_m<=2X8cs*3Ap=F3JV%0R=M zMH63vBi~H^GM6%tg44gkj#fN{fm>BaI5G2aIXYTceDXzSH+=3~ZEC+vxK;c;PTiYX z-CW~0le=EsX#Dsk*(hdUwcr{waL^7VgL`YGTX)Tv+=691z*T8 z6v{XqQr?n(%k$UwG%ax%MYvsdv6itx7bQT>{FX*RVdmDY80C{^-GkjYMCy@qkCv&k zyzhaA_+){}!u;I8$$&f+>ZUTHpl9#8zIazHrhRVp=Bs160(or2fiEV}OBj7cE-_mB z@|y|@|KZztJa$uLQtkqD7$ZblchrNv{bJze9eFpY;Xu$JQD?6vF40M zSKN>tgo);pY*F8x(P!f>V@9M<-C6x-GAy)8v0dqa?i^= zcPol--ulT*T#B^j+jpO!pOoW1>iGv#vv-l}il-pcHmG90L{p{s4(mRh-<9q!S_SoB zFi0WZ6cRMw4$CJmQSWQRzIww2VcsfxO@4xnqg(Zfa;u-wSCUA%s}~q1Z(mc4nRJ>r zzP!fA6M}5d8?7IdANd2PK`)vABtwumC`&B6v(rgC7Xx%XF}bCH+ysruWvXU zxuMU;OGJ+ro-6F4AoW$KdU%bzInuCP=Yf+|^99n0qy>qK214t(FRjmZuUi=*S}!zm zed*@yJH5>9BCRADih9Y;lX1nKNqP=lGm0&jy?Q|J)6#tFd(n4AK@CqrM zUrsp5BXN@BqPuY;gF3XehJ1cmPTgRCQDV|k3sp)`kb%fF0Z04}7ERQzYn+k5f(cbKe@xK`D-+d<_ zo4GDh6p-JoC-xcdJwJr@zjjaqeqaRX`N~QGW(ArN0j?GZ(4ZOy*#_w_-wB7qMbpAJ30R{?@SODY%24DnYlQZCVFM#x9Add&gOZx9QJ6x3he+4|? zjrPv~V?etWRv*^B?DdPj_!Q*=Pd*8{PNrHcq8O@7m>g5;6V=7yze94 z#se(ijebgp9brH}@?BWE0VejY{GW&+2MgJbq~53|LjYdXLr`STujOs}|Bj{xO1faM z!?jhAg8|+nsUe%K3J)*6uW`*T3i|)z!2@9O?v`&uBA~_j-$J4W`K^NQWjVdaXIeqT zryO`|463xYNg&Gmp=sn_53`c9H3Aj^jN_nCi^|{R z5YP9qmE~rHV9`gG_-jiHV-KgVzc13cTB#ir;o+;5C2LnOU}G#-bLmY4W8EW*EUj2- zZ<89*L^B_DbN(g_BZc($3TOB;^Q7%Qn~s0RGfL%J%&huEepQrScIVCLb#BQcGT<0rQJIgSL4mgUX-I)Uhn< z7MVs-Uor=h=@{RThtRwtc${)NtT8715pN^mfiXV;P-nNA9kAN~%bb+&zX| z*Fiyov-9-5CEc+%tk^Ek2Zy>EPGwKJq+a7+mBn})WDxziH3BtsU2y7lhI6(h(l9&s zH|9IO1a2%SUaVDK*|*!P?w(ZF6yt1$nY4z=2HBK|x0XXoJ@DXxZ zMM%|SBRcKm(oAArGaAx7=aKLBr7R^-RQHjT(k;`!d~jNJ_6F>9T{AtdcH}L)MfOu? zf?p1W-zL{#L&HX5YILPmLepBvelzpjUTD-q9X^l4e^GC|vr|bY+xlytvYCl+lb#Ddhg#M}r$HmzYM&7@9+2KarzBlMjm6lB z&C-97WomKUrO&$0@`f=8s{R-;DOzM0XG#Ea$qp9cmh0B3nz`oD;#Wn=N&D=s7+1`U zez0v#<4fDu#Iat4TI`XUKZ*sfy>NK!i>SI|F&IvPUP$4O-G`VLMu1Cx<}o$gWIIdc zOf5M0fRZnY%NM`OjxYG?)wIA9L;S+|&8hJO0#k;y0Z(ntot^)slot~%o7_FymCcEZ zH6@V3obw2epEl~$a~n7629nd`c}qXUi0bZF$)h!;xA4DF=ezL@?eV1EjEd$3)^Y>B z9||0|13F;CZ{OFGJReIb;F{rR61{*E8vM*Q$DZ=ZDvGi!Zxd(G?F{Hk1^o}V>;@d{ zxHQ#!#1fFmV-%HievnQ32RMC^Ee6t1>XY@gi=l-5A+Y;>lI^m7?d> zWIAa?6Fo)|L$<3i8T2PebMt$fzDE%!bNCn75+!FFucf<_Tq%1dh}lLiq^qKThCA<8 z&)G;cbS2n%r?0a_50dXod>X6gug8>g6B#puHS)<*qqKhxEiaSGzH#fiSVz~pNX_T1 z(lkHM!?;m|NS_g{aJ#&o|9`xFbzD~2+O~9;Akv)zQV%VlARwKBG)Q-MNH<7#r%0zX z1}&*{BOxi$Qu=K;hoivbJIFjxVoKsO5=c0v>|t*ttU1Bi!C{P7 z)(z~*_kxl+tWjj46fEgYv>oR@y-EIjlY6kTeGsUIgwtMvrx&Z3cuV9=rH-}yu+44e zkY+U|I6qHU9nFf?+ALTQ3iYP*cgJl!U!P=ep%He7n3iu+rV|UA){j@S%v6hdxG0AapI`(PI2Qu(s!9Av`d8`klAn0Mo3n~jT}}NwYqloeW#B1 zYT!(czW<4uVy!bO2mg(eMu#{irJ9b2uCo3y^OuIc5idpMuOZmP={}3tU&tsM`O|z5 zW*Bcg8?2mE?{Kx$*Z;8_?dHt{jnL$eEg6eK?wVsn8k zW7UK5O|9}Ex2d&pwLDn;<8JfL(j^DSvDf&0ZgO7rHNlm?5M4{0k<+r#VD`x}nn1IiM4Vb#e3FM|hKraO+P*}#seD-?53#9&@ww%z)bggyKMe;|7SL0=h(i8a@yf1O^J8DGB`c#DH1W;2bu*~VeI2)+) zhe6mXCCM|1sYXCz$~7~W6xjnB-gex3?MaG#qD110MhdQeEQ+#sXfecAlY;Ipx1k?J zVJ&vx8ra^bfhLNznE4_wI>t46Xt(v=*{T+?hCE^+nrE#@kV%;Di9i^}PJYES=cc+q z9PvoAW-$(7;V!}hEX>zNBP}^W#(Vmr@%S;axyFyFe&qKgvCxV&x_E9R#L;=&y73MQ zWqtrXONNPeU=+K^aJx>$8CmBb7&j<4ELbAJpSW9QO^`KagmD++#wJDxMHDOr9s3>i z8RGTSv>r<<8b&@X;c-Hu92yeW2F9l6A3wtvm0&oAjIP{PB#U#fn@@-mAE zvmqT?luX#r8G&#fx2sqLy~a0wZAaV(0Q^)7%`DCaJj9j9e-f(;5#BvlWQV=E>=(Ef`I2l zc8$;Lt#3_hyq~9&MDbnb2>RqRgcZ(h_>Y$HH%fv}Qn>HKPUad*9fyQk(nNaQAZB8r zJ6*G0@h@&uaaMpf&xTu4xf8O{Pxfm6(?0R7kv6r>tnnu(!c);sLydAvJq7&cAvvRX zf*K1NIqK%}wF*_B3QxaRL5-U)KfW+1^y99zD2oxn{J zOXyUW+bsJ0Rq!p4MdfgFS?5;}rhVHRD#|C}!*=Asbf0u%pY+&Q(3w~B{?Oum^cZ+d z{KaNKa6mu74LjEk)?ncCOgh^`Zoi=yrRXPbCC~-b&7~WuQr=Ax*urGCektyB7IIH| zr&B^i9xM3JSzq(r8@-!9YIa>Mq3%Z(c1mPNy%AacTvxgsco3)}x8(j|MPCoYI~B@Q zGN-p9rAxCYq6jc9>^u&p{B)u= z6!uo!>W1CpFrmW(IXMn7d^@tm_JoPnA;pk_orX|qJ{Kz zxiF$0Vp(^(Z~1P>6)iF9cZom3*mH50!Vc`DMJA{3Ag|=Bg@wM)5rbK0!6!0C`grJ2 zZ+7nPNI9d2Tasez$~;e>sgYwthCHESZ?lD9UOXfj@swe+eUe*tR#ZZm`%B-^?-Rs! zVg=L)WZD6Suha52B1sJ2q!w-Te&p=YSS6Qgk)1&)?ayAxpqAu+V!vDYUYB%_uV`WgXj;RIi$l1P_WaE;mH;iO69%_wtu*@TDvLH(w)5Bz^X-Qvx91cnL% z!Ka_MHFzp`eotMdf5s$tUnO{C1D2WARE(vyF->sEc(n~pMQ^k zNOAzK_4C`k3clb9Y@BDW{(5V}B_HT-gMpCbA1n<->N&ym2(w<5G`;lH7aIowp8_io zjJ-xv&P6RReiy&nISA;<-~gmIuA{HC`GQ>=*dZ`o987Tdsvs&@^jXG&6DT*hwl)wj z{_9f%)M9_L^M3*cNZem9%?z;8v+)wwHhzBJT^#vOX83;+m_8RLyIA`_G!bCle@GKI zl-`E{rKMBHbUuaj>7T*}>+j$GXrz`M4{g-mN!2MJIKYksD1JHRek@_6l`E%^4Cz6c-2%~M9yZdr;8Yu?p6l$ z!_JOw30;?QnK$1voJ@8Ma0GIiVs>-jA&qd16T~2f8E>6t2;H~AOZezn%=|ilU$513 zcsNT?aud2_?YZ)s?LzGa+eY-ai_*@@Q`7tn)rjUbB)gKd7L=97QobsANF%wQg zo)*9LAxBTYKX2|EJZtST`msE}ukF;e;doS%m9H?26Vk}5ezj(zGvMY*;@TYg-840< zyR=3%-v;(vjTF>n-|`6t7!_e`5IQGS)M2a-v|2jJ%t5Oxc*?nbe}weqljUI{KSv5d z307Sy4wrQ|tD-Xvv}}-6)U#Uu0zpyR@}Vi;%CQ=D1%qTd&d#vW!tVMPj~H3rlt=cz zFKT-i)G#^iP>u{u&U&atY4SudUd@&WxuR<)T}QQJ%OYU8*WV3n4MWONH=pxF(DKQuh&_bb8$;YT?8MGE!A9lgq=yYO9+2r0XN7`LVVB>k; zNDBQmeiy|=VtINy8Jk@b5`Er^tx1FNy9&)gy7$p5-mjP*Cmp26t$B?7or@W+J|1aQ zy*5ZwJf0v;J;$eMjLE*{U z&MLhX9!N?T{arFhkWcugT}7t8qF?PTXvxHmZEC`4OEc7XRqGTqw{FL(&FSc*n&09q{th+l3nmGtN7kwwdVqAI>mgL%-ZyqDP(=30FnFS12 zyrg^xo-6)KN%7Z?T-I|z=s(W8pIM!AYI)A2Y)Di|SkLvSuY?6JX;l9+X2S}!eXs** z%d>vhvtidD7GT^X5X4{wvfIF{oBxt~v0O{x{!5?qkLG`{UQ(YvGx5KIF9^c#I$ePW zxnk?Uq1jo0VB>X5cU6fL?8O(+k%C2oSb-sMVB|{x0rtx#8r-&j3%;sE z3U+B$ph1@lT+r&O7Abf%h#iPDf;lvx@Aj{E4h-}G+KRxm%$)x~E)4una`F4H(=X+I z|Fq8)te_|`)ca4#MasXk-arg0njkw&Xy>$J(0{n>qwORvhisH!WbbPVnha6|*z5() z<|ZWi`w^fNQ5Q&fdJhZ!^}F^fPk7#!X)w4?-R&*$?hxAmZIhX(J}I6b+Ty8m}&;g$iwh8uS36oAXYA$oDm5qrjoYh<#FJ3&6+^WC`K^k=RnX*ymL3PbKjDQzj4ar=9&qy0b zAo=LE|1bf8RO6|?74+)E>dzE4(ESFxb||GRn|UPUu~_4H^wh zTCWw$Z2Ia>yO}d|ctoEaz^qj&KKq&+Yts&GzaA=~C+08IkoC(3XcYD-v^u(u!i=8;7KmS4V0KrXY z`7blh5uP5bS!NTAnNjtQS#JI`3&L5VcC#T-qBAnzbBLqq6zr!<^ohAF3uzFY`Geo| zff)KU1`_W;jrpLaFU72sAr{s_B`KzTWskVs=)_}LL2G`)nr3T9zd@!wHm+2rY|P#g z`9T7b=_ISE$(zlIt&n+6eU|yJ$)S0?ydsQ41P%EX-%cMv%K5UwjO?jRAY?Kxi@`Kx zoRrTMnmIKpyvi&zwAZu$U|eY5wnlzyDpqJ=H1wLgjk>sf9aqJ1?cJuz`kxWL-$a#m=BUSZGb;!UfYd?z_S|&tFsV zKG9K~#T%`iiOPqZVTNw>tE|8-%bK!~I~fiT553<>y`|>nI~y(8*M}R8mwogqFv6_=5FgI=lI@gic4j=-p&ES}J@QSTGmY)Ik2)*<^XJ<=VicI#v7 zUL-*tL^-+wY+^nxMbs$E8!h=QbxN5rw{{;(8a1k)94_GJ8Mj&KLoj8%uDVBjCmw{` z`bD(!reBtwOihZM?#8Wh{XnR_Ru;zsOf&_!PbWAZ%2jw%t?Bd3{HhRLwVWYSB133>?Hgeaz&KfcEzhxsU7Q&adsK5D+je!}`LvbTc#33D69x|r znG?dsY=RnM6SQF}Uo5VEy@A??S{FPDNm5~qIyD<|C(>ejs^eArh0IzwQl13s4s8o*-z*7!NrOA3M)0Uu`IMf_pFr|ReE z8QYuG7(iZ-cx88%+unese67v;u4t~He0T_|=nE3V_R~F>M;>IfDzV%f%Ov3~clRgS zUm-1<5-gu^AL?;&)su||J|LKVtz1k9P5SlZH3AfTfPczj*CF>YENSd*Mx(Y@i)@+$ z-KR|_w)Q#I8_;e6_i<>8s-Vf7-$N(b+>MKBrh3GX;cYLXMf^=FQM$?9zgNudXyFB# z)dHZ7VAC!lma~~}w=^l~Zc&Bu!vsqM4aSS)YXs(7^luuIqm}wDI4ZZgkg}5Rxf-(qxD3Efl?#&3+(pgAc(NrIVW669EzulF<*-ExdKvT}*GI`Fn>jMh2?Zy!p$v+9YDy_Sc;OPw zHIS{$qu3*dj~;|R9x!3=4z1%NBiXM{aCwP9HRI3@>F|ZNUCrh}sJa3beT9V9jCp); z=X$4*u5j?u5L8c%`{6pQF02&W40bQVja8ZhtoA$fsZ&gB8O**Mgc%L+P*|_t97KB8~Wu;(K4SYs| zKtHVQ)X6*6L3$PE0W_2PP^y)ACK%tq1>l2|`7n^n_{}dzbib*JKBrCW@DUuuz(xsN zU%Xm>+k$t|%P+=xN(pd~NLG*1Ep(FC4!zQuvqM?xhg&N#D(O`N@}EkDiY2M<|#qn)hXB0KN#^gUjq22sTU?L=#~!-e%tU5oEr@FcE9Xs1fU{FbQ$ z*@l8;a&uD|+H2mP^u$gv%3c}uhNqkPlBF1Fa9xA?Y5?F>L?i@=U;bwFC zWQ!7(VBS>2TwJiMNx~NOpiRt(i*w9QXtDWIjmaCn4G`*lVfdhetX$#xTj!9VuzJN9 zL!|GIyQ!*Qxj^+>IWpcMRS?o=%%v*Whz+jZbbzHeEYGRuS{CH>BEz~tupEp6>+WNE zca6tue8s7(Zn57k2BkydSXkCKCvdG*uSjww;COx=Bwno?X>0~B2vR-qbl%A9x;a4F zI!97OkKq)__CZE;UhsoU7?8?-b|ct=bP!A=>5{}Mcq@E<3trATUMR)>nJnyu75=I1 zcBZ#>Ez5ZRXBRj9Ka3=C07*QcQva+n25_OzS{&H{GI5rQ0fwFZHjt$AKMJN@4T_u} z-Jd1MSb$Ajj!XOszObNYJqXuBIoA?ge+~sE&HTZ#X9Bu_Cc~WRv0Pgl2rT{eaRXf7E)y8B zG*+O-?yu3z96;q0P+N9=?W-Xua64xPVt!}iyRV@y>E!=O2bz)kg0XfmcIdo+#2rvLC`ry(K8zoH^V8A&K=Mz1O$J3sYgv+6t)KUZOG*SS zUaz>6i9@0-7^X`5IBtI;WnA-qvgM|#A2|}k%|X7zUUP>4-jW*u)zve=`pc*v8&cwE zVOIi93ULQ+e)1Dk$w`_A5C!ZrdXi<9_r%tdDk$k68GDPtK^z&bu6D`%c$wty>fhoZ zelpFgd+W>eU7DO~(ivTtnY#k@6AiXJb?B~hzWb+Me(djh1c!C?I>o*d%JwJk!8Uub z-J^?$P|_+YSHMMV)-;>9bsXy3VYkBkw02u>Hq~nRgt+S;+X-= zO)-tKZp+OzuNcU|J?|DiRp^$cnl~wXZ_zfW3LeJNvGuU2Xnvc1Vbd`Fskx9PlW}%i z(d)S%o(Sym^cG@O_-LvHcC;;)fZHp6{5k~5qlz{`W;UXrM&|WWE2HJc&mQ}|{fdXh zdM>@;&N?sJ((c#tZsHuH%eopA*S=(+RH`v9*II1rToYqwb1aYFmQF?R6Q+%0@if`J zN#7;Wz7@+w)+hE(d3Y%Hef4Y%Dn$CA=Im}`5DAK!$X%8MH&3L>c@pDZr$&SFxmu?C z!uiS+`J34-Jb@NLH%j_2!`P z<_n%B@rAKtYA1+wGI`H6cz6X0wZR#glZ z$Hg@xE^qE6k5ZcD_sYnN-6F~*8Vt$d9u_1r(Z0r~fj&ODw4RJYU1rsKHDae6H8tMR zMF&qX2Y&?XFs=PCp%*kh%xzD;u|%b{U00NS-%pe9Wa(&0S9G3IYaxPif$hY3F7ilx z)yR$N;ZTuJVryG@bFt=9$P!Udo2DnX95TB#!7;TEH8O*PO zio?1K>Yg5bi8>fDWkpAIPF^ZxZ-~@cS|ov8f+e+RNbri%0_07(-<{v*@HynYB4@eyTMRsHa_a#_*}OF1gE3^WZ>Nejtr`2yN2Ck^ku( zDT}$5UF>jlsl;)o&WF=q-(iXi?|ok2v_lN1w#hU`Kp zXiLV4O3DwVR<8vJB!?sf>`bR-wdEx>mA$<&PGWfcB;bZUJlt|~xf-+J_`dD$(-fER zDB4-48(~X`C&uR-ZM^{zL&Vwd_<2b((P|8a@WBt^YfJ{F3JWBsqQb=VsJPg56RX~! zxto{Bb$?org~nj59!)9gq^>_K*i_lV?p>-hQOBAKj{mE5y-!Xtab|DKal2u*wQZM< z)=yUv1&!Y}72BuSdeqJ$6Cg+yJf_?}jF>%CfWAlEoaaZ2BO()cbTB%mi^A>qi8<&i z8Xu{1n@ehjk&f@vzMSmlEKI)TJaQNaKN369o6Dl0Rpa&7KN#6R^Kug8E^}~JRH>7N ztgo~+b;nP~A@b5Z&3Ck&@8E7%erk@!4w0zMdQL;t&R zL&O?$D{A~|W#)9Lxr*wDGcKeJ@jn!m5gDh|)us6k22Bc=U%wn2^U^Lti%BhaX^r{F zg{uC8f5|t791P*Sq$LWTaGu+t%Y^e>WbSXLE`JUCTxBEY`}i~V#(J)9d|?>RA{f7d zFUZJmlYm#na>1h6&nDynL7HoX;Hp?ISTu;86{vT=PDZX334z=A@4&2Am3F}|4X`M1 zDa5NLu!Er?Yp!iVCaf%Bt}6j4&BM&eSUs4X2nu=uwv z$4}gdAK}bvwI^`LrBYDrR@RRnPYmOPK zZCO8gd6mN91r9%#L`W7{=p8qVxL);dd&|h~Ut(SrbKcs-3j3DUYFv+S_5hHQoSpcd{F`4q=ZwROT2pIzfQ3gr{)AXhRb zS=Z1W`RA>7pkI(Wui>I%nH?stby+2l%p<&b(8lhEE2hI+@?IP1x8l*+vx_O+P(<|Krt zRWPR?qh|GoQ>V95pQ0wk!$IsvyUsK$20f*Oo5bZ~+|6KlrP7K=bq9+6^c@A=0W>!H zx@Kg|hK$a9L(KF1zM04(Rk;t3Y{M0@Wr9p(HdBK`Y1G->E!7?vd)Xhc)QyZii^^23 zb}-|N^TJ%;8&T4FMt@r!VrI8jqW-IeAaBhFG`X@DPc7|&ym=YzP3pDp-=RTmc#JVpRT0uyPB~h@_R;&X zy==oBTZO%sN^;p&KN27XR3nPod(7)vyzL;r_~E6~VsGDXHRW&Ah-UZTtC-@imi!!L zin~U~`@DR0EX0jP^4sZACBrjD56_bCkfKcASHRcCua8?RRK4z$XR)CAC+L80eCS_wUdkE}D9y=&(4`O9FUM(025 zi--Pcx_@7S^E+$(_oZV&mo&>R;vYby=1)y`tCA?t28PwNru3DjM}Z03OFWM^TWZ}Z z?_)0JD=wf5jDjK~;}Hz>Mon`QS`xijC4*Dq{%+~koXf<)eF6q@0(B|(y3}O#7SZUe zdl{m(jREj&0dK?-wOVjPfiUyCXx$3w5&krF%Q~CLfyva@U%KU%k;VeVA5S)?={eq6 zu+HJxnSwr^n7z}Kr9}klHZsOeNmViy{%Si`B2;m3*mSR6tKRVuY!H*!{3xxl#rK;z z({QCGCW-0yCh)!*v*!^=^FNiS!j4HwnTfNjUzyaMQp~h}C%Xv6X;b1R#quzqy^?nD z2=vfLsy>t^$MZ3^N_D8R?nnDM_D#idwOUFUjY41St__;4oH#LCcljz|A%>(yhf)Da zkKH@T43ilXxO4KQ1&`l}C%U_lM~A{{C1HA5_cq4e?j_YTX=+T7o`*KE@@r`W zDia3&jd(6?2WWiLndKkr)Q>z*Okb)GS`SrEt7xwy%hFZHJTatJ*KepzbxlC`2p}(C zq$gsHE`OmW&FA`77RDvKIABrP)$S#6GabQ2}i&q zeTiNu)Zr7X+&y=fxmkfq1Tn2B^P{!d7&0%0lmxo;3hkEdX~^^43QldB9fqZK^e zOf^bxRhDUed`6OU{fyL5lB)27yGNJ(e}J%Rq#W+#bfU(c!>>L!05E z2dPcPQKV5TJHT0M7O3A~SzZ`ij6bItsT+{9?gZKEM1abB0|L>G0lTdnfyuYoI&TE8 zziDJV>sAB2XF>gqhHa=33sEU_Z>9G1Iil9DS?W#)(sMX<#IRdEBTpOig&gjU8Klz( z3QCBgGWXag41Cx|v+4UxH5EW@xk|aivLES^;F#c?;FRDZTJ3A_OpVErkyvhW$H8CU zdizL6>4yX17ZQT6{YP-K>j%EqDHI53@c3!j!BVJyU2T_KYS6jh=09<%FX{9E7yZBX z@n;kYbXDT<68Jw9>fB0PX9OUiy5i>(UtRhF%?_kfxWMoUAPe*dXf|L>9T%9)#HF&8 z-!1(+FzAvh+3(P2y>T2s*5Dc=xTGBRTQtBsfuii|;44-g?1`V1TC;#XvnvTKuxOUE znLS{-c0lK%Sr=CQcN=HsVh0-7z%hznvsgbl!T*Ij54xn_^>0pa)*kq$oS;YXLZ1^| z3RUB^;v?m>2M6I_l<>1(vs*cfT5C~`E0PBz3OR8c?%@Vz(|37ssG52tKZ;0BIGFAZ ze{1N?RF`nll-N+Sua3oIH4AH4B@C@&umVGaTsqIFUMV)Bxhv6mPWVxtD?cfnYiM%>huwuyWzA~lh&CCnd%F((-M`6ZHRB3FGppju*^DS|q zVK7Yo&K}E;1OC`Yp#>!!UNto^)s|4y+m%$CbamQU#`iqAiOZhfB8rcYm54z39K%WO zSe@@cB4BrO7|IfrWtYD2o-agnk;#YMRX8C+M&%iGZsvV=^SC1%bVgC?17b~aD)anw z9;$?I{0wzw_oA^t2L`;1Sy+vuHUa_PDb!bBQZZZJ$X6|v-Sk!y$q*FSv=yhSLhrWy zwBMb^Cbc&-RO?=f;c!pSX=J|GwUoAOM&Q^;(#T{dAdI3}ON38R{l!>Y7Uh>A-l-U_ z0(Z3;cmi0Bc3RuFj`^;<_1Z9)3IYg+IA4sLSSw7GK9{Dx>|3I88iR(;3%91;ucEP( zO8I7{jc+_2r!~4z_#)fTB5SF;7Oz7s)OXe)rqP?3Jqck(UfZJH`MG+f%PWb7MTcR8 zZxsozECa;}kVVVyuhH-JO3z^w+|iJbe9TtT6QF0UrT0&@{H}aoo}w^1c4~FwxPS;#2Px#KBmd(i z#xZU>+nRk;BdVN^8X0+&Y(h5Lnql#nms0)<#)Widsqh+)gL!)@6n;Q}3QXp2LgsF4 zMh9}q$@FomW%Imzmw=?f_QMcnpTwaP9XY$vj6IP+!bW8Yq%AMcejuumSN$P((xXdA z@KYLuKeIO6efktrn%l+&5K-&TD$(+l=X+H!@QUVL(rp54)i=@xl8KdHh4F+7M}>6bWZwi5n2P@tc^60ay= zKm_U$(HwJ;r5#$FJWI$-V_uI)FGujb?on<;uQ}@q z=3XuGj1L61fw9S#LB8b0+HLjYr^L_lGO}?r(2#l}? z4CTMU7gqJGNC5=+L|5(0)$+u@1qM2Ou9#$SOS7NJxq!2aR|mX+U7H<<7K4j5gDwdh zof#)^Yo9eQa{$)+>SF`5`2Jw$Y`~#01OEI~^rdY7ZqR_IKsqrJC#~)hnD7R%68~?Sk$BoLmX@&Tms(r3f?|c+VN*%?Mjp@8ozOz z6+HM@R_bxgtF`j-uEKJsC%49ZMAdQG3O*;$KFc?X%MZ%z7Jodpn1qTV%(Q3(HyTrH z8hmJ%v>4YxoX+!b*Zt;{(5N1{#|Sc#C~5o6h2Z5?JkR{&6?PAhN$ekbmbBpHnUJAxhububWZE=ZQ}-0Ae5vegHCH5MlC&K8grw)sJQt>F z#{0}&g$?GN+HLLbJ@l+M!?35wOt7@KrL{@mV-MgJwIIq&V|Jw&Y~-iM<&;!EPejfO zhqmmod6FH%NxNu7py!ytah?w4s#Ie+9TIljA};jvL8}W*+|;|(Mvwd%?NDu|`bX}x zdPY}|bj$?yI29c;Rl^%>Oo%{3n6GvTJqnDZA|xH}`DRyaoBe6W{A~0ar1baR;;)yK ze!n47&F7k}O|Db$SdNo4s#x9tE^?evHCC%5fV0RdK`T7aZQgz0Ag{C#mxXUx>>w=> zbEK9$AqE3BLeNRA!hUjnUqirat3vIiNz$4SzDcFS+G#{c;x?>06D&`HG%p9^Z2tl! zvREXRobyxfo1!E!C#CIu53n~dr$695Rw@Ts_92N=3d>v8}>FvIYNMUK1M>vGiB+W9gF`q<0AW9F8F<24IXF5PSQ1 zg@8A5=RcUsM(#q;?!Py3S1PPP=ll3WBX?C%>k|0F$guXfayqbw_B${z<>3!Dem29G2~5%hDE#~b^jR+|xTFU#e(q1uKrbpYxTMF` zt_iTu4GjMPy!Gq8{-s*H-+e2;1A{JU3H=s*7U2M#=xcBLk{sIa(9A%#h6$Xv4&>7R z`bz_*`T;_V*I6XMH-16?H15Cm_5T;+|Ci)k{%zbj0dD!H#(hIkU3vmA?wciFb;uan zh|8i($DzDE{ra;5%Wt=NPt=*^R?-F{eVXYDOIh+p9!CHfjf-z^a(te)`Lfq2qy>S_ zN$iIAJggT70zravPU{{V4(TI7RI)IVEa(t}**4Wjc8yYQZyQ{8$b%FlSeznn`*!3Gk3M@Y>$lQW~9tKF(({0FQ zB~fIeJ0EYsm%*asPaDh{@0$6KXwqp^zC$AK5JVF-M@F9~aEg7-kM6A=6IT7ck!zh^e~CXZ|=m@{1aSFQx^pE6^#)ZnMhpv9)}l zY+se|Ube9^6z7_2LGGbgUCnqMG^g%kEr>u;DT0bMIr@ckiW15Jw3hx|tHi~mZ3UXG zUNjsQwJ#2c@t>dDA3D1^tV`nln6(D86lP@!ss^_NPYT{&+`al{*G}93~*O+M~v<4deGG-ros)rzLtr zzdcRj!jgxgs(QTrGRn59^8?;P-30Ay9n{@DDcce&*R*f<6v}f0_7&H&pS@S{H6;2R zA{Vsx4bj67 zCA#iS+);kkPiBZ}iqBmCGE`x{;nyb;8NM zbK68D{=ivaSbC~i;VvW(iShIqCyo%QL*o8-Ki=wH(`-IVP8J22kpxl;5WxgD;XOjl z7FIy!^SXV#T4;4? z<-Y=ht`>QLMY97HVrK)iu3h$5m7u_*nSsVYKpo*a`d0>cW-7ovHXA!IzaE^axTGEO zJM>vJoD(R0xW4xP^u8`m?JPGBG&o#CpXbAW^=<1zC#%yeXrXDjy$MIIh32Q*4 z)onz{a-mxxky+cr!G6_$Fiwps!HOV6@H+6|{$|l2+d3TnGke%AFiNdIMsw5Qg8}#f~ZgLhI97UW%0O_*$%(q z@^G0p*=x~BCfD~?T0;uR5PV}|OgV^hICYvY6K^9HpnwME%}a&oU{NC)3^cq9u1?q6 zy8WKPHC)q>%Y{ZVpmWo-r@YqRfWu}4X{+$b%ZQhA5;=u@*5j*s-xsB0tHuR4v9rFq z7zKVn_eDS9F_f)BJ{V*PB3n4l@0w3$OQ2yldt*X(Oo+tp8#o^cEhJsW5sCItOh8b% zSB2_jrap^JCYN`_u<>Msu=9rw4^XD4w-xy}zrgJWC8$ixn0pUPgRrXt^X3%_KYh|B z0=m^nd5Q&AAU$cL)nX20AbMDobb9PW@u@%|QOSG6#wF?%0xwo>Cr;HAdgJUHMmw{- z!FM~V;;Jx8XGi(4j*7I}W$cK7D4^brhN529sCR;SAsjBD+ ziW;Gp4US)NgBvY_TPwz-Xi0O_Op{$vvGV)G{gpNBn|6Zk#5yPO)*&QAsEREeuVF3+-v9M4{yy8I$V!BK|P6Vgb*V>Ej;K zZfD6>Jhq$OOVIJfCEe`_i~8P7`1!E8zfE37&8<>g04whZ5&~|U{r!1A!%vxPkqfaa^z)mhJ}02T4g@slolk)Grz}x zx#9JE8_>nrGE0Ie>#^$Vueh5JX~+^xnBDr$FH|cqzn9#r-34#l&@i?6cMnWV`f zLovS^G7EE4xU86jJhy?k;|lF@aeY^(Fjg+9oir##g|23);F+eKxmxIiaJ@qb`2lt+ zB?-=17no*v_h+A zjbC(5C5B;gl0a_=CN%~oiC)*R#j*JY?M&3bAKa8wgtvLhz3cj$%XXyh@pnmeIVY*tK__x471^X{v;~9|v zw=_Ek5ZwT3Nv|#qIu|;-uxh_W1C^2B6e&UHiWGl^W&@(|OuzwMU;8Q-0Jn2CV0so1 zo4JN&zFM9L_PKwD26`|5;M71sMF60ge{F5hRV@s#YXiv@K-S^<&Vm2yAFRy^bcb?) zNt=MKC7ZyV8ZaCdD5C(Avbm(J_LIf@!x#gjFhIo5)a=iEhCk{R0A1>M{x_xJ0Gb#6 zl+rXRs@p^Z0f)~@x^1_IX^jNn(Pxa!Qmj-&@(TDW-O|IS+RFR=O!-gtroWcK=n@tb zNmE$bZ1Pfnra-TJ2;Jx~-J3Ec_=Vh4XxZPe>3%eNw->q)>6_$3!_*9U2g;~Vk8ZIH zq*Zn+7>n`pq&*wu^?BW%1ChZQL~7C4X29M;YL+u4_y}9j6le6w^VV+IcbG_N?BW`P zllUpw`b$;yn{F~B378riLRZd>uCmya`uMW zE#cJ(3JZNCtxBRoB!;-PdjqTf$v5`&>$D%K$5(%jjT)2+gz5LRL|y6)71U;XU|TVe z(Z_@aEvD4F!u0^x)dw;@5NB#AgAPk(bkySwrwDcL=bqHCw5r6>`;z_oI5Jo_!*qy# zC`$6?Tk>_x>0o@6QaTn*h2$4jWbOOh(%AfHcMZuXas$0~Hr{`i7TtsfB8>?aPDdu7 zFv*F!K%u}StLy0v?errJRP+Y4_gpSPB@caQk$6swYU?zl(@XNILe{k&>$6z+8Tfq5 zm7IWEknLJ)AtKjmRTS5JsY^>;cEZD6(6LL}^L}mh>ws!=Qxk$ z!`n$8xvHPCj2o=x@_qES+?w+1so|WD%WrQ4leiQ4Giz#n3I1&LMDVR)l#vfqTOQ$K z;?X@mG~AW4fdph%2WmZh-7kew@Ac(8)T+diIyXYBl~kY<j-4+T&=YnN@&?$!^YW5urCqHbBn!)3Crw(DQAtiyG#rN71s8{aUW|! zrsA*yXWmQj6Lo=dI3gG`dP#Z)yczwM62Y%JnV@s6oPT6SuU_is`}jjMdMzjXEBL~U zvICI>4$$?~D)ZIq>oX_tKS7MYLIbY$m0KAcnhj7wX99PpUy{o?v!h_qfE@+Yov+)I zt6BwM(ZJ1rmjzrJ9`Lg-N1ef~%?gMNF@dwA*Qyc!4jRO9)s}%pgMi)$;BLRh0In(> zfPHQjE?`JEkWjde{xx3yyEA72Qt4n${90lL+`i9r4w!+W$7?HJQk42>MgLD?0YHV~ z&$s=bSO8EC^M|p3#-B7y;pd=nI&*UgF^A-Zh_f;8KYM$)K}1DWtqGqlGdc>?dMF4flEY-omy$ z%!-5PlKX(a6TEBq$$Hqb4~=Y{h1C>JcBluH@E=#z+J+Ui+Ti$lut%Pkz>GlphYZdn3+z8f4W^Vsgkl(41{`|?nw3Atq{2{bRZ^JY6YHtNQ6GM5$; zY&=l=Y-g82_^KRl=593II@vG0S^UxoJcW@n4-r;224X1 zB9+$MdpAiN3kRwQIZk$o(z$&F3{)s=aynR7?yxhj(Q&xy<)9DBwsu zs#C;sG$33Sw#nt`gnH-DS`-tErxoY7I}n<_n9A{M{NEzgo)W%gr%VtixckBn|Mtl3 zxT(zz-=>ity|+)$F|j;9e*Y*X@)2Fg%CZ`!?^P|@k>?j%Uj&ra_c3WBkI5UEtk=pH z_DKxf_-H%sn zrBZPMH%ph}&h>cV=+Bu?Q>MS{b|pVx@QcgD=rUcy&N<-6d1mV}NgiP$FiKFY+sIad z@79tHjVsAGwsbq5byX*gBUAgwa!`BDZJ}^p^-fjun)POdBZN2llMvIzN~6w=Q=%E% zf_sU%`lfVNGvjfvtHp|DjN%F?aekh1r)e8qrU`m2dRl?2!3VVDHktShHg#`Pw_y0set(3hdB5 z;VgZhG8a>v4;#(N-lB79p0*xbaxNbTTr6QG3Y29OmzPaopSm*`Ac)Ia4+@U37Y>)3 zJM3V^`|EJRlAPaempyyVzt!&uF1c~l*E`?GA5xNQ$>?9f7o>uN1u(9FTX)q^Fkh=$ z|2ycjWXsR1{>;FEL!Y_!>|oTSL05b4!J`360*G*5+d1fJ?>$)bnQPAm4t*`F18(O) zm>n462ga~p?Vks`_8A>IQ%t{l=Af(n^Wf2dIu^LKfvEZ)ocWoy7C1EMQVZYj-WVY3 z4Kx~D|5`xT5;NdV?QE_I3sA{({keZ72ESXI1sFTY45sD+bp9*52<7~wH2*L#@JF!# zV20u^XZ~+W!+9Y!N%Gg}jg44wi)1GB_RV8j`aK!NJ7H!_&&7DNofLvpswCO-DBvJ_ z{es%DM@_dkc-mmG1!NU_?!+0Rt@&;_E^*8sGCmN0*dI6cxpjRunsq^EMjKUSl2i=7 z+7zx9_08l{LyQbMoyP$*sB{Fqv>d5#DKum9tk{~BlL?c(%wA1UVbv4W6u)A=E2;mG z*uFgeG*$M=&4=|iIIV*M+T8VZq%>X*2JqA0h{gwFY0GK9RWdxGUVge?VaIV&Y*Xf3 zE8|6&L>BiXp2Z|wobmZE((EknZRBGjGnS)R5we7&5X`Tvuhg>kZ+%u)=E3dh-$K|= zXcP~!yTeXQ8~l#+)`a2!K`;ybralO+LOzT}^wvArL}5Nvd$P)NYsif#-;S_M%|}#bb(C|ZDm1iq zqPoXL?*mWY^p^r{1m|8;Vwb_hZ9Td6_SkonnCnoH8%G+LQri=nWQBY$(pk$6n~Kw; zGuKlI7SSGHz&$=j)ZtfJ1LEqe@Z`+-|^Bq@^mJCjVtRd!DPDzPaUe34oa}# z5QRw4bVY6hmCs{iuGQK;nR>r_bTq)e#bUh@>(^_-)+XIO(VG~likZwZ01= zBqc>aKpK=3LApf*6i|?oelsXu5w7>%pT0ld=kxG$oHJ);&t9`<&suA*_^yl0YEsJ& zahr+n>XG!lxFlDxwJqLSj#Qc+AX(QJ|X<^##<;SN{XuUp#OHYs7e5w z^i{7u5uJ%SQnG=Aq?vB{4^|GIH$D?e7m^F?C)|~H>gs@K2lTGoaJZtkYJ$Nh`0^^c z{XBZAulK~Oaf)&;wJ3HRp1O`a^?;Gf=q-XuqaC{x(L_k2lsKQ=D^3yT$MWJ&73W{y z?BnA6(Axd4Eet@B2Y@#Kr+=@+!Fh;4phU%a2nle!BFEQbM_lYHN&jmxG%(4V0|?0i zqw`n+S$bFy7pSWW1kC-SjH;2Ht&54H(=|KM8%EZ4_SeM>oD6;{+WVF8KTIS9AQH&! zJ0cP+;KuU{u*ZL<5{!jBu6!Im?tiB>fvIeN-}o=B39K!4QVz16$cXr{>wjtu)PegK zeM6xT=9B4mke^Wt0B8kp`W=T}go1@%PtkfHKcg0$+8P4HOrA6;Kz;@uIJGT+#soNG zPU<{tC(AQd1 z7Jx1VEki%|%z4O4j(Yw}XZcMt%zt-gK#pbA9@%8T^q7Bbllfjm_d>uGWqhPBU7c$< zgAUnove{Q7b;E<-jC!aMO;Q}uJzd2fbSbo@7s2EDM?Jy zyWw*tg4-U>sN~S?7LevP&ycoKOuFEenEsPaCV?_ z-C)Dab!551xlzFXIT5YTi~Lak=KK7Z_If7bSMe}c7#`h3Y2d1J^%kAZSzW?jf8XeG zi+64tS)d=gn*B_ru4h(XL(;nslwszVGWL;6b7F2A{=+O`bYY_Q!@gs(ce9gFyxDvtFTG_Cu-^ zm)@4+Ue)skxFW2;m=v>{~TJB*p+S0NpBlr&_cZ>16 zWNI?aUh=8-hfYrz=*pg(op6or@{N7!gN-g>82X9YJtbG(uA5V{lF9B$vcWOl zl);E6ehz0o=j?nB-mEY+itqA``%jTGnbwBAT;q1EzTEuccxUxmQg7ivf8*-hyN@{D z+GB64KH*VrzlpeJ*X=-U-=lo(6Rxj+7*hBq&I(m!5tCudSGiQkt*mpt*gN;Q(M%kn2XVe) zePyF5&4Qk_Slr^Cl13jthezc?_v21d<+zP!6UhSQcU>L|jcplsTuSas?=>~S^su^3 zyIzE7Wc_lr^9r^cl%xR1EV)fC{!&;B`iqoFMmR6QLMeG8!GW1f7-mPFFr&S+r<5Pw zL6z;t^lNSJA<&V#u~*Lc+b}mIlxX`7N;>#wGrugJ6}Nnumyky!a8*eEjc=4Kjx;7G zjPMw*p}TQ5{jP zU=8Yg>0385Q)}6@+yN@M*VH`mo!ism)Yd*$G|7*dqQiq8nHig9XR0v~ms>(=A6Z6= z$`Thod02S8R_W@nvjxA}I+AIfDOaN^CB;B5T)C=-q03BH;k?-`Wn(?kh}Rblmz>eo zFDfI6(OzXLh0zTP6Fnn3y<9a+9NQU^41Ynh5_{ybBGt`BE31_?Eo?U13*pwil~&k#yM+xW+LEXnYm+8RZjYq(qdRelRx;ub}#M zbfOqn(|Ek;*&23mTCw--LYDBBJBLhCO_Xg|W}ix60}VAJzq%1?B8%NUvyJ`k!+EZE z^$qm36dzXGnh|62yQ9Qs!Nv#$GNPU}zZm9KRC zOC{`Qz=dOt|5Bq)1Kwu)86)gJw1xa^^g6XIh`bFwrFt6}d->N$11iDktpVh1Fkj+l zl>mtM_!q4qU;*Y+w2_~o8cyvRtlG>Cgpd5(HQUeGRsX3q8*jVS{^`0{kd<* zVFv1vCiHiM27p>JLr;k&h8zQW_}kV%aTd_FcB1c}Q>Ra*oShq3O##NFldXT!)=zH@ zK!!t4!OHylf*sxWUmD7ZdeGh zu{s0x!o_<&MLeQ3SJ@lo!nszB^t_ULuA~%;nK{R!Wj>}iiAbO~z-LQR^ryR_ieggn zuCcJcY-a=4D85=C#&-1`@1thff*T)nJH?X=rpCu`32jR+u0HFVuC*@FiF9mvG$)Xm z;C#^cX&dD>E(YyTg@pF4i$26nZlAYjdTncyRKnHP^KR^o+cNJH4u7t46hr>>fq_YF z`c)DSp&vtLEZ?-v72Q_uR(4q9ATyD1@^-)+GeR=-pG?543N35MB6&^Lf&ZKH%vYwvsqHS zkavgMYf$?EqYW$VMQXVj+)0!u2dWMFByAJK7}9FwF_@8PrQ1bLlR}364IRZeJLi}n zJr5-AuRis#Q^@8L=zD*bypOoC(Iz?_Cw#6lBAF*}jJf_YgF*f)L3sGs`$Iy|F8BG> zF!>QizKh&2^IHv=-Bu3Vp^*l@=jvz=5XYi%0@ejWgHeg7WeFR0s2vP~48u7wo;-!6 zM>2U69jQ{lQ2jdjsujJs;ycm>z4)oND15EHOVp)(fKfrwsyn{XS$ zuR;0hTD2U)%ksH~3ry&=y;UEalpIwqOpBMw_w6v2L@Zfz0cgK5?bH7M~}n!k}+8a@W27hR;VP zriCm;?BY%8xS`i%%}cBLoxWHVPo8*?w)n9kcnQ_2G^_qz7 zgQ92VSv0Y9@e>G)mYbZ$E@NC9}$ z#}fOJ)@>^9{WDVE@zhOl6g}&gg(H#(N$XUHX;*qtkueH6Xn&_IpjpwSMVaMh*%`4|I?*bJ<8DSMrNhu8*^9%9hoCJ z()q8>b@+Lb-5-@s8SB317uuiAnUwLNoaB=RlKty1AuKKTOWv{%h!1#h5JAKTfhvI_ zih4^iE!y|rTTYS@*YHz%P~dV03iR$Hr(!%ev=^x&(a|=v!=m)z>2xXCYzZxV2IEVC z=+4+$Q`$qxCt&3XUF+cIX2d}0Tp&=~UGDam^CntYNxc{-#Wytcn(3CixZ2Hu^(yj# zZ6brGgF+3OMk?61nK;ymor(By8KQ=(=zE2>TV6#@T)fdv8H>=qJ8sgg%iC2Dbv_II zedZg^iV&U{Wjy$TWIu^|T2T|)375Erd$muHZp%gr>0w3a&{EiCza~d;%C-Rp` z?jKUqAV1s1jx|0~fgwOC704-xc*dM8c4kV8;` zBZcnoTC)MM(O_Ajlgi|evG9MXga6VXcnk^szZT2`6WRZoEJqq38<45+FEzjd)vq?d z9W`^Hh%s>(l2jO;z&f?_%#)-iZv*?+Uai4Iq~7sAM}!k8cB}!zR{uJTDPl?t^nqKREu^|Rl$5-fi2tB1b z1Kj6ZP1}Lb1kF@sZd~oXER5uaE=Gr*Zu6Nvm6J~mzDjxbfd<1ug%)$sY)<^-{mOAP zx%&@#GQyP-{GZ1>+SjomzKWsS+2&^%?Q$R8C|0{N*}CHE41o73GE~!`mok;>y7`#;?cc1i$!^R-G~O&$&{%Y z!UNl45p15qyKZf*8Uj-~aS?Ob4>H4Ox$n<1oks|bZXZm*en`bidzU2W%xGK%{FNXa*X(K!+@1ruNz|$Khacf6 z&cg_+GQNW6f@8`piQ9RsfvJ8Wi7!f=&!8pQzQj~u0w=g4pAZ$HJiZLqeKgdPL6-#@ zIuJtpzG2#^i{|qf6_yPr_f;<@gg2=4ekK+BYjb%`%|mb*LmY8l^6Z-PZ{s!2=}F6_ zS;niyiZekP;)2gs@0@i{k_*uPprJOx|0X|=?Bd1v54F^49B=WkWYcQMUXtPTk*cCq zHElm-61x)<`<5K{@tg}LXBgHDlsNISx!nwQ+--;84l+7pYva|>8D~q$kygwcZ7IBz zn`HiQqoTGgZT^m#o>HuB``jH*2|K+nUA{X*GrWnoU63UfRBfg;{46UyroDW1)4|mA zQ3DFPW?7v~0@6F-mQp!y7CweJ%$&Eqnm3X1dk7=_-76=j1%1r!q}td+h9aP1yXPt< zW0%5lL-_;E)?vEn->0PXB{sdg;!(fs=(rs<hWrR(MZ1tkuF?9)$U==F<1Xyp)GoH!kGcSPUT2k(!T@F)P78WR^pr zV9+%0l)(OsF9qk{+#{=5(7g};z;T7)6v2PYuyMNJKV*K#1^*HH&A&^?I`Z@WW&48s z4Eh2&q~l-OzJA7hIo9|{bOYF6Kuq*WF>*ox{@C+TV<3YCumhc95BV9j<dbsp-n%?A2)#8_q~?*B=Pw!KKHR>4W6Uo+p zJw$%EX4SqA9K@Uv#W3kYON%2KwVFdsR+?)`L~^{EZbv>3zWSn3XJ*=%*Q3h$N!-j0e<9Vj=~zCNkt>-?Vq!aeSH8 zkBL;8ACbqE`{+g&C0pEM+D>Q(k}YKlfdz{I*+H%`LP>NGG;{s2d!lI`c~DH;h$Nd> zGUIibpu*gniXHq3)#I|y%%^=@uj4ybCDJ`w5xA?nnrX$vALNeUqlz7j{g6WR{CbP% z;CZdCvWJX>GX2soU^w9OpQ$1ki|ljVD?V3~no5llriWARIe4qRw@71k(rx2qAsx)N;o(aZ(U@FK`t+&n(Kzw2 z`Dd!p1CIyRPXtvmh@1K|<|Zkx-67pSg&iM5W;&f6AHLPc+412r>bKTmKYBnw&HRv# zf60!224yk0^2nTY^Qt_WxpFb=(kJaz^ADj`ueE91&j)XekBKo&NJxW#BZj_3kc1|sI zgH2Q5h7)i>3@y*arvL4(2w z3pXjDmz7Z}B`b`kOrpf90~3T3v=(#c+?8}3*}18K`=MS!HT(&o_I73j*{qF$8_J)C zO*2CRE7s{(^i4bG@-I?8k}B+cgX^fKD=X(B z{}j&?$6(Q>vU7_U-zSiwOu3ZE{ZgUv{-CXPWG~5B;W#w`1MTd_+aZyX2o;{Qe&Z@H z;cj2mqcDe4!puin(K04nrHYFbXGME$H2;K`3Z6Ihyl>!^@y9)eJlWY029`ncc9%Zq zTr(2r?MU+THFULigncbU%LpuK2K@>A1=gwZOV&lFmrCV$Qx>zLZw#;&Vd@eL%qJ-| zjw>>cN$@R(H^x7V)keTFp`&@1-zF9EqCONy=?V#!m+CEgq+!0`uGh*!R46yN!pPM` z1R}3n4N{ZRTyj&X91$m1d=YxSAV+A3DQRKaqkpq>z#(e~rm4rO7Eac=DD`1STu&4E zxmL%`9%|-6>1e-%C@pFe!LyScRwaEVbgN#^RP}1Mhp{47A0?o>!iePPOmCi_){eiY zW2yBelo);ba#`20RNEY08ZpGq!nJYKDCEfC}Cbm1K2W z+?&ydFV|FQ-j^Kv&R`I4hgf#ph4?U(UQS1QEUEW4_uy6$a5f2bqdNHCw$Qy!4RbA- zEfpDxomiALjmWuH>qr7!t-AJr+K*={6v8Rs*ye12u2G{0OPIxchbCMoWey3?HT`WB zXY3_RDUwwd2Lzb@GVP_xp7x{iBuK5JR|$MZ{e}}P>Cnu zhT9nxnx}$$wgwmaB5;Ctx5bHu3b*CnP+9J6?;}qZTsx&O1>_h^(&#}r2eikfU9+CX>!Qn{5+R6$%l*7M&P8lhPlaCmI64V1JBe%w0A{5YSl{;Bm z4B47-8NdPFc5Ey{F=ZpR$7wQx9u(>_)`KYM{A8W112^mFYU&y{Rg*snOl%d*v8+}H zNL>-YOOI_CN?;LK+_{KC!*Y-Qp2!#ab-_uYce!qR?^CuuWk+F0c)O9U+!YH@spU!+ zY@A*9!;^V3#KK-if8jAdBLYNmX^)5iPu=;}UQ!qaWi!8rf`Z51n%f-Uj`}c(pYU0c z*5(e|^fD*PmeOoylCJ}ScpAKfehcd~L-1?W8NRfRN)k1yx(g<~!i@&>f#g>jk=pzq z*!a>`?e=%w+}INo9w`z{Wa(e+U|?m?2*i?s3nps8iWXB{m(W(OCX}N0oQVFQ*x{6~ zqPQDp%zjlm_j5_ROu=I;cCzaPI0NW5cZ3~?UPKuV)w~V=BHgzti|fX`MVy*#cl~LA4JHW1?AR4)L{Kg)RxS&<0{|DLpl~#RnbTSvrQQ@FxSd(8; zKgSK7=iLeq%#D_Iy-^q_j7;Vzu0VMs%lk25=Bv*MSGwUH#OR6fa`1)_o&0@7=IuZD z>UU2_=tiVEh8J?4JvSR(;difPuIOmZ+R#2rHl5Nvvxb8d6&-c)g=LI6YTy(-6Vm*7hs6=;0pi)62N#iY&z4-T z;kLh43+cC{=UB;C?f$G6)>b5)siVPrhvEVmR(q?J=v8B83g^cMGOhiCkBQQ|pLbUF z2znc%!7=MyJ>#^`k)wB8jKVdT|MC{*u2_ondn&A^B8OP)(e<-wLd^15W6u0`I^j*+ zF5;sq8CwtcNzX;HDD;VL9q_SVTEARCxl+UvC**j8AJ2T}xwMr-x$3iiVq~gC-KX(l zSu{~`jGIYUUKJSdo>!tRj@~j^iR@5n)JFE0uWW0h4GpY;hkPbsQg@LpKKl_Taolgs zF@}nwWXLYzTeTCb_s*88+BT zzaZi?P_s?oUTsQKRD#Shntx|%$mu<{K?hv6m?wTtvDuOl5E0kk0J^BF`V8Mwg@OT*We>Qz-V)+kz3pMEqxlXynlY}f!HT~X)<1S zw@>po;NzCiueGn+xIQgM4cnBl^uF_;ZjsQEYw-Z7V5i~r6W(dIMqvb^PRZC8v(OR^ zw8`#IweYwoFH29ZyP?Oz=}wjCU%ApTi4HxA3jB8x9eNo323+BLx(nc(JY<-VL!2ii zD##&X6SxKaP2d((_QCB}#tHyVe%t?=xd1uD3j&URMfL!;->&x+`~%qk>P`h>;=Z;! zM6v+S|8~7YbO~_(+w~4H8-RTv<@B)MLnH-o|1eD#*nYd-*Gyhu{~LXW$*kac-{?C` zFa`DxQ$@k;x9c6IZ-V>ZuJ^5aBjjr(RN(h-*ZY?K1NoXy1pNM$KImaGp%NAJFa-tN ze!XAlVQL4s|CK)IVZsHt|Mhy%uQkDd{jc;vza}10LBGau0^6_j>HJV~fPb0AeZIUqk^3;oQKR^p8ZbLrzcy&c{D9RA8l15D_1E z2bsBn_m2(G2|@fB2mlPr0pPK7D?+q0j0LTJ@$pMUv8GNY$TN6-B6#_6A zATybZo;lo#u2{L z^o=9@6HVMdkJB;4xZk7+fb3@lbnhdYjyS?U(ZqIQnjeGE`8}e(bA)dXj~&1j-~pud zKM}>jdSax0wEz7cQEW#e1x$BV!1nfiq(HML&o9^%+exZ^bP4_*RqUYK5s-*LXcIFV zpqj7)NqyYF5*oq*7J>c+M_@Z4W{zQX{U%iaq8B$HUqC8$H2jUZ>WyACzyr| zW*mHH>7YS|?H3}M?S%L{20HeeRDEMr05B#Xivg;>u_^!_4DjguVzQs$>Bq3lev_zg zZ{T;L00cB1K>PehqIgcQg+IvDLB9ns@<&7+X)pgs)XBMi3_R`khU!Rt`A*e0_2r+b zIx*J|mj!=DePIX60dWJ%o$piu#zsJ!`Dda|2%Ez-${!-?oBGKKxb1j=wb_xd0T5*Y zm(s5|=n19j805fk>u+HKF)|_l$0VH4z$O){o*tyt#!PZaks$Y09U{F^o|rzU|0a{3i_QV9M*v3 z{?*%eLev}s&iXy7jxHXaUerN#XVRe}8kr#c4o^?OtuSzkDSDsVi2<>`nkfI$jCYUba+f~QdR z=d|_jPY}@7SpiU#?@tia)_=7uJ%y@2Xn^@9mN@`z9WbJS?gST zp+)b{NE&v4dvgO`C=Nh6vjUb%c0l5QRx}P!S^vdUKZU42Xny%-RA2`XgaFG1pcMn6 z28c#t2O)%hr4_TESZo~{JO9j39Zf2B2oS~ssM|-AiXEU9So8d1s-L9l5At;mP5|5( zcyK^u4i{jeKC%k21J)s)Us1(&a$5a)ZJiyg+yG3cBW)eP-vgEszhLa_KkLO`&C-A9 z39GQ_K$d;@N>!H0!VU`YA;HIlj&Ya7s47M*&VJ&_@Aez5o^m z;DG{QNvxc|SeUZ^yfFQ0vHwFu^=(?QfgqWHvG{0Ou>oOozZ5nniTZ@dEz5uKDWA_(LQ0O#?l&83PjVh%JCRJWvw$KT-7ujW7Ug04tD5 zzy{zwumkpWwr^{AAS4v1j=}y5s(xN=ef9JFp|Se5hF}AXG|HRDnsGpc4XI-0)BVRoR)@0mlgFuKA^E%zlEXWAOREr-XtfUqIAe&|L#6 z?BH^O6EHD=?wVgxb&{w*$JfCiUk=bh3@raxf#4lZHUP*2upEOJDgXf6-_NQO)^+xu zgTTLf)c;+a7r=&oaEk$POUD`?#cDwT%Q1+-`*T$AS1X!1u!rgw289IRV(1qkg!7eXbv_4;}}Pfju0Z4{pKhAGP_XEqD#^1773k1GeD- z`USo5hacenKp^I$eegT@IiwFzwV}Xq@cuyh!0$)r9&Hb40FEE+AD#zX8*FnlE{EfG z$RvPS5A=U@Z{T-MppT>NkM{k3Tfn0L8vQkMz9Rr>0hIpm z^AR5b0u;Xv$kBuX2OK0E>;?RMBMQ)FzCN788vuR>&-sypAHRd`z#^7M6ND28y*Rp+ zznf5?YI$`2f1OYuEr){*Tm!rg_yOqz9ruS502urqCkc4Z;P2q)@IHZ|K0FV&cW~H` zjvbwMG}*whIXVVDfurx>@8ETg#tke42Hr3D8%PKE{l_i%`_XuOryV#4{0_csN5_t~ zM>HPZ+&gUktJhToYV zxDPT#@H~(q0k?U?XuRcymBwa4f)!9FED+O#}Pi+kE>D zN)hn9qjulh0E8Y6*0*DaL;-|@=K!9aNQXQr z%Szp!Bx7gYef_4cvUB4R!mf|g8}3-unb>U+vq*O2a#j1uv|$XFn-+9U6l zS)8l44?37O%P=!aM-ENk;Td*#)w5?}_IVJmAOp4FK?y!NVsUdLRKmA>VBk4aF4!Jp z4Tk2rD4n-YNp2-3*|=U|ep}R}{*$af;n{|9quelD2 zQs=!$?~TR|!R?=U7FIf5hiAWK_7=AFpvR5C+sl>KXaOOg+Ix4i(4wdG6)D^S>n@kg z8n)j-?#=zjd!?BBPG5?k+iDBDMoXVQZc#EFWIWjK=kD)_I)q{DF&q5>EFpEOS^M zq0b%5gJ-?SBkRNT(+)x)v>ew(Wk`)ACF{MIh)0R`Bw-rs=O1+1$ifCO=EHa(BYU`V zyHBxlJT8XeCx)55EN=^A1Ze8y1rG}FUm@tvEzV%(r^1ivDL1#nrM^9oS(9%@OU3{4 zUu`o{4b-1BApSj>3%j`*9 zc6mRE(#pI_3Oj6aAfe~I=m;E?f5Qd$nSNiQ6NWbvI9j+1998k8p{o8cd6)d|+JOW{ z&}9`5Nzv<5wHn042Lo`=&6fiRLr3a`CtnS<4>iBXX6x_@JmA6gBIVdswzgPYv)f*j z_3Aiif>DQWs>4MO9ep)`HY9Nn&dPB>TT;GHW9zP;7PRj#ThAC|U9iua>}3U$@g)hT zIAcEO;6dbik@HQnsXGTth(wgdb@^)r2g`6{a1oQb-Xs@hnZ2IwSq%?t$!n(GdvAv~ zRrOxa4)M8H9?WaDog}j2yQUvqOrJx&%wbGsy)Nr76M9{qBGlZ6^;zFeLbz1Ss_OM% z_>;4~^Fb?$+sdoGEJN7s$FRY3pU%PL+9VcW?pNKHJwOSBRc9WZ6o&U0**9pZhmr03 zxXB*cBsbYGG&{MG68EO=;X&pQ|Yjc0=y)a?Xq*zO5uxpKeka-3ln6HVYN^PKLc$A+5ks;Ew4sgt+jWmYsSiLuL&;TQ@5vQNS0B>N>7hZo<3J2Kr+ zSZXaY_EAUGTYhnC&2=6^%Bw;&r>#jJUDKjYxfHuz9ql)BVNRB6e%16wi@X@QT>X+O z4Zdxou1&F|-|hz%Sz5%icy{oRn*+@)nhw@`-VaJi6cR)e z<2F?ANgdV9Ek_NO& zKdKs6^qOuYS$%p~f+vpXix}gWl*PHTtLNPDsHfYqU^8P$e9tVA<4@$Z#E-#4T4dg# zm38M~`7KyNTC|>U``%|_T-3Xi*jUd>w2S-MDsIE%vz0pJ4s$iEo%p8m`!Dx95bTIq zR)!c;?BV9llpUgp?7^n`vO+;w#1sD{yp4zS4?uLNAu_oE($Om`3GBmCB=M zN5T{oqN6G$U349N%&$+p?`G_QpNi9qThsg4qNj0++2p0R%a!Hfh)}=tgs*x>L+nwi zSuBW(F{$WPCot!F0-Dxoi=1!SM~`Kl_o7M)Yk#PX_g`9hb@f4o;(mKE?M z?xk}+MBeBc32ZeUZD%ho-^Yf)i<}t=Z=n543stt$RbsR6J?|;lDYq}SN@iE6If+{D58c3mv+fZ^!sArGneI@QzbBF zH{i+DF<us#SfI2&TQ%9i?a&f{6stSQUB|&lMq|}0 z;*L~0a!?g$y;FOUX7!xLT4nET$_n47`F>pOy6#zFd}6Bfia7?h6eirM8#hPpT*2-N z+45ucU@j6p% z$hFZ%B~<7SA%;Io`i#12YSS=_C`Li)H=wc@j87C=yO4V=HI%IYQJ@+PI=*Vmq9?Z% zA<+4WS;Dg|)YQfvH(RTeDMlp5=b~+m-+cVp)#sOT`8=?jE_}Z8Mb*fG_t|+XzogIy z?hCJIasoqA<&>_cMvAe)qrIeVsgG%5HN(T}LGbF0%3I_$4ZJ5%=S$}AfN&L3IYY_l zyz-6tq42t@$>R9N!5jdxSA1-Cdbjyg{ z7PW(3Wc{JQY;1(0Kc|S^m3u<8p^*$S)xlkLl4Ja`j-DImy3ufvTQ<}w^eyzYina~V zRHm~p(Uny=>TThgPHjJB=-k-Vh)8^5E|y|4JLJ)b>|wq*R{5wZO#1TzT_L9KnT=%4 z)~SydH_wuLRFOQ%e@Z`T?q=9Z8DM;88L~!~>?{6k5HqK4wjx6(v+W@q)}ynV47ZK3 z_E0V**sJA3(hR#Y-0X!&sotp?#d=~r=aw@vVK zsVqs2+r8ro&(9^ixY;x+CGGpL^Ytc1mhd!kNh=&0gqfqK>39Sn4%g%0tc%aY6kL14U9cV_l z_Spq)^K+>P*(75|ltC2x+I`Oc5ttqOiB?LYu+mj!Jk9L+roD~l#-3tA=Z&%=@Amf1 zCO<0qY$rfq5|KImc*M@Fv~-!aP7%{afY99rYK9{bYkT`STGl&n&!=NJ5qEs1_MA*IgWY2+{@laQp1C5Zu1dC}ipIjPv3fRMd>B~Z+y zGe$2nqn~Fz!)YS(@%~sv$UUfQ2f_8lRn}CR&vXxQZ0E{*0~1Geb2%UmdT-jyP1DbH zcO>vU>P2Jga(aT5TrUZqo>F^es-GbF{6K1;A$?TJw)T)$RsW~+d__9a?aa3xs|1d< zM=?}B!wvRBrE5_V>rQ+2E_%hI`$Gci;|c;?ffkZV+gkXTjS7t5C2gN_l&+8ODxRkK zY1a0};Y}g$!PR?Kgk8T?HRGW^zP(FpjK-jChK7YV+G~U`NPpqx%_JVZ^_;V&j|Kx= z8LKR5%kIjO+K5y2h>a*6v*4i|Vvmvu? z8x$6VEZih)P8{-OzVj}-el0hmS;~1v+OG6L0h04(JzXqg}|JnN>6sg_%ilPIc3MY4+t=U4aV)zD$URZw3nmZIYCR zM|+fZJx?1(cnB{kLeI)47cGYvw-HqwrQP~#o@UOCVQnwPJ~lta{!o=#WET;?&i>he z4pssKHzi&8(d7*yp_}ym@AUnO-3wqlVWsjNcYJoX5mdAinVPEiYuY<0`rX^CQnqYJ z8Wqu4Qgrf1EKuHi%EDzMmxQ(HtJ?V2L>eeI83p&t>G5hsq9{3cTs1uizBev3bt6I9 z{BEI8rmr%R8lAx~{w4E8sB`UdeukcE!lR+=ve(PCVu}KDGKj96iNaPhMr2en*yPJh z!wBdzEAU2H6E-ZC3JNM6_(H=93hC5bVTJt$5LwGKwo#U6dphyAN;kv}v)|3GcJHc{ z7z+%#_6u_E6;o-{T;da&q`~HKZdH6kl+YBEL@D$p<1C_MTxFWWJH)CwpS8PbN}t5Y zWdg-;x%nmM^s__%|#d#dfYZDV-xhbGA zkKuOm&D9{X!^RC}d&xE&$B!oF2~_hY}Ga6HqBMqy6r z%2vJ~RSd@qYC8xrEB3YbF{M@LbK;Z+JlCdWh)K`8cTV!<42^qqht&vP^SMlaE$QxO zspRXSX@ZKG>|c<|>oC30k}n6dpXaSyM7&>8*25Y#s(Qwysv&DOo?9^BMeDPM7=0(f zJ%4$8dV$DvXzQxxENqRiPMW;!sGJloIhu%H>XRA^!h0smU-EVps>Xt@F|l>z`Q9|J z+$Z4Ldc>t(af|CZ4wrm8zZgBWs)_Q-((~MgGJzb1r=Mh}_$yt{FWgRYuArf9FD`7p z6MvAi*R>^IqK5ZMZF%k7^`3p&1>^n!+3iGro#jgE^OX)nawYqwN;00h{wMup!V2lbb+-%wXa>qv#M$)eQe9*4N zy-=6R^_Ub&V);wX8{_R#4wD0znjY05^Cg22SMvVs#}AR|Y>Zj2XPAD1S0-&>Swbaa zPjr&+)v3 zaMU*Rx1WM|Hv}cFV{H&AU72b#F;{pRkrqHRl3>QOwE>81P(Yt)|Ez z@r&d2RgRXa)l_552yRO{YnM?jj(9=E6tfp9Pb9khyxY2VJugNS+ItlBNQ~O@B5$gp zlaZCeT8{-UaD{qar#6N!Y+_U(D2ZA{dvk8F64xpHnKoBlfT8vvsgM-Kv%R86YyB{# zfvMWu$!EF>Z8^tZV%9n#5u5rAd*U=<-Y?*O;U638S*$n>+o?4O!^~>z`H}9rgz9o9 zj@WxK+IxX(v$w9?YN{>~LmYmTVxCPFG8a*yVx(yF0vu%BH*z{O`YU}C;8*yDH28dIp2 zhyTD)i|lM$M#p=BdA~D)Cc2N0Cu;u=llV-$E0)p&Lu;Y{C!>MKxq|983s{*suQa&CU1(%w zYzhLaUU82>b&`mo?<$*h+J|fV-0#c_2UEt3~TzF6ks^(Dhs&4#JL{L-cilMxQ}1}y?k)vts!{g5~Yw19Qq z&fryK?u*6eJBi>F$gMgtZ#`tzA(4*`@(<8>=rl-8U3`Uku1Wj0tcc-x@%bXoz~F1P z4>f74217P?pwFD&jTKjP5%1&J`My+eM%;yJCzOQybEVUrrt_w8-5zSYWrdU?lGET<2h;vr|Jk9-s(p< z6Zu#l#*n9(HLx$;)V!HJ@BkiJ;?ZwuE!f_>$1?mu_ zg|0!k3AvmHJT~9O?7?mJF*5dIxP-2ySz6Ikyr}PLMKIpAvS5IycAfL(#!J1c+g3x> zG0>q+6w#V<9rYvPWE-8xOlLUt^NEz0_*Rv9>)ZZ>hE;7Qc6|eFbGHH?L2*N>-XTWa zui%|2Q@qe2{K0HU>{?ccbePFS-ZGVG>@ewP8@(@Y=!n{RT;j85m5TL9zkWZ>8`m?` z8^MelYPI|%YNqS%t&<4w4Y+oqW7lIchQhGt z>rAe#ed&JEyiIl?&`bK3Sq}kzw+JsxN2(NT0Ja1_Ay?jecETd=A|=*#Blj%s%Z)E? zy>>>ktyPbu)2WKzD8IYnp$v889x}h_X>eYfBSBjhm#XOVt1oD)7&l(*c+zQr@6qC&b(ZX(rmA`mbA$cv`|IOn z6eKUWuAneNk}5^WjG5W92ys@h?LE;`Cm#0F@(1amUDnYgdh;Th{7M9NGdcb?a=sI? zAg5t+>$$D>tR0-!FG+6a;pJ8fZ(4goOwpvp1vNwk@)-F(Cr4yi?r;!uBGLIrZ zSQb%NZ=UO#ep?Z9Cpj;xew9#rUxk7v*Tgnzq@j2DtR#uqEBk_mFE~^?oQu!pTc2qt$W?fP{qi#8H)T;n&S18CMm8gcl=?f}w6T8nY`Q7I_ZEXqMZO!EzLk`> z;5I#Js@3RX?TCHeGmoNku~#p2itvgW?IC9CA*qrrI$$wmzQ8)^}W7pNHda*d7XDk+xlZZakJ;RzqWhH7V+VQ zq*+=I&PTKE&qCM6g|EwINQ~&#%MN8JUDG1;}TIlKR~e>O>eDMD4rdX9{jS zaznX}OA+6lqpj%snXqg#Pjr<(rWKofI2kwBb9bB1z-%-pNk!xB?xi#hHpF!EQTzS1 zH@637&adDS5;s4EK566~&2c7_C%a;pG!;%(K<*e?oFtWV!1(@Y;Cq$P-MrcrZ<*`& znS0tAISOe=DZ5B4bc$flTzGPATgqhGQV(T!T-NnU#L|LULno)E8?w847-`K;dC#r$ zxAA5@0^ju)FNnF2*Nv!FOvh#t^9eR1zSbZV54+A}^Ll?#iypb@oeOlQL(|$En(ecM zjmEEr5Oc8x7QsYspqH4eM0x3QDLVf)*G{k>ouGU%_L-&Y&_T%r-4Xj|>*o<6Qxs;m zbQuno?Ny*baZdE2xN|Hp3NCU%XmI;-p$gRH-9@%Zit1;%{qLZuVccP@3Sy0^ihC)L z_t4@t?_B*`$~_Zwm94;iV;Hei97bhvhaj}zVl6Vy%iA`=WY)I_qrIDr9?<1m_MbCR zSdo@COs=_FNq$q8&C*CZ4doNJfxc&g@w$LY%%uzEvH1#)HwyCV$SAb@*i7#dHf}zT zzKdTHd+{OJTREEqE2GH+DNNOS2wYhUW(qT!@nj`)D|b^aglk^*M0&F0ZG219Yl2bz z;hNM8-1PECM`f$~vGHf>x1QK!+vTZ?-W$a(t-irK;dF-LdAV6LjyB1lc~n*;N?K?8 z*l^3;1ig1x9^QPu;(vLZXCS>3BP9D4w%%YG*IfF0;*ZyeA{cvKj#zSYtt)ohzDY=| zy{b{vq1^h$;O4mpI?(u>jvf{navFj!Wzxz-@pg3EF!Y%IdJah=3v3@YJUe;g;1(gg z!o9P;j#r#$19SQrvF~M=5ICImMMihatmsmov)VMG+Zv3T?&@tBM=U+-V&vjlQT+U= z$~{M8lpw?2k46$r?Nz23DBQ~%(e1>6@(6NC8*pdkRy{~*v@l2UOTsra!s0^K?MD6&Tkjm4NznHHZn$waw#_@X&5do`v2EM7osDhV zwz+XOc5?DO@9#ZzPMtGIM5Y1 z^=_hp4gNO-DoV!BqyxVcum+Se@>2Q0YH5Gx<|`>onP)+DeyCnqhW#3_8kIA#F#dv| zPtaV-6=^m|Y}%WpJJ{T8{nb&P&4>MQfAvOdS{;%adNCr%Ki&8J)~G@AQ9`PfUp zY;A+UGFaO%B4L_9nSic@G0Yu;rLOx#Em0QT8)SQ0^?wxn19bJziZtShhV&%O;mcUB zlSvLO6m322ccYkSqRX2pcCm0_LZUkbbPjH^<|v4>a;+0%Z~Yg_uRxC}0Xs3xKh(OZ zJX`p85yQC7_PF4Yrd6H=)k!SK!+Aq)^gLX=y`6(oTx^e=|2F-vR>b_~5{kGhh)(zd z_`{~MFOmeOBKD`DAyT=*miN|tQAnr%3gaB2Ky`-`DDxgQ8JS7pTwS$1Dz4Mzdf*NR zbb7-clEbhrTt@p9#u@d&;vrVfn$EEdY1sq+x?D82U{DYW+|9Jp95I#OM#dAJ(;c(J z!4k>tz|F-a>Y#=EP5GP`M@41QBUdP!-A_q%Z&Q^*rA1k{H>?OyBabXVlFpr{a!Z;m zlzmV)B{dYUg=0^pKT_fe;K2;dzI8M@Q)tU7Hpvu*|FR=xPZvdwKb~mcdBDZgFpG+D zxHwF+KthE55Vuj0`?LR7I=Rb{emW;LwZsj_A?kkAzwkPA@{uX}THhEk0q}ZQ>C90@ zG<#`yaUXa?7aEQK*U3qbNT6&;4R-6H^3T5mrexo=^PYIifl4&^X2)Lld;AcC1YmUh z^S-5oqkmdSSOlvy1Zn-@9QuaND;91l_aYndvKxl3auLWr7{r2-1IhwJ_#l%eJghP(n`bD3D=0|rSTm0fShfspal7K}Jau8p`1xpsbi@g* z^jj2*Sv3^fSxil|SvPZS&kv)|4%dB2I5pd;m-?tNGMs;vB=cHC!EAa|aa`6)JiCKO zFK2XelJKxr#=P_jSM9g?T3rvYBaZHZh9%AVijaKEP@)#4NgA_7ygeQ|<8M>mw!7Dz z>rkJUu2||0*Zb!k#6j*qBjcg6om=%i122Kn!0=RUl z0-NGabYxmM`t;{bMfcZdZjYPdS3%`wG<6+mH6+nUK$^7EAy3Rw*_$Zc5&sxv$n+Je zoaAtDoV1`tReQH%nD`Y*=$Q8aB@>q#ALQJ*0#&S6v76L*vk~{1>h~^O=}xUnWgr!@ zw`AS18|vIgUo$!O#a;Gd6C@e2wa?d*HE&v9EDL3>B=}E6OyZC@YA?sbEdWdZjJbI4 z9L=0b4T%;D3C-Z5VCeUFGo;bjP}jbxVocG><=eb7eak=%tApd@ZH^f&nB;L1^8=xN%(^{FpHV-nys7; ziJPzzIsql?uJ~^!b`+qsMZ?WcC<;M0UW$CxhCB9>jj5Y2t$Ft0<$N1O@DcNoFlnPk zH+@)^j^(+>ZKxIH@o?=m{=2DcHZF>GO|v(+>zaDHVM&*j%I7)pE8i~$;;5tI5(C3< zmlsmQW;llPg$GNx{YibMZOmrLl>=h_U)i@fzAgAAnO;r=Y$v~avG^YL)dXgy4^yBX z4Zj6@ITz;LlbEGt#)Il>^o-vFNN^1x@PB;72nj9@z1{f00)f}K!+cMM+4wppWUYX3 zXDE7VPpNz+OL2>fOKoOs-V?79gz7kX%VV+ar@L|@N-E=_xZpD!u27b$Dj$*X^IM%w zMzQK^d?I9Wo0VUt%^`{RPug*+z3;zRMcj=lkLD#x_YzJ7auJ5DY?d};ABC{;i8#{5 z-B6{x6^GafrZm~truTKeh@h$c1a)ljQ%T!OxTv_Z0}|!un-yXULqkVR6|AM))%w(D zoYf8gI$FF#s%VZC2ca2+r?+Yi&Ed@Fb)em>R8Qhr6F2?)Np=Ja;p!Sh(dn~F(n@&_ zb1sf)E`x<%|FpW@x_5i_YN&Usml@aMSnoy|OxFaHnWxSM9TVy!vM5hclo6@T2Pb}I zi-}6RRX%>30p5X$R5}p)=U(q_Y+kGyo3(h(mTUw7 z5f_Ot%7RAc1%L)S0I!ipX!0BGOtbIO(w+$;_`O~s=00&+V8z{0pyW)9<7lS2i-j7V zcO*;9e8C7xt0xLICKPvm1B_=l&%YpLt=d31dFU zoLBmhF$2+8A4A~{gVrv(^St|t-%iTRW!a3CTrmH6kpWvlg#V+)R*L6_Xx*gMtM=#i z?|PLY-(Bwjz1)%0w<@~geMe6OOeR%zPuNnA9?ObLVZE)n>2eN_k?0{|Ti;!|YiRxk zOyX{ded#b^N93bYy+r2SJ~iiEOP9L5 zcPS)4-SaBi_`nWm;-gtaIU& zp_RWyTOFp1Ty2dVYR-IY&lpk8Fc#+inx=$dr_J=iJ`t+(;$98f$1bXY>aXpb;ZcCRSO&g3I!kWEQ`7&}7=ki% z3BS9$i=GRYcA%jnqVHCz@L0pj^Qx)lsDCHDODeTWR>04Swf2n22=WA(6(mPLL$$*Y zhJBkACb&6k6vH=7B9TS2JD?giIJP!FCK}X3w0=T)elWV>JbT>ypl5|39w=c!f!>ql zwcb-8sfn#h=C(~UAy9hM~k(L`bTnc+HCg=YW& z;uTY3>}_}Kd904)Js7p0c$*II0l!2^u!+Hi&Lqq6C-TORxNS+wvIl4OuoetB4<9sM z(kzd#Y^{y;AVE>gX^^PWCN}@6jq1>89>I6~dg`|&s}Vv&V9}Js$`bUTM>Uj@r!2>q zsEkoJjN`?bk`J5ZE8Ofd79O0gv9K8z3HMTrI_Q3N?5qI6^0Ut->_T5s7{fa5zBa77 zvz+K!r7cyLnzt|OOb+?LItA_e2g$>Ww+`;w0BO%FJwEAowU+>qR)S1g0d24!m#eKM zapa<>^{53;{4T~stf!26^yeh7*Y3>llE*BKvamKrE2T`7Q@KXp0x?w!EdO@*27so7 zIRc9edFK`21TJbD<9oxZQe1dkMVXmCakwo>6*mw?vdNK}kLDig2WVuj!bC=3{l?cT z^4p9%moERgIMbIAwFwe3hMJfo>U^oV$2Gg4;|@e_ZvH6_w)kuMj-c*0Lc-Q9u872x zGaf(7u%?FmMwttYdu~+@iLYqZ_>u40GqQs!>lR^{bCl`fZ1nZ52%}D^d6E!SwkqdW zz|QV0x>#-P?`x3kc1{LLC;c8A?d%y$w=W6Uu|N!nA#FL4q`9TRrhg|8HWOdv*}XW^ zmKoL5^3x5`$}$bYQAIlD z6WrzWPVr0%d@wVUf5zRsE#Hrrd|7VsX5v|fyjn7%x?pX_HLH&$3cL%UPFeI8`&j`G zj>Nn0#e6%4O5+0(3T(qhxo(lkx1$f%F;Y1DXFr(GALF5`^?D6CSq38)K^#TAiD1As zkzAPG!IXG4rb<^_7(9MH(}*wA1vP3cCkdnTQJ7IFCdZ+hs&hnjh*ZF}66p-yA4pc+ z{9~gZp|PT2KW;b7=V})zZKb$e^^PivXLU^_y`xi9Qe%oy*< zz%2QN_(kcOA(-%He$C@Ri_!SRW^{7-iG02tdsUNWk3UG69oSA7ttKujbo^%VI-eb9 zZ`ozr&`qa9Aw-i|@+peU8?}yngJN+oqq{4O%%8VjFDlSq%t&umY{tK((dEoQ7wDbt z$JN*J*B%5Yz{|bSjPb(gGGpc0=;tVQy{Q~_xq|edtK!e3WEB63CsV3J>mw5;2o&utiHvnURxktK;fLp7P;#oo&1O82IvW*DF$)7`P)W+P z)1)BwOb2KLxdjTkMs&TT8;U^ZcR$NEWAQA)YL(`nbQEZWZhk0N00EY~@j)G+?;Ig# z6hJKpo8LOz;u&Zua8iA5S*C7*moI0&H6wSuH&OWO*P~6wG&TD_fI3clk=ry(gH^yY z`!|xsT5%};zcf^ln?fb~m+AF#q0`$oVZYR6^GAbYdtmqIX(gmb^ufajTFy_cTW1+f zG|y7kj@YL35TE0$9MV;x&K_!blB(AZ>pT5PEnN++yD6cl;+10zzfiyG-B$j7!_!(-*G+;>JeK|hY_l`JIuY?83uv9TaIgw+>BZ>%)9A*=74nb$+ zU9e>PnB!b&OXK6qPQ0;1q9G&Qg)IxhPXZD&o42FWCgMimWLWhiLNJ>SyKs_GiRHqm zcK`i;bD2u-4;1U$Z;pNBOAj0?SB&a{;ep@gFo-jxo!##zAf^pH_*2K8+XU-_Jw>U? zs#ipPsNYk_0v7$WE#Z*zaDUr6bXWPzDUj9{l5)3tfO@YX=xpH=vY1Lfo>pBsZPnXcB-J>?2Hk#b!(OIhlU;q@al5mljg z{Y_#S{r8)&5k-}|A{@_+ko@ZGrH4}PR>}TGn<5Ll6oEkCm)bcGWa$8iop;{GM08;8uc)<@LPDr|9S zO*fV+zV~~GJinv6nB`W#yC6hS%fL*-v4*3=dZY?GVh!6v-d!TK^bIV8mi?{U^z=*$ z8Jq)qr0T>u|F|kQF5FCVR5s=$vY;+JijFM>X9vu8l)k&Pxpe7|6HJ4xs){CDY9rmF zWV%--+}2xAt3EcmPj%KlEkjaxgQYa++yE?DKv^Z`hsE~kynjo+#lAoThXgvNgS!R> z-9+i*a9yJMUA#x-sb_36ml>pD#=F=oDpcX2xEYq#%+s!@>z&deDJjs)`_FQR2iTQw;3L+$H*uZ(blDOjOk7jwxickzlLS0JF^md ziyBflvx||eG`m#>%7L6@Oe@`aFiS3-;w<>AMyh2whUW?<3+a0nU+z7rSo(En30WrY zC&){l)Lkb-`2|ObIaVI=Aw#J0pN;p7{oyg*x^0^~_|racwYO!PGI`Q7fiZ=U z+$|>~6ILaU^^-UE;_I4p5c(D3ZB3UOJJGw`NH{#FoR3h(c|qgP3-{$%)xCLeQbY^l z!)~MUi+VLd$0uGZ;bf`f7n`6|uIf$GHJ3kZ9DCXt8)yIQg)l;mB#rEjnxD_i z=XgJp!sQ!W8cpaYtqcMLgOwyQ_8KzF_jt7qY4ifLZJMr&l!vbqCh-9g-L0;Zn^qMQ$?3mNpmWGd$vkYK2?!V|G_UM+IxqKLGgx<* z@UU&n5yucR3cv0YhCZ{@h5LmYpf&~?S?xoy@KOpk(&luyv>CoaO}n=W{_6Wvy@u?H zM~a7qu-|>NK3sCpCWZ0*mG_Bj*#gA+@gy2#>Fp)agAGdb*4`urF31w*OFic-U_nWi zu+TFY$)Y_f2C?d$tm4hKo%@E}r$OsL?ITmIJc4b2*Dx$Kv`19zR3H4x@|5leb=a7K zT%+mHT&!L9?jhK-upAC$H3xg$mrIq3`z*4t+@a|8X5x$+tQNSNtJ*pW;6m=+H!$L2 zavJ}9&o(qgd|ol4jJHIX%2C@8XfH1BWSzRa*@F{14E3yky8h$YOTGvO;kprb zz^`tsv~@)y3<`V~`*`2DTiDlsmz8looDg|aOR<$%I6|in-ZA7?@cDJOrwEi)abJ%L zG<%ex<@w=Pgf_zwnKNmvL?WmyYF(0fWpaN#5RO*arsFt0$fd$uO&WMN2n@oFWLxx# z&AselLe(1Ojoc2rao>(5xkO>GVce*axykHFyn3)ViTknEx3~4Dz;vX-DVFJ?Rvm_b z)bvsUUT6txa92S#Em=j=iD9hpWcZ5vh*Eef!~876b$ZHa3-8&@_L4NW(0X+_S}<3| zB!@tOQKGPxw$PLHGm9 zUdu;>|HZX+?ugj!K*Ui+!NMoSn{L5KCx=~>$X&J;E(4^Y-gDCX6t`?=_fz6Y$*QD* z-F@J=bVl}1=5~<8+UN*JM`{8|P6Wu`^{UJxCXp26f@G*J&o|(TU${hpTmD z7(=p!8;W%sXXm`M&B?NT#?V6}^8;%$V0>@%_ukFFx2H8H6HoDUCe{!LgGE!6trpbhuE9C^2--v@j_WgT}^cysW zJ?41Y^z_b$E3hF|IjkYy&f?D3^sw(A#tC`0Z^)!FHVdYxQ`r-*zb%!|4A?6TtpikE58`9g;j;iM5S)mu(cR{T#lI+qHGZRL4`wwqzI!07O!A+6u#!vCyH z7fQFZ6()8C@)-HaV&tw#xRSFa7gyC%<(#VH(1M8KVQEw7@`!Ek6@`4wPC?3WE(RBN zGm{3HEj(dmU47pE6fcJB*^WuC1!r4eBggNk^5pB1n2k!0h}+50w6{={vDwx2F_~BI z4&Y>%Kpd_>M`C#GP|1N*(dDRRWu zbEbI=t6zR4yGz}XcO1(Va^LXD0}b1J*#c#rth9S))SGg5gPq-6bnt}rRw_{EHsvT8 z(b*w7=1RIC-Lqr6_#0_T$0kY<#4Asps{*uP39^Zdj#e{bDy^PorIsCS8?vGdS!V5W${)foYkxp{FSp&7fmroPc}rv zqsG-Iip=KsY4B)1AW-S7lY1eT#As6jr_V@&ZSQt>)lk6;2g0r8aB+{N^5yw-w5t(( zq?|j9j-Ij@AiI~jor|=%_b5Hl8tmm*!FLLXPSOJr;$P^M8RYa+2hQ|HK6+DJ=JER1 zs0f)};vnPf32J=G-96zg`gM+XbXSm4vU`VAz*`c6?rzf;nQs`UeO*IhPGn8=r1W2~ zzau6(GEsgg?f$FF6dr~p(}K5g;(-bA(F}52cQX2 zxI;ZagM>7Widg)Y+E_+jAn>gF_RIIF?-J>0FJ3K8xlSISk-Xk!q4k^8#y7@Xd^gXT zH~$HyB5bb(QN>6?$cHX~!%yudX4rqrOM-2!{y;(LmVtEt zCb8+l-a^EBzD0U~F044~IWj(eHRTLMkj{PITx#y`vtyRaQIK#7ulkn2sY+;e8j=W6 z?7+356WYuX%Ia*-A7%jSFX$ly+EJCiil;jB*BMCoS(U)Vd$r@rN<_65BVbBg)w|!{ z4AVEz1d4`ZP?t}5Kp7L2zdy?3E)CeZ?!4i#?wlf(oHC65I+DM*>berQYO- zH^x<@aBwX1INjN9cgd&BpipWMWAIjo%qM(gtDJmWCwV*{eGF6L&_Cb?ij0w)TCH|p zK@QG?tWVm<%WKvw^-R<@Z8jlq0rp-Sb#f0s^ZS2w8*wq(rB)L_%%2(^4Z?i9p#4GZ zcdSb>JRrYY>6W9xV9$V;(O*4gKnmO@1eNmX(e|2E8o6 z#9E-HCbHK$igmx-<`#)#(iKNADZbJ0vgONq17#%?Cw~c*Kkrgi6HKe=Bi}uk&uO?* zGfhrMq*TZ|If1lHs6lDG6a*!gyIb28Tp*Ol6F1^OP>Q0fsIoJO%P0QKIQmW-vkyUQ zzX)~TL!4}^BP`2R+jJIE%&MR%nfeHl6TZVw#KoZI6Q#>;+?zt|t1Vc-nHn<+eUbSj zHo%a-Ed~}n2nutBGoE6YgiMFQd6wA{eejW?vbE*jn+2M=L9dZY@^xq3ZQz}SSMgMk671YI27A zSR&c#HFABR#@R$ca8Fc8_9i~qRHqF<7i;v8}hk-eP52vtpb=bIz-=oHf$LP(X zsW(0F@=SQHUAx2*VI5Ee)__)N7aL4et8SQB-@D)16sp-d#a#1ErrNQZ#Y>iUfn3(oyeWQ*_8LuP6WA3fc zPQ||{C!VRQFaKp|Oox!93hZ!CKRY@f#3r1a_8OX_Gu8kiDZJIV3Wi44#ab3&8#UX-3J`de@?5!Gr3ih_JY4UBp4P15o z=I|9Br87_K1lqb85*c-Jpp!{a%M9Mm91SH8V1XVy&%%J7V7f%2rI*CZ-Kbx{`;k(7ewCCqT?ohYPYt5hMl}YpX7zNg zzUi>K(PQa~RKaaIR;jxGxB=%pvMt(0&7$kmd)d-F?R3zt^yeehK{fA2dWg;v0}Wq& zwWKt^iKXGl|{4cCH`xrqpjEF?UUOB zT-q4Y%*vqznNf;}J+tODhtj`gYOMxxY{q4M@->u&t6nL+b~ck9`}UJ5g42}>mP@iD zR$pH&JX6|iC4LHXt}%8!{cwA+5<)1J9jD&WUdrzIvE4kF(>FVk^jzWn4_f}1hrmUv zKPPVEoW)-V(NXw(Dt<)W1}gN&dK_NzI?|TPF^Q_l@LQE8Cxd)M)Sd;^kC1T0q!}?M zS?Ho0Vbycb3ZZ^$eNzlMldzr+oCHhT=Usbxm@AG)T`oFqx+y$lGE4&fvG zMu0>3saQ(nk0D(>tCo}T7^Ey+D!|)DFtiG>5i-+CW9Fd>OmOx|#T@c+1N)!a8r>>| z-n8P{F?!yfOFPA)d(AA6>h$LsankwFY13gR5F$j;zKMvz;$@iT13YP7OdeDla5lc0 z+qjCA(u~9tLs!7I`Y41f6ybaaOF3$vM8%N!l)-R^J9#A9X ztjl=rn5z-sr*+r`DB(hsi^Es5n?U{PMYP&-id7=v?mdO?qrYOiR-8M7{bq|L0G8;i zckWN=Cg6?ZYi;a~tKBl4DoV-3s_-vUa2me)pu@P+*s%?ISN|=9o-un^IEQjW?^wy> zdSI?oV>UAF9s&fQz25eUy-CaRz`j?5V<9;Jq6i0_;+Xm@{O(wi0ODM0@bt2+Ij8wVqG_Kuzsnx3Uo zy>)w+8cR0tVHfnLgOP{z@Xs;Wum*}wHf!QuLV$rl9p*-J&T9ZW4+E|uJnW~|W478K z3n4LJ-W27t1;m489wil+BVgiv!hbUC(P3M8np1n|N3`f9E81)r-lyEN$J&AXKX&u8 z`rGIQxeaI(t;=1Y$JyvpJhI^qro8m8PAM*>&>bST)pm_@D|Wp1dbJ|e!qnoGhjN*1W*clqxgdCrcpfM>VeCF) zBCZAlvUs+*Kc|ylK&Be-2DjThvN)TVSiy1q;T*>v6i6#9e(o&5E;u0k6Bzm#H~d~a zG!y({gT5G?G*z`_qltT&S~76jKqAkr7t}Z?f~uScDIbG>&jYQ_4eoE`Jaej~dI)ah z#8dU=kQW9^`aZ`LV;CxbHDLJ;k$J7dQirp``%Z?K{L*-9+2{L@^4Q-}8om!P6hCFP z{F7f~bZ%?Wt}#WOq6dVcCEp}3EqZAaL#rekh((O@=ZZ|EN70c-p^KxqmzUF9QiMHw z8bnZ@oNR(hzn00y^W@9RgV^bV5ZI_%l5~ncxYV-B_6Leu!VH_DzF1g)u_KnF7eim6 zkRiWSnJ@bvILRim8BGz3iRby~ku+WH_2`APj>me6iR*x&p5)9-X zF)3<{@e_EH;*5tLK3&6E%ap+IqQr;=W!+2ZwKp(i#F{n}9IpMompBM2h49=&{0L<^ zdYXr#qMT!o@K#bA5jv5Di?knt=K-*VZ&efxHTpg5ASJ-n&XSCyS}_ND<#Mgw?a37t zf)_|)`wCR(0BF3w8-fzM1|`nm0wU zD%VAvlTPOBAe&K9zq)KS05W$tRUR+OjW7izH;MjY%F7P-iwlVSJ45mBWRIRAn&CI4dPNanvH@&$E z#Gnb}Y(9HGEg(r_N%w|Qk=3(UWM;enPV_X`z~0dKSIT)h1rT3Jvwi zzN;6X18-dRkyVl7Ky`kQ_KEB~G_$F?F_*2`-@d!7f2KFeIrWW2S7upnLT z>mqY3Y3rEb_5Q63PA_vt$I~Rz#F|(F+?z4HxR#N5JV1kt?h)!Lj)X4n6W5TM)V?{U7+F9vpL> zkn~EHb3!fV*JZ+Z^d}7o-S<&(I1cQ@@ z2Tk?9e!2a>XDRKF?=0un+R&dR$7b@F0Ij2cyb|f>+_M>6Z3)RAetRDms8#msOujF8 z_8|Jy!I3{VNIu#LPL+)^mmEgSA&07?xmFfFpTx9fyaH1S<7Vpe{DOviO+b)H2D6#7 zH-!dpamWzXIY_*SYeB(okgYg3z^7(N_sg~1G4uvHKhskORyPSu-2!-&IoNK!-q`pq`7r3?nw-W-DyrR~OP z^;7S!7s7Ka|NHI}!|UaFvp+^R^FdL5+V7F=G93m#BMZw~z@vsX+^B!}TZ=Wo4-Ms( zcQF=5z-H+)(CZlN+0|u=O)!*K86ZY=l8qqg(D+C85th?P>E;w!+_>>UmeTd*uCpIu znycwkDqlfaY2W4Mb?4Z-*7nlS%5}NuLpfy2x+$3Qn2$04`^^myZv%Nh_(zUU5Hm?c zS921k>D%iYmqn?g|PmE|~{zfgTht#EBe_uj{!~c;<_H(vZ}B?T#cI0|z^ga+nX^!9mL>n5)GR^+byg z_nch|exAjvMlR6>E{Rg1-~@)R1z1-_@nK81D7gq;r;lojK

|9oW^b6<*SJB2v6N;t+zOKa_I_ zo*$$7GFo$p@78XtOe<{QnfxyYWYinn5ocnL^$??dF-h*_sWAa9+gZ$SdbnhTej<*T zR!BM%=x0O&`xG_@t))qLG5js4ZcNV~IWNvxzUl|DcKUbKuMwyy9N}0>%V^4ch7rsw z`{F3*Qz@xp0-k3=-|pkYH4vkOFJKm7<`q6~L<3j?vwbDt$4X-md;8EaDJB)HYm|Ni zx+?u?%?zJI`l|B;Wea6u>=13tuhXM-Ebo8qxaysRE%g%cc|J0g*I?GL_Kc(@WlO4t6SwbB6S^>6?bFxIJhSPe(iQ_R&tX zhBqXpymU-Q?Slh|Tj%PBt2d%cKA(nWi&z7GF0-vc+relx1 z6Uc3XP+%$wP1sGyLT6c=S98mbLg0y#Goy2pGP4YO$Y}5bz1~pY;OD+p7yFZ!L=hKL zU3C2xMcyXhFT&%a8?^Y_MyRqak$DHDqbjlA1~+kX!Wqo$8+r4jFkFc=-b(oV`i0C1 zv6)tsqMfIcu?W~Dw#ypSUCqoH+=3A#@YRwZ4Ff-Zw;~Uol?!K~OD`3snPzW`b_b^~ z+GX)+eYzCpp&$ZN?l=N_m64#!q3=iWj2*K#_i2b+i*-LB=d#XA4DZIG^W4;WqRYu7 zTOWKlC+p-7ouA4Q;y*>>ZY4>e= z^UvlN3RZ;%+qSl+<1*C4Y?Xh{<^lzu#^H~$t_!Go43VuzgEI^=^PQX0gn{-vJv}ELSRCCMQlzQjd+`@FksF)f>2se9DucM)8em z-ZPonoO-Kw;5=`X4ubpg;?PTdDw+Kvf!}elYgQ2+WxBsVUBSvNQ&fm_jSIGz-E_c% zq$_^XX6wUDue(?DT2Ajk=V-)nyFI)hx7`O3f3oSAFIyNg6Xe$N?m9W}yzDW6)Jn1a zB?kA!f_p)2vl*+RjDxvpQM1EfS?0ftA1YPLrqJ4IE_BfrPZ+>l2rLnik&;T-?)BTt zK>h8aP-OXJzj@%zpEvfI(%>Xm1Z4<6X_k!PMA^Mq*ct>flLX8+rG73R&2k_6P@Y-k zG>sp(uY`r=3|mD5X{Zu-b+1`Wi<6Bf_j7CS9rq&-IS+2_zJ5U~>qY2g8CqDPpUr?N z>IFI}VQMQfw{{kcN& zk#hAU;Z(qcVE<7-awFhK7rlYsibQX2Nh74ea_|Ee4}e*0U(t9~@G9I5s;%XppLs#h zvNZD)M4wCF{8*PF;;f_~46ZTtndBzP}-Gb%us*N3fOZyFCnuzf$d1ryd!OeA_&ObKE8f)c`@a>S+)3rTfg@})uMbvzpVGW@_^-;Cr zXZwB~PO9)ELHKmfZDj5d#P~%am;9w}l5~&4H1zDGkE9B!OMwKh!BK>~|0!dy`O18Q z{PbaHO7i?=RYg+Wb5!PRQg^1ZD0)~1Sl#=%1NuxNZJ_L+Bn);88{hun6uC+0!^K*4F1#5 z%D~i-@LLDKoOt>PzI;~Q~_!L1Au{}k-52(xs@>xUTmmhE*JrfY^`i+Aq91(-Sj4V-`u05gD@yPX-(24D`b09XR709HUpM}RfJ z24G`u0|eMOTN?r$9L-H_0JZ?z?+QDBoq+?;=D$Pvuk}9zu>(4o+ZqGxtehPI_5gcl zTPL8gq1FEwj^_VaHhR_XfjIyi0ggbIZ+DL7ZU9Fs14lD}6Tr#L0SE**x!MAp0nRqY z-~Nnj9e@BAfGfZa;12KrcmN%2ss85b>9K;QuZCzw~eaBSHM%$$-p$)4OiHSoN+WcX^_QilAlj6)r_vF(;^g6 zsUQ^`8PpP8VE7#aaTY^Kjr^c`-B-1}_{Qm*_4mcccjl>uXJ^C?A~=GG8Hwv8pjQZP z8dVzHD^H?bLZG-$7t=S64pjb^oDvHQoL`Xkzn|D-SSAg-s!WlHf?L@BJ zj}|1zr^({TmC|2OWh&Hv>H>liBR@)#k$$7j@@q&2f>sF=HKR%hRtJ$eJ8sk*#DD*O zGK+|BR3H;Mb1GX4JZiAlp1+qC%4E865cOt~tyew?%E|SU0y7x3$G}P+YParK9dsG@ zN8t}Unm{AAY$kz8FjI+57MZ~GjRQ9*ME$u|P&@8H(79a0EI)L3P@!(9P5h^x!6$A} zTm*d~I3j_cYbUH;O5z4_tQ}7!&@Z#9gqW5QL;F82?w_2|0(2=+{M+_z_xKtmelgsw zpIq%-)tlH{>lNbSAt@sVHZ+4X9J9GCQk4;d*fOfc3k80bL%m(ra!(5V=(pNC8SF+S zfWL((g9S;%8mI>CR=X7p`UM6q)17Y2j2K+`8z?sdHgT6_e3y9Ft9$2+%Ez=SE6WG#!-gMH)ol+UWj!VCaSo&zI4`M z+HMe&=}wNg0I0lEc36Eow@qAnKQKmOeR)EGEp}ml2FKsy4-8-iLJT;0FbZFD&yzL1 zEK|R3UQXOh=%IMufHMKJpn`TZqw<{q!SDRCJ=4T9ikY}3BZe6pjYf6rv}amPoATCF znzunG-G*2bk@DuFn-;cEhiocq+_!OkPFv2kLz&A5&nhEgs2KPX7>l!x#pAYO^DYKn z)4#&XK25VlcdX5#mS6Z&7e+JLgKC>%YDse7SnJ$d%7x@4*f;HonMHvL-M8x=M-XU{ zUO&kypnAG@828VIKc-?ScbvQCuyDFb$h5`|=7TqshVe6#=sVp?b?5S$i?!y@$^v4q zrCd}{bG$`Y5U88T*|s~4KXVp#PiHAN8Xt{4y6c=KD|Jp63ePJ#l8#srFIFy$_=%a+XrG$q}JFSp`XQGAux z5)jD`ct&8vE8jFXRB2LCyxhc;THB}1)J`FPU zsIE75T2ov&z+hPo#uDcYb+78-w)H2H7u5Y@yo4N%$c=Nn!Jf_(Z$q2y9jzP**}hWM>aSZFUSQ;ZfmsK z$bMeEiZ;P3hH;_-OPwTVan}AuBt~SA5%5bGKT?I)n64~G&wF~KaSh*x7(1laZHEP% zAK!idq&OC=3e4x2DFPMv%fAk{-U;_VQeZs$iYM=0NqR!iLQiZu?AbWgjzQd{&#$Ey zL$TtU!EE-}-yBNM>a)h}co8qDRiCXT>G9oimYhjpNsPRTv-nY)s$}_U?v~Pj0#ib` zPJd2ZkA7*C>&JL%I59n*3J1ah+o#%}%(1{Wq8B~c%rW{nROXM5qjOkcSEccHCYF|~ zbnpFj{_Xt%3Ev=Vte}~KU5_qDB?*5}6}?N*#=Y_peJLiEPwujOslF(jnfAdYtGCK| zYL%ICq!~Wq0obO9U%wP(8cyu|Hm@% zEO1G>OOte2HuNedig0h|e%Dbcl^{@9rv);8=??yBWiZ$*$mKEa72Ky4SLlT?T@sBfHC z7{_0?@GMv{Aa+#hFBowXwHoRbgf&yT(N?yU>%KpC6(;>M#hJuwkn>#3!ui?Qb-vma z4=URnW;5#=K+61Sznp|r64@;Te4mCZT1V()`jWMVW~4BO4z z>;bMHt^?^Wx9HpwowS9%C`L*~{*+Yye84{;@?Sym zr@)fs|8G%3m4~TH=6M1g-i9tV#MKo@Ah^3bmc_;<es z_)c&hP(LxVxp~MVOJWN%kR#9v;OPJ&zlH$R)BvF2;o*5e1qPO;HUUk{u0V3tRFz8d z3JShc4(O2s;@|mM@v~zHn6Uv4hl8MJ#+IhAEcPD|_xvwPVL*T~Cw>7a$Dtw+5Y^;T zl9B`FCdVm*N&wgfz=f&-fSMCi$1w_knZPtUg3JNP*x~}HeRBXr+1kno_$M8WydX-i zAR0h8Gy-D<@ofay4GDB~t2_X3=LWHk%--%}0yu%Ba$>A;_&)TEq5;%1HaoGsLihaM zSa`A*aD!{cM_a;gk2Qd5j**KQf+OH2?-5r6RlN1zabaS2d82M2J`skkW&NyWsbh8f zswnJs#W&<@lnW)m77sw4nLMr05fcc29GRUOoB1Su7H8lFpV?-}#1&*S`xX*_cK}Go zn z#I*m7H~I~Y@?C@Q(JgfSjo zZC!)UMkl-gPv*qdx9nIqaNWl_jrGX^fD^EV|H9I<+k2F%EB$4R4{s0ff(2&p4)31DRLKj&)u_lQBOwNijO3~^mh=Q zqn2-Xvuu>yttW6msSi?db8?Hsy!7a%enOUxOcl5nGE`KjsNFpXvhKB*TrPF~16Sm%l zoY);&tr`4+{M>fyft7Kco9Ew}$@(zN=N7W*thJgX&og>i1k{UqTN_lAKOL-TGYZji zv0oS8@-$Rt+m0-{**0o7s((}cdci1Fdt&;<(~f*=f*b+;Kgu9pq6ohc?= zVi&2u6;X&&ABm!!{8p?JDC&k{P|Y_eskY-5Z1mD}vR&cNDykF<;#Ed;Trl#uyIMWc z8KY0iZHe_VXY;}915>JS^g_>83tXW&+&wZaXWp31)_T?Ihq5$D`;R&Rdf%l8@b(9g zId+X^GhsG4M>9AgAZi0y1-`RiV^aYX+h`N=H$iA)SHZvqGO*Ej1*i4eLCum&%HYin zkh!saz(q6}5)#tAvlF~z{*J8tCRLO_e-KaB#cPbpPV{cgL)y8zriq&sYVX z=k8vlxCW3;#PoX_PpJDNU%D7MuO7BnT{pKejae{`-%QRdbC?;gU~H!a!yO}Mp(i!kAhgeU2Lx8U^{zsGCd8>u*qI^($Pv*GqIAMQ>=po;fK7ADw7`~tbfKF zQ$svq8T7C%<1LnUp+q%YH6MA6b%mNy%}%d@nRtsoyiRHRU5l;miAdu^uFD?4XeHoU zWZ|WS~LV)lhq8IO-Vm9)O;#^`sPYT`)VH(((qxM<7k=sEWGkYy86}<$3`gESoWwk+4+`C3(>Nz?& zk$zfx@;-sRW|Y?hmj{SGvKr&pQTdtiQGe%lJcJxI)N1YLtiF5Q+GUX(GbaVx&AR_Q zo4Ku~&N14j?-R#FJl2)oxGcIf7Sr!W0n>+MeVk;V7bxz!S7mI>3nJfo4Q0`xU08Q- zVtS@TwRQ|O!(#MCYY|ZGjSq2$WXDoz@UAcq|Hdpj9NMD%^0>8&zwKJAxd!rED|N#W z4M&|)+hH4&7 zv|o%AfLZJl1^J)LU>N zEAkw2nMVrK2T|KGvc1sYT`k4Kw2(yAV6iU!1M{OR^03NPTO84=1`e}Oc#wVnUGxZ+6Ak#JVok<-@<~|I?=@|8#h8bDRrX1KsGWjMA)^46xTAMj5CBGE}glv*N#a?U(#}5TKqM_#UkILSjw;k`@3~zxB(Ew64MJKu587120FmO~c zkkg!#0D~lOPq~iIV_0W_wBp@b>6Xf`u7~?pDPa9LA!JiIi}EK;E6`Eh z+*JL!3M1EWPr3ER?Y}TqCr4X2<|*z5Lz5{vQ0u>5g9qUYvtbz}dFu5TN}*aX!Vkc;^^Yr# zl=0I$`>0QGpw+3>6i4IgJaUlxTjC=`0@>)0S|Y9eutE|eOii_z$LP%6_W?q5%lSu0 z-q8!GLvkJvLTiv>t4@vBG0PzksAfst=k^BgU^vG7Gn|zaQ?8kZh&$$Gx+*KZ67ao5 zu+m&x^}%(YD~$F1kND2XF!8SvVIj>L1F&-TIcNtk)=EpT?@ktOEpf!&d0Jk^)C{H5 zxj)Lxm=lJD#L<5;b@#NA`m%t0DKDooWf)*Um6*oG`I=u(`Bo84aZkbM0>S?JC+RM@ z7HQ1JMPE1*S882=;lZ>E5HSKIZ6mJ!TAy~*`7kc)n*0*Zx0=byRi;@XP2-Pd(y zEugQB?&5_t^o$e=uWI^-_g@UgY}#L(SAFgeLL3n zQDub@;=avz+<(cq1mkBkrmI+DBXAmwEoVENznux%v@mIhk)SEe0>Ut+~Bk)O)X8r(jnjW*a_xf3ESnlQF zQ&JFYY-z>%!BwoDZlrO-zOrR)BU=OHYFRSYO3@i;{(gVoL3i$}(vc+JvKMYloomrp zlL5r(oNv4cx+z{xu*7r`^KqriX%$7|s!D>T!7@qz`cNUkfw_%H$5&fa%ZG$}GfF^o zeg*W>OI6?GW=S-*y~^+C;OG@+CYbLb4ri@_U_SaI(-lmkes zIi)EdbIBrX^noPCvC|@{jzfieoH4R4$r$>1fkzGWK8I>Rz+=N@)(cm`;w4n@@x;Q( zWuDkC;L2*SCO$WLLB3!8<7!ry+fQ84WQQvTKNIxae0T-J7uJv|GCrrDOS?g*n|=;J za`Z92UK^taFg#K*){1xr&`AKqO2ZL8Xj^-5~vbhvlV-(kk4@=Gqjc1?ZixFcXw{M(g8 z?6PJ|H?-q390Mv4?hPBn4+WIci=4u_6`N%1M4=$1Qd8m~3K&5^)1n{ehN9JHV@1#T zO3+j|UE)(6%ay$2M2@XQiso&Eko0E++m0ayKHW$9;tWd*%NeRd4Y_d66a9SLrUx~{ zYh{sThj1$+67dgH7_o6LMOpP8@0{#*!W~HTKmGv@XEnf5;=A0}tVg%DzxJlYQYEU; z2MkQ{esz%GsYD2^cj4f;)gFapcwrbb03xt|sgHkS4xCAj7;=`@uj)VWiW%<=&ViV0 z2gL20K!zfg1PVL2sQ4`vuKRd#$fUDC;GJt1I`%J4G{q?k2aj1Qbl~RdlMyD+!|)9^ ziY}SlA-CY8(HJyI(6Vp9X?h$PJeVY~sgo_-(A~vJpBP16;K{dg(1xDRkwA3dt~jO% zn@}Ftn3`MayPH^l<nv|&eLwY2AwCk*L+Aun&ikO2B$%mkwd+)>8Ng`z7JtoM{0+qHM8LZm^cz2K zildv{dS8{qD6HRs41A@{uJ4JI*Ezf?M}j2$Gtv|Dp|<8Q0N*S6a!x@lQ9i$YyhduZ zcWsZ3h2y6-Dz)&Wh11xuLA>962f^VAyTag0spM(x!Qo zEM8NZzx8j2MLY-_#+qHqgzv8~(8&DJ>cEIz@psOll1J4n#(aJ~v)jk({(%}YGGhed zpz+w|&hV52#;@=C@q5On@?l%`lW;|;0Ae=cx#v78F_MVWbc!;ae&a80cH#OppIisT z8f;b=QqCp1&7AJOxbJ?PgvDyIw^FHV^nIt2;p}#Tz4$8vhJU#em1Sks(12HnNX%F4 zI%XFOHvz8evJ3d0##!eCMn;M84y*3kq{?ThY=bpRw38qhl{o3cwkoatO|~!DJcmh@ z3xLrzXXYGpNwy|EN_HC5<0%=0pM4}oTf$8sGa)3Po9<%zF7vaLgQt4Qh0%nb4(+7N zrS8QY5xQ3ooP5!kGCj44~Kf8 zv>l|pWx6WN+9Wehy^0A9hRshAo|Y1Gf}I~EOUN>cR_bz_VzJobzs)@VUA-t1 zB^=y@JWAIZU3S=+%p&oEd0YE+h^Xro9oes@c?2FjlmR9`_g%&H8toIlE`Bl_MHg&w z6jNlXC(EhxgKctN_lMc%MbnRa!au+PYE)v3cI&`~o;J00`T5FU;(?%On;=F2{e&a< zfa&1h(zUZWl&$T&!^sp%zE>RMpkf`tJ^bR5t!L`p@4qrQ0BVRd2qwY*Ece%HEQ3ZjpMZL$@gfaOM!I(4$H1b$oCSi3e^n6@>hfhZkq0K0xbLb`kkhJ?-S@&}~ ziWXoj^@$20nB?aBQNzB)lUPit&MH?DxX*Fm*psNO1#^Ueqqd;u8028%mE}Ygb!Q23 z%NGF;3CYS53L+QZ@*|Vh=FrESz9)S2vLL<1{~4V1|KdPmqK8vBs`6 z-Sk8%bbj_C84^9Sa9;Y`9rwI#^&pJ5Tias3cRzi*WI?407E-1mHYM*S9z%sWg+cdR z%s7sI5EhKkAtI%@ZsNk6Ql#w|va_?xGKT$cX-2|iil02l2Z^pujWPi9Xff+H(ZCW)(> zsJ7U#9CeE$5(a-cBQYP@wG#OQ5-X052G0moz!X1SW-PelZ*T6|e~}xuzbuN5{K{z5 z%aSDFe7k@H8mqR*KtE)*kdV;SNI(EPmzq{)oLQ%)iNEFm)OAn5eT)A492Bg{|N?$+PwgrAmEKb)|) zEA_yfdA4BtKDEeCnYB}j14iE$)=VEZ7&trmBo8j>=~tli?T&JBzOuVc$FBOQ6KL^p ze=5SRLTOoPjFd+0I`|bOY}MoPjQO8YIy1a@sNw3vS_rQd0r@KOU)v$BC3C55Nt5dl z4HHt!R^P7x(vIMn%ir)+guq6rjTd|myildiA4{B^kdphkrF#Tt{_!; z+UYEvm6sVUa^@=2YElkI+@A8Jsr-RT4X#KSO=3ie)y?8HWj*jg-z_cLMyz6*m-x5z zdWtaP+li{?ZIlKGdM^zjx2Hj=xbAIOY^m`Ce*Yn$W#3~iPKS8E_p+_!Ou(3BouzL` zZKsad<_V%+ZP~Yc#qDmST{;MVhdc#yN zQKcrPrGu(j%Hi5_-$fCOef|1F&E`jPAF>644liHPW)K!@3l(@JJEs#P7Qc{^5Qkvz zwAy~A4Xlaq@b!&)O-FpRuq!}n5>RbL5zhC_r*q{!jU?v`u&(5v(+V*LwSxE+7hL15 zwrwbXIuT^WYsiv$6nJ`>mwsjx*48am+7c1tqt5wX1Dj%42XNai$k_xyf7jCNb<1&U z+Cnm_ia)Cadlmi}H*CzE3wwYpLn}FtYF;9Cl%M71W`G`_iu{rh*I}kUZBz&7Hi>(~ zfDH5Gdb8$Lxl)KHvow{}h?Wpoo1;-CZ!ubCb#a64v?{mO;!OKh)8JmB{H&mcF>avg z;rkXF6UpCy?Z;Sq?hu zL6Bhei4ZXUPa~SHot9ETPOU|SNrMEgICDMriZdM$% zBni9|CJOZ|L{~kO_e1YrY5>TQi$HS2`EUDq0H98GJWirj0P8rgKI}3af`b_X0~vum z6kUZg0&jSsKKdAlzNTy?Zxw(Ux(7jDe4LRK3l+umx(;&|`AR^%kt~m^8m2t6C&#PK z$}&Q)A-2r`NqRn3!e*Jqzn7NrhuX>j0|u!zEG_O&$baJX4tyv<64>SBsxrB<6m6He zwd!<&^x$r0wK2hMb%yM{6V5C;!aZw+j(6r$^2B@6sF#5C#1O zvg4e*6$+&%dw6}|=2j=t5r`qPb*I-Wa4XrL(uR{&9x`74)Qn@al~Q@MDpVI8$ z&Rxo1%k1x9g#7|Soxd%%H58k0)ux<)t*2>Yk?$TLXo?Xp#QBRcbpbrR;dWU+>ZZ+7 zK`$@%D^1n^uOp8^&rxB_=2zEF*ot_dyI_DXM7eFNZC0YdOTI)ZPUBjZ=bT*ZxTnoc zU=XeYNIkQ(wq$pt5U!SkZ1hZxpgR$=WcD9rLQV4xwKvUtQ@@E_y8$*Xq&HEoA*B>> zRcqOJu}S{%W_W}&$sJwLshJ87l;{bBBr)8`CSy%ZAmTHYkWG>ksiLbDG+Vd?5eUhR z1^zlav4IDES-z7}!CY^Smi=Z#>go|EX_r;DqKK1|rw)1{FG{o0wIUmk<#(8_+u~n- zL4n%t%uKAcXXM2*^{mC?u$}Cr=zPQ#H0U6Y2Q}+|1vdx;rC%y1Fy^3unIE&R;LHk? z#Pn6|Cx$>71!!uh#0e8u`UdFfmMeZ6sIBvmymO8j=dAe4LSZ?Quf06KJ{}0R2ns(c zmz-wUj2v2wadyf^^EPNc_~^GA<@P`~v6{mbN=CVL=rny3e#FEtLyUa|R#XgsWL4xJ zh6WoGjKEH+Uyc5S3gjk3UN?o1lvx2fRy{%|{kjZwpD)}b923X@i~dMVZ7Zw@sAY0OtOtMxK^(>k zd%k=(k8BU9CDvH$9a=oBK74{zlY!`{(9u04uac?r%5PS44)ue~;g50o)dqh=jtbR& z+Q(15o2^ta?*A8&nXv1fCJ;63wvGsKoWjE6@Wpi{R>N6>0!ARm(MV>#?NngJ+`=M< z`hzPsvQip7pdbw{~4>6ncqzVFkXl7Xn705h7Cp)KcJb3n8;oa z>3vm1mXX*5;~!x3d$89@ZIKGpP!Rf!#dBn7^QE(R!;i|v{D58`ftpF`(^05N6=~pn zw=INAB!~TcQ@Z66Tb{_;DG|TvcBv4_>hRXrfGr(}Cg?EENZSXV=HElP(?is8;OdQV zm?EGfps`BF5m#ucuR{=lmsa^)JPn7{jBir{Rz{4czwbLrHy5u9--_6FlJD9#K zhH4D*X78h_%*eCrb5x-miRvVRCMPJ8C#LdiH`XDMy}((KY2Exko6d0evjlr1MQgFJ zcuy2VAq^Bs!eJ{J5hjlo9~rDV#pF^HAk|-Ttna?@o~vw zFlL1%t+o~($$A<5y<&W02xP<*;`@)^TCIuR@#?I-Wc8tk0$hlG|Gj{C7&6_yKJ9rH ze{QR|JBsh~iQ_mSU1|eNM-8F}ssTkJP-Uk%qT_GA4ap7h43?K_gULj&M8&+FH`koa zTUsJ-ck4{ks(+vc5J8(%3UTNEhTck@vDfim(r!e1!9DQUar<@oq!_|qO1HJT52ig+ zXdUccjWT)m$s6tLNY((mgf*!}Ysu>c6&qP1>4&gO78lb{e6Jy^)o|#H&Tw02XB=bw z-P>xjXaHE=6m=RfRt6liSwMcJ;EQO--eVkunv$IYDcoLnnh!8n9668M1R=O}bCXK< z@+_amgTAxN$t0Yf4=!GUL5E1^xwpQUfelmL_Vf^=xpP~D9`4g<-P2zXw<}Bq^;=34 zZT&N@nEgrPp|Q8A%h`8IJ>yvUAbvD-?GgwpiTCP2Nz{!~Y|)uo;Cemuoz&%|s{I$H zmPGaald2goq01Xs;odx##anA($Xc#%bc&*epTl*UTYTSstW~E43mh^+_FbYw-1a4O41o1gcA$*HKZNzCtt{xv)w0&JT= zQ3uOu_N8N!Dt55N>E)ZRy(taD;55ux2X-p`Cu0`-1H77d=5b(3L9@2=|erKz+mcinQ!D7c$!TW9`{tlkHYb3W(6 zD@}>P%D&4*<;6%b7`BEsvB|K?ONi=lbo!G zK13Da%;{HU3h(8%sL-to`US=Jqy@Z;xlu#!q2YcIxHn|reNfVe2T>sO3K~MIZ>45T z78gnVSWk=1?o+1n^*a+AA&dhkw0W%)^;;?BV}H>9bQe16Jf^mEPws@EKZ^I(;olZ@ z)`qn(#%2eD$@Lm_d3190+me(KXV3t6j+-Da)}FEGeY0@5$0uV{t|K<}z+p?RdWSLQ z^;s?Wa(X_S8CwM3cWz8$i3;)KybBdfPcyuWm5r!zp={6R&^6-}s2A0g210B%v7ORv ziDGi#*Q|hmO1#L$ zid)A>(6e<`vc60zqH+r7vDX{YP~Z)~SW@ry6SV5H@T zs*?jxQUtR-M6L#B(&xCSfo|b9q~$Y+LkKN4BpIO3OUPlV`?J>RQa|lBkP~x&u7}xV z^gYsse@Eh(XsW2fTwQ(XXSH?3;qf ztKwM37>u|am<(`CZV3QprNW?2Y%|RgVm((;wM9KXSL*=>kxE?M<%i=K6jMdXys)Ql zC(~V#kDtu0JK2SLHk;gvf^p_tE`RgTj52XDyytt^mA|^(P!* z_Ie4NAs-@X?XJE3WSgVl__!mjpW)TXe~Qe?!nXCf87v8HRW1ciwlku|2jZC^&I1$5 z@qBo;n><>hRV|)cZ3t-j)*B=Bz@E4|uN~)&e0A&TUP%++9n~V2^yNH&sj>CKIWHK5 z!B1S+@2gFi{r+{8UhAyZ@g01T{LBs^$)ZC%t3so~=Ob0`t&!9uLmBA6oYLI%C#Oxi zv^wz2tNs>Yuh!7ynR9dDw&IzhfnoIa*_WeAs<;M0*zbcqCsTa%W z;7b+@OKDCZdBcK!GI|asvx~iA-q=hwO~D<#xpqNXd%>96`mKmA75GWtHx2`kC|<{( zENjAvz6q+fk<$)^I=DkB(oyl|?4~6a`75!%q^+yZf0Pn6$uX$izc)D#UiOEn5+LnXT5IuyTFTcr00&`VAEA#tKTqDTO=KBt zt6o#>F0)XmK+g$?X?`7U*xW+!l64zu9zGT%q<(7FFHfO8(W7xbV^)M^%o*mmYd`Nk zdc9}BCR}gE;kkvx!vSqc8$4Z7no{hMv&R`ln}$ec$~!2WV{6$&)BCT>$s`46Q|%e* z8nW(Shd4AOv;G!a!7@%?4mHy$W(wHp_16bVz544tX$o$@PDW^`|IR}MujO{;map^I zPr}SX@kEZ4=(dqF`@(sYX1Aro_cOY|%iiarxGckzebVZ+CuLYHPSbz4SWVFQdXTlw ztd9U>fJiqDF^0BPJ$BO_x7VC&lKrxu$AEe&d59?U+=%!dyosWL=jT6+&JM%Zo+AUD z6Zt9O`YLQDxOWyioXH__2<2!ejb=vg3egvFKC!=TI9R$B{Q2P^cv(Ht&2c|+ z+w8d(*>pZRRXg)72hpv?iE7A?^DP75Sh7AWJ?!bi0G6B5u#1RBSw&=ECN&o(s4z!& zWk!iR`uDFNCoFuph1VSraIsz4x*nQVr5)P>PBj%u-3V38r|$u3AD3CWTw#5b zO@6bP%C<{QothJUUv)AiWGs7hZAkVa>lRPr(G{|*;|Vm&y$@$&0!85`R4U3=ZaMSA z!P0<6f#7Yhv}`E6;Ke(Q!*$lLs#~t>*_NOWJTcb8HVtIpYGIww7Z|{bOfRjxL2lBbOYR7>Bo4oOx1q*cOZpfp8|IfuxL_t6 z@p9c1IeWs0yH1>=1)WlN)EDWPpVDFEt1zE6*r)JC<7L#hqS{lo=jT+)POtDCqBhmt z@kUNEewj2>ti>f$n`*rZix?Hi?iJZZXbaa|z6`@ZO7vGE)j18kRkP{#4Q$&=-^b{@ z?aP|ot(rsj(9fW=TfwSxJ<_{WWRg#y;Mm&3Y=kjTdS_F6J*V(W?$Eq!S%Sd106#M( z(BZO}K~T$AtRF2Ct`Q6jzALgNLY64EvN~msfMj}cbSIMUX=Q$}3js46xyP1)yAmSqvY@YHVizW_5HK?NI9WvrT2r8h#E0A)OHcF6qC^I6{r z11Tu*ud-f-xAP?1q#jMgJT+*3ORJTm{OmZE=}~Y=CIW9^ew(StaT$H!izsD*g>^^^ z>9Ow~@%RwWO{LQL7>4~TAv-ALHly6K#M%w=a~{3=O0SHdw8#07>y8oX_az|-`?71y z+?iy+z5L%vN7Q1}h53SoT-6{ArzvH6BWa~DD=CHWLM#4QtK(d-zenplZTJ|)O;+Rf z?82IkR%(aBgJy(Ox)c`#6N)=EmBF;)HPo6a0r1Re1L~u`^g@0|LM*A)AY8$n1vFE+ ziw03{o~oEG?5E&a+>5YtSLLvLnhq^4+I$)4(PsUkX=Q<)6i%hMK##Y~Ylp3c!OQR7 zK^@wDm09(q)cD{*3MKrv4od@Z;j_2Uy&!t8M~jE9 zbe#|2KAhRL_i#(V-bql&1mFr8K(yV=cgpmXa124M0Tq;_Wq8?OSBh6gcol~Q& zUZXjAR%a$@FHJ8znq@#R_?M_a5_7%O?l|%+6=<1%%!h#dMB_ZU@G@zpNFBI~aS}f^ z+@tn5mT>Rsl*qOiJ_TnW^uAh7{H@Vl=Twh?N@f2UfBkeK0#N9@*71&?xKYanGA#mz zxOv?SO3{g2Y@IQ2hp^P8bD3j18C-Ln=8E4`Ft0!} zt}Uid1c!Ff{(3sjs#(`p zV*V!f8|4)#>%?7h`B8_V^Jq7^^5L&yOV^EeA3NQg}@EI~m<9X^vD^Y*Wm zDwmoG#@1&UX$zzkakXZa81~9Ode4VX_CMECFY9nX+cI5hBKWRvj(LHd+7TuN z{mRAFk}hcx!VnbMX|F>##etaqX#Z2XvlJJ_m*fDkMB|>FWKs?(DP}0Ir>dD}WL4B= zt5}fHzNwg~1@EU1I=cSu?UrqFJ6eEOFzf_suSI^2^NTNTV zUi}JF>~u6pH5)KA%-x z2^w<1H}KOb`uo3emzWv<#p?Ngxl6*DD$sOAMUv{$vFFm-TP*Bl?^DxcnAB^8SCQ`~P9>|9@Kg|M2qvq3-|V?4RoXe>nO7 z<>0&iNcaCx?*E5H^$%z2e_B*b|8l?ouWir9{PVs3x%#oFIM|qfZot2>s5n`E!WaJI z_&>=5FY=`SJm0T4_I=Ns-}l+{Z+{=gGp-4@-b=T> zs*?;qNU{Kpx`dGxxwOf$#5~1l1*k`33#F5baAT`?%baVBATy&2=yp=WP*NfkM+P>B z=GHa@Hb;aA_E}g^n``fWCRFFt%MSo z7+4yZ?ZG0rHnOla1c_^AV5)Ov$^%JV;{>Yw_65LLUB%M=P)D>bwF#Jk=|kJ@!sr{HOC5RGpEYbRCoS(IBluTcR#g*t&&mKwsNT}ltGxuk;5X*D z%lEa!m%qU6H*(;2&dj^N_?7?hiGTaRcgyo@w{T>;#?SM3}FtZa^r&9$trNhFX{)h7PHHCE4#bTe`8nxd{iQn81Q)75f{?70Ciz6$T-^aW77=nV_?g8ku#Ms~g z$>Bk_*Prhh2;|6-)89k~-2oWi=QPGU7Z$s4GjH1L!28|h-}ux1SuS7LQDIf_S-1QJ z1qU_;)*tR`U&=SJYa@fRxAddmS^)kPU$OVyM_U5}n*$JLuA@_7+$&7H)ctK}%=Q*S z8Wr6sh%OWZU+O_lj(Pq~y0Q9RFL34|U*fV5y89^0>KVg(X`jcxNEUY`=tEgO<;zD^ z0kh#5P4x-y$TY#Z9}NjQujpT*oSQ6a&OuLY8D!bO7W+3LK}9#`;2}QB;LOBJ&&{R$ zjh2P{SrW*-LG%k6-#8xR3dIN#*YX>j>kI!Jli&5u?&k6Hw(R(Vw=T3f&J=EdrFK!8 zi;Pa;y~V)8is|pzS6|2_MXu6XEsjW1*=4t0OVb6D#MW__Mq#E*fS7Fq^}NG;NQXKq z*{K`m)z--jhW}*=HWr#6OK5k^l14hFwy{Qk{Ht@Srb(SyhgK^dttf4DIxtwNtv^zZ z^05~Lt(l$&IkZ;}gCl_ng;lP|U$Uxs=I|mR>VcU5V*M%ZPkw!uGH~L?@s1$yc>z|g zB!^!*&Y4nz`(_C!h28IQfcCo6)88{)V~8o`iuVcfTC6dJG~O~C1f0;m8bJB3vA{sY;txAsWhm^fN(A^b@W)XuHLz)DS?WL=Mm z-4AW&G#%79b|Oi>h`<$wZ-I9X%8>6#o;Kou;-&zv6Eom>EiXyz#4u zKxqJsWXi#GS^mw~30Ua_S7Z^Mq^-}ExOB5J`8e{Fq{)tZryzXmGHqdU^zmU*S9 zWt18eL)o}lWc{b}-OqRpmB^cyb?fiSjMYFXmOd>i42G&_LW^{sBvQ);@ARVXs@1t9 zm$u=?lt{V?ZMybYMth0WL~5(hXKap#Z@5d018N0qf~Hv}YpRa`Ue}&Q7qjJ#Qlvc`J zmAQmH@!Fl|-6*bX>UnNSl^zA!U>70u`IyOJ=Ga!RZ5f_DH)oW z@6-KVwfH{pkMwp%=AO3d%K<4KxO6oVGuPSXxGzhY0s+O0t{o^y>mAYzH_9$EEi!A8 zlX})=H2{}UzFx+JM@6se<=Z(VypE?@;>sMQQGELY8|eRaF-XKl(GWTt0n+=td(3$7;X#j{6V= zo@6IyF*Xf)cuK9j&MSObxSC!8BPBO~q$j0}g2(A(U-24LWa@aFg5(ZI8qhB}L^h9F z%nlVswl0ff>sL8G0A$O283|(Nxs?CgWRq0Iu>lbU4(CbbNn{HNo^L}J%q>uK3rKAp z9+`hihWLP)M}mh-k1CsJi@yKdW$^FTdMJol6XujTeM!$7MVy+Xhl#I3XpGj9H#QOx zQmla<4I;kX%g7=3OjI8|ph;!{_$5-W5>RU1BeM2p#<0INyi%g)+wi{jHV?Rf#7A); z4XiG^vKf6rq9v@GsN0{&Q%Tync|0b686Pil*ow~l1>4se$QI%Z`IZZfgqmupi2=;g ze@oFK`Ai7Au+s@4&RlVE`ILBmUGe%sPF3V|4Wkz~&dGAaBm{7#xGN`W>F5xu^0U@5 zp+w-LDHSvHf9L?DBs99f)KVrAS|t z8zo_~`kIAm6&lA}lT8{U+A=^Ed!Sl*nI-j;J@XgXE2b&F(-awFH1|qNcbM?2TAz*? zIY>8skO}KRXBQ=6b4r>si0_ygfseP}#YRnj=aqfJ6yGaaixOD}M;fzMyx2S^g|-s{ z1$J7BdPU{{>5t;#F7Z`J?|CTCn=~5L0==w`!F04{Fh_2HMv&>+UMJQvx6JRiP>}cp zeM0b*?)H2QCDmHXFvQF}%n!^!O5u;Csz=n8shBY5oY#Zvj`dDV{?h!Xc2K-q-x+n$ z;}@fQp|K_e|lJ^it8)ZJ7|i zok+JtfT0;K(Wa#T4JNpsxNLH*AiazgP@2Jr~w5yrJ!rg&mxgZ#qtVhk{a0*&R%S&r5o4<(vtU@GZ^Qp^zG_>UZm2oF&tnOP~n7MSQ7Knbp=Z z<89!7A>ZJmLubD?4v--P5{i8GAa^`7RvyIKT)Wv(ot{tUj? zWzC>}JYF;tF65N71orMggX(8h(dczM0WZsMn{;RRE*`nqMp($1xgEU*|L92?EmD4AVL#SjSN${ z^s#7^wy!jmOAWlPzk@9E@ADi0LfUQo@#NvwU87{Fiot}ur*9ZsV&$2{`Y%5*wA8@_L6^IAr<@pGM#&PafS%6VGBFY znDcn8#n@4&910P<~Mzj4}= z^IcEUjk&j&vX=&+Box1+8tFkA&Cg8gx9iPnil1+B4J0mTsgDoT&r@&LJ`=Pr>F!^s zzRyIk`m{S_xf9tuo$d`JzD_;3|MC3|=U@YuSzKfGiH3Y?UV5k8_q}!-LjIF_{Zf44 zCh%pTTzZ6D6AN*+P*j%Y?w0@T_B!{J5+f01VDkwMcjaYy^Afa9ffRw-7tKKQ5=x?; zVgox{TXY#oMg+|Rq1$>G6yVk;r?gN&Yrma5*Khj>w_=IVElK{!Rw|kH`PThxEbfk zdcB2$VqJ`hbo{opM`-*4QR>SLKDPEEuej!f^=kOfkT+y&$;dg@U*jYe%fhZ)_w;!- z5!jn(%$0Kt0p_>C_;Bb7=?#?cqCX>1J4N2Hw9%}&NyUo-6EBGjI(*vRmpf8XTMvHBCLHJe=i&^$r;W19_ZQwva7WR;lC_2#{YpkY0W0Q5?M zE*6Ad4=MMR>3J7}F8e`EdnD~-U4rSHsbhYx?1EE*n@&(tLmH@()e+mtwVpCC^J{+S zX6JGP!7m9@&f3QdK@~yA?D@N86@D6-&RGKY{=_08ybAnd39nrpG^Av?vfhRjO5hLC z+zF4h+4B~{P;2>nn>tL4jy(oiZUm%~n5=s9;K{mBr!S61xU|}Qf4?VjUKy)s_u!-@ zQLdM*MvY{~V$jNivmotVL{yoAn{S`O;hbB+hxiu7%Hey?c1@Wq?g5VI`qDzggDDVT zm}_#(93}Yu3sdJFH#}(&O9|6rTuQJmvLIIEDUOU(&b5xHfoV!2uyn`#qbU{6oTYVo zq)a?&yoMtJ?MYDW>6yX$^HN=m%-@z&h(@tpBgKrTl_nes7B*y^Gd~5pY@L(JoBPc? zrnJB3uy)ZR#(zC=f1h%CaIXRND8yN+s?Ab&B2m}23@KN^ZjrZ5M}y8ODM|)RJ85(2 zBKv(h;^WuDlf2snq;bYUlBRO4b!a?z0XTeO^D`=tmNcnGDfyIc2)oyqBMtHA#2S!`#?&wQi_~^wI%P_~#9nZtPWcFon zGNpMVyi6Fr?=hvz1$@2jXHjWRD3PQCI^V0Wo+EcO#sK(4L-9#12NRPygf9k?r=OYE zCuz9=uL}w_Y`vV13ckPp&w30Xyav`15sQ)>qd1WiwAFa9nsM^DdVEe_QU}=j2mW!0 z*JOx_O4N#8^J7<5iilGD-*H%4RntFPlqkt)>Xz4C8hTyw z8enh{7zvshyC#q_YQ<$-w?%KdxHQxSAfBT1z)7k~ft^YCfw8Hm`SI8W7Q-;nZkXG} zRLj@YFpWEM15~f9-qJZy%oD?vrp{k$rkZEKQ6VVE5DKs5U|}npr1gM@Gx|%ejjm^j zyI&m`l@)yS$h=(mOvki*b(Z>s?uD~+6Z@d}+WH1yT+c6ZRrFYT=QMcOqob6UfTs)$ zZx2LV^k%f3U^dz(XgWmfO8aaBTHjy&d-P_a!zE?}N`&Q`(R*-L8%~7D5A`bR=D60N+Fi>Yy6a{YOpvVn+IDb?ei^fW* zlR$MbcBA)`Ds7z$t&%Qoz@@ssY1~! zle_Ctm2RRJ89;J{6AxWE8gj5S)MY=`l_;%qXBmJOh5_sxYC>eS?t24!T>7YMWJ+Jn zROlPY9gI384Q&8TzjvIH1blATJ~=2wR}=F0C{3B_c?Rd*cl$8{FrE8%m3Dn?ZbzEX zJg9df)oa+16TmOkT!mrNjgO_P6!=m^mg01)^c0ja)DZlBTM@N96;u0rrpL0(CNa7l zo-KwsAdL~g$&o5|*%1!0ZjMY2UBt1g{a`01vIgf+sOg(=oeGB@NCxGOoN$8cEAcEf z!u9*bq>NFBh(r_E5X=}fntgVT&;s>AO+tah7t-CXB?ThbMdEd}INzY6w0>UrpMQW? zbDCub+P#aONZVc{set;GW=C=Ly`O$$t+7c{&isNc|3os&K5os=d%ZN#iXzLZ}~ zMn8;Jy~>q^m~YAO5-F(*90iLp91IaLBOxEkq;*y!1|7q<>bDY(ONx7|*IL*p3pNmz zd)2GZ;bgRq#y*DEIz_khD%YxPRha|qzeV@eZ@{<~SBa2`xt^)0Q0j6H-)?rgWk3 zMnh1?;N%j(N3A_s&virsK+ryc(eAfKsw9~2GP!c(z|d^a*O#9=nH!|;&y80a35*J3 z(_;2*9KUAjn9MLDca-?3Rb-Bhzkku)VvPD73@MN9{(#UbHcWe-6`VO)aU5nPQ14XO z)7#q8zfq#&c7is1;_*+gY5?CuCiuf-GYRZpb}QGZrI0*1a(6lW9h3z5wf!~n!0PJR z3!PS4n^I$mwUH&bPpXrrWtHAd8OfQkiWf6Q6=miq*UaOxI= zYQA-wM%R5FZaP<4U^Q1gg1g8L=LLeSZ)}?=M;Kd&sgM;z7#O3XP|?-Jik62Zt_4hp z5W5Ik+G3l+#=yTRB!=NdhkEmu#lWX*U(<-)#36r+<3e%=!tuDFG8ifF=J!v5=j;>V zQ!9GHym@R_HTc?}7tJ}Y&a$664uQWnR(V2Z1YtC;OybEnYNvgHBQe9`hV9*1FF>BL zm?7_JKXqYLb+)arIytpH5hc?3zm2r=)UD$PP#qpXqgdy;%<{ z!!~R}d-QY-+hk zF+C2iIlj@IGtl^_c&q%}1s1$?T4GcRa+-s>w?-#v`fdH`0O9W_Ib#&S z<^@w{{H}q@@U!S9H`Oy4SZ*kpY8YEEVAPLGKu4)_c7hnnIES**(4w8~Z8rTaDF zFTiaTuU-w<#ZpKXIk=O@Y4_4krA_{UaiBS*6zxt;(0q>}#%k zXiWNA9`mJ*=tqsMmH{d6?o8M`E0{93LJ-^0+g#+tF6~j4>6)WEqOFg{tz{=>P*g{VQnylJ6BJu7rZF^ zTLMmLc{@2tP4?c9x)y%oIIxVv?l7D+f6>kJ!Ov^GzRHTB*6fZ!0Ok#%$FB_-avl_a z=fJE^jMwz4A1+Ic3TlDE=z2QBHdPn~l~K2OytE8r?7$%BLBi94CN5x&hw|Od$9vjw#biM|v7enAc;6Z&u&b`Ux4+2n(aoxzH4-Sw#{L^XPXK=(x1o?D)aqT z+n$Io--UVpqN9{Vuyda%D{luJB_8KxcwnkMAZZ<|gdX#~c|R?531#zlKvvqM*OGrG zo8V@fTvxd&e?g0}+(`>k1bTdR`c=#^Orr&>y#;@q4Ch!bK)72L(j|bryX}U$L5mz> z#9i@@wMQ5kT()Cjfs%S%yo%(<9ac>V^;q}u;KVZA?0wNC>>Kmk*Z-C$jCM^r4fyt; zn)Hn*eA;|%8E^uLD5V#DB?rYE;2+FbrKS9d3}gGb0_ zc(vm_szn2bG2Hgr7^G>ub+XW-G(z}(dGs_2|Zp7m?TsqG;u+6dhOzWBu`LlaHVLTpl z1!n>4(x^1w(J;F@K}hyo6bt3~bFj4a;CRs?3_R4Ism6|D6jcxsn~)&e(}Be+lzNXc zGFOU$IgS;7b2yo+yqt`kZg0i5IYR!Kqi=whp%%}uTyuztL5^#?Bcg&VToJGcZ0Qb+ zmB?x{P>SsLEXfDez8gd4o+=43zWaWp(~WcawGB26v4r-BuTlFJP9jQI9k4xL0$teV zjvj3)iVk4c;FUpTK!~OhrJXXb*)=y+J=m&90d1yras7=RuVf&Uk`v;Gq2JUZr@gHD zakF;J)uLoGQ76}eZJAxs;Hr|le0MtEZ!@DwitC1AyLX;13vFN5t_esSj6eF_T_)42RWem|eJG2}JRfnSPHfGZ6~6vjwoO3qzCgk1X5c zHN-&kY~3Y;nu(5tWqR2aW(0Q|c;ykitg3HJlB+ZkFNN3@>pxc10Kp2WX7V@;v-|mW zksjAy0U3lxx{2`w-|A5dzZ|FOcjD*gP~E_OaPkWu&}F6AA!#TOE;I3EnJHHBCD#Ue zRCegEz=i+Ztu6Ha;=ZK}S1JjBydClVy$zs81ZRl*SS$!vP;ULcc2y502X#w`EbV^l zenMk`MF~%%u*$+YTNk_^GZPRv5;dmbT8CpRYbEPnETd5HOTuI-X*5G+0l}AbsKqT< zpD?CCq0%p!sEanYFhjL9hSZETCOCHWkm!f2xhfMJ9b*L<%D-|}h^4A9DC(Oz3pn2c zroB6>(njj8@>QQEPRB*jw15(7TUzyp+wAnWI?h7~4#1Q|`5|=jrPbeG<(SS_lUvu0 z*1bl^6r!zZjtjEB;gsZO(wyi|4`xi^^E0wJC)bS4$HW00PNics9FjlGrJqu&tYbag z>gyTB59etSks8P1rq!pQ_Ay9V#sNVEA4XjQ!y%O2wb6JWNyxKjg?a~ag_<06POn>a z*vNqUXC2{PlMd^0%ZyMiU=- zpytT*p_!fDh2{*L&s9S>_bZ0Wu(4A8N7|Zd`eI|-$k|u$TBqc+22U9x@7#@GcY)N& zv{(zl0^BK7H_h&EU_@z>)CdJJPDOUb{*UCJods_);JG2LVW4ZM{Ce}8I}~H{MPALg zl8}B?^Bm$s3UuxWD9ap9_7_uTw3@bkC^5~@dIOAnz1j2<371N2itP4*lXyw*f-AP* zYNV6}SuhnUkRXmZHYb*7vsYd#MKAnzLofxkZ}g@ruMndWgEw=Au3*f%u#~V=1vftL z8qxXpM|(n>U@92KAb$wIh1PyT5A6J?IJI8M^c&a4zfQ>im;}$}ArFvfS{M2G(Lc^q z35JBJha}`dY_ynk$_Y6TvAOc6A~tUAq&CAUkg)k(%)wY-Kqq{4>I#89=O(#@+W6H7LTz5)!<^9rQtuFZV@mf}aZASPEK~fWs zrg)N+yQfbr?5aN6$e;^7PWBfp;u3X1eFJx?L2zO1 z;TA!}Q2SITz1PDc`SVji8d5{O(=tL+D7`vvf9i+qobP1G9N_I;czf#EAT4}$JO-A)pOduC; z%r9D>lt9fm_WHTm&DR;|_#Nntq6@9CQ;#Unj5f%pIhjC~2250YYn^b^7uR8%1SZ`P zbS>Uf8*KC)VYaWX^3^)%I9*ykF=5q?|MPTGqKmu+09HQ4^#&5EF9%S0@`IU_*~>5~ zw9^OnlGXHr_?|qq0$aAh!$LM3R2>Q#V(l^DL(D7M1E%a&q!(4g@-bu;>y=(k_dC zvF$(_up%^pafJ{Vc8zXHhgs|C=e=>r^ANa5Al4%cX{}r4#bFVEFgLzmM}LBL0{5)y zn@Y*iFpd~bC8=%+l+l8*P??~LJ)VqY*Pza5`%M{Fwzk25;xc@!Y6WJZ)+p`1mqWdRB)7^T2 zv48c-%cPY^CUdNNf_~7@b>Y}@70U(oZM4>JAsb@sjm!6(pG9vm7Q>w+g)TONt&3iQ zs%Cdoje{ox6K%1?7{Sd<4cOyJSwOKiY^fp$`Ua=Xw^yUWeGW=0dx5Mbdv!p`ai_Em z#xgkiihzP8d6h(Tl;0Zm$AlU9f-#8dAPxU6ZxvMvj9bQhBf8)0bb~UI(WT9neD*NQ z6uK$uyNBMO`FwWk{ei{ntiVShX8h$UM)!$UVF&*s$D=m#B4RkTQvwHn2hoc-{WX*e zL34naVlD?)j}dC{W^sgZe@4YE#TO~E6B$TJxTf`7P!$g$3Xqa$N^o^1I~o-)+LY#z zCXIU_F-vN6CIGQkK?r^!5~I$QUH(8;T~9hfD}vaOyDpn>S#FjVnZCb6f4{>1{h4Fz zmQwHT0^csM6O1C?fr!WG^(Y<@YM)@m>58CX!T7R9)K`XYR`dzdW95cDL&_ z;cI|BxyTA`5D!6|qfXv>iv_T3OPI#?F{*Hdw@tr@ZaO)>3PeNa%dH?jXwo@@G zRWBDQgrA6j*L9cg?CS+f^iA}K?Fq-S&-yz<^LIU4Js$!}|5aef!F9*&BccG?5{<-F zzWzaboGt0Z(-)_h>@L^UC5MWOA^sK6cN~U0dZ~C;i9F|3TT*?G$_Y~AZ-E$pRmS$? zDAoW9lH*|J2%-4c;K1qpbD>R7Lz}nwS%n*AKl{CS6ZFc78EB5i&OM!bR*L=-+d4qyo> z?#JcG6ST!ZovKdpYlqiJq7&8^f{P!D~xE?$7P+9^tr#2SJjnmO29ZUfepj+FDOwX9>y3P9WKTJT2} zSjOboG75J6;+W^ z*;3;>LOU3TzkNmlmY31Wf6w0isSJ^8av*`&d~qW;p1HrZ#frFp(iv|L4f)cefFeU- z3-;%r#+b@$4;+X=)*?O(E2qVP7!0P;7ch%X5Sp|mY@2l>($OR{f+;^XZi}meZ@}so zv-U<2O*VIe9oqg<^P2>}OYr!EM7`T&%mC!^G0zvCGh8~9bR4@9h}9Mp@sseZy{*|Y zbmtdP*Xg6Pct7~kxY-B2$h^LoW(Pks|12qFD{*^zm^KhG(_*4v8u8DGB18O>v{c78 zztIC>XdU`9&8NuMV?4IXZ7Z&h5cZyUv6$NiiY)ZnW6UdDvo8Lli(~gGijR**_<_rv z@oAjFdZCheZ%eDrcxUfVgX7g4MA>?*r>V_p(hlUT2k!^0nN-8HBO=C!T1*P=D zXqoX^Xb=jj#O++^_*?Y8)bPM}m(tyyr0l6*C=A9``9F#MTWx&0c?l)4N5T3m3V(~7 zZzz!@cytBvN}t_~WKt@-m;QL-0gW{_L4KVhq*N1?;?BKFxWV9hM2;BQW>UnYbuEUR z*Peytd|R!;q{|mFKTHKRzPlon{)%UQ#Nq6^%$%GQSy$xYP^2@$UrZDGURbP;z;0?AA>_ ztpw**MfB-Q0wZQL%z|9|5rvG;R75XF6Cvi)$(D7(BR{Q01n%i^>v{yLc%ENgy{WqvDWs9zOs0xg zl}+;O%p*>Cq+!gM6f#qY$Q4YwI@38Q?&mi`V@K>G zEyWe3h~PW9BV^2qjglF{JPkm@+}|ZUWr%Ws5SU-FSO1zAWdZ zgqd&}8DM=v&8)}rH%J;yRkM-xQOk|{C^PZ+E4=sXO4xV@#I-4QjlqgKO?j=z84X=o ze39b{#u59aImx3wdcVwE@a~sm5eE#j(Gi5I+J#A);h;9>?d}BF!<%}}P@Q3PN%0%I z>wazgG>3zDLw79SSf0ThGM?8yCAGv=d|ljEBuP||)s%CdC0cRXJ2nXp3IUZrHWte? z4T=7M7m-csRsK>1>{%qCv@aWa*(fcMS<8PwWYO9fgR>W!5N=~z;PLB$P%x1n7Bu`h zS)Th|X(%eI#}C{XMKkb1iZ`;N+=)+KQG*eH%ciu|VZDU!CF9&8sMZrX#|#*H+p>ol2*qEr9f#o9w-_3-;;( zuF&)$!dys9y<-TVdkX001>Jh1O(V&${NW*`cvd<8m>(iHmFHQc35(;(MZmzM-^D8y0+F^mnd=(Goa>6!g{88L z@lrsK4NDM_Q&RGv_D~axR+tcx7lBd#8`-@{RuS8&Ayv;3St3;dbhXI416ECU00(fu zJ{*@qZg?K)(Wk_^I=REjB(aiNN+ed~>FswJvaJ8v4)<$Ukt*5R(T6HKgU~inuW}(= z+odkQ;C1z5xBz`u2IV17ci0GmDSs6awe`A!iy22CphcYt$*X%p7J1%Fnry8QXizBi zhhv=yy9RgfLBZK`F%PotppeQ_U8?wqN;R_oou&?zzcp6APF&EAiJudD;%`H+X|Hej z=;qd@&C?I?kpj?n;EvFO5aayyM*{cX%8aW+LUv$&H#V7odFgf6v04}pEqCJd&fkgo zMT*qe_81}a7`i7Pf$KGa@-J$C;G1MsO_s1Hu5t*M$n6m&*e99EiqS3|C-clMM`Zds92sXdI`zYm1=BWXnkN2 zO)wIk{8c^kU33A(S?6|5i>Rwf>dhpPh2f0J>D9F~+kT*D!%8`iEkqI2{HmOmlN94M zuhWhy;voL~oxI2$#sD`H0Yj-VPR4Czk3WkOM`I)&)3Q(L${yTf9}zBa=0f$_Ns{pz z`%a=pB>7kvC$1-?5>0xFX5ap>i3<4;sai2Fz$V6I0?oa?u^1HJrTmmd{|#p@rlBOj zAO9&Ja?0{>Hh%Gu*)NtFM+MDr72k9U_5p2EeruS_={t!mF9iyPv9BWpU>njlQ;J~^8QKl1cOYw zz^u^-4iYr01&0AMPisccM-Gb2?M=Y#=LAn-S@RFSQy$Ce9rQF2k)nsX^N}+~T_ssL z{4KxWg%V0VD4ZDDdOwD4{Tu63uY+o^*!L+bEqv`b*ZoE=mot8-MV6#LjFN2!p|Slb zBxgV>4?oO*IW_H{3+=+z<l-eqS@x^ABNQ(|WMj%hl!D__y=j?AP_lAAsyV=n35 ztToaxV(?}^aaXPy%e5>7l(9InfOKk#0t#nYas-RksYW$fzf|)`5)M1xrFuRpY`P{& zzF}I?VFOzimFll z!``!LLzSHX#qbYqWhI;VprAL=(tA@bDf;4*UmfkjTnTyZQ>Lz&Wg5$G4Qb3j!ey7$ zZp+bb3UpNVRZqg4CbNUEZy?9zI?r0S#&}otNplWTE8iw-1Q3qWMG=J!Dv=s%NfW&x z08+IBKItOAv!%)^`IU2(sjP-oIu1hn6^5g0KmRWFTP4od7fHP)@7x?@iQ zpmQ2ZYrqNEr$@EeXPGSOM|NRuu>=&zb2$#S*MY1PyHos{V!POfn~y{RNp#=L?#{-( z5*|^BU^2?o6Lu-dDP~=WZ4Y+s3ud>z7!7>aGH7`F*}BQqE-?P{YJR$PJ?5?^hnfL(xlnwa5X|v09(%!J^BlZlv7b+(1#r!q=Kn{HKcu^t_1m9K2(bRqRsGXbUP`M3s2M-RVfRn_3U z_WCGm6@UEv?$T}YGMd`|g*LWvY1`lW6uIi=U%+~Yd_^h3>zXzsx~I-NK-v>IUI z9!ffGoGJf;RGqz&AZ29VAxv@;=CGW&3hOCn16$QQ2G7*gKOI2nury|0(`Gaa)}ivk ziDCNePCWg=s2bfh$ARIc8MX-_D`VuGBa7RYtW+KQQ*A-qn?JSEfe_I}i+J&yol$Lt z`4@$zM?ez!Zx6y%r z4L-HBs5^^@yj202PNIZ-JUsc}?48XFeHs#1-qgE+khWLVKPyya&UuWSOEhPb2FZry zT=SZVaC5U%2RkXNJ1@(puU-2pKUSMa+AvwO*h-A{y{>fT zMS>W7MV{SB<@Ase_IdybR4pRR*dUw(ph9SJWqcN8#YkZ^_ML;hyb|~aPr-g880dY_ zJ@j_{FJ!=~n~1Slm}l9_YGP#F9kIj`9AARx>2+faIFkyXNXKIN{jj7Q8!8)5fziU4 z&dgP*TZOi5x(D7?G+y_ZB!U=$cPIyZYte^->GY*>_*hjFYhuT9BxRb&zqXg`R}Xy= zX#vvK&@NQC9o|5#<9GO+*y%U+eE?c5-Tg@BmNI)6Gu# zR_g*TK#(IcW4}9AFqjt-R>d-NnQz1e|0^|NMq87~S%)jh4WEjM*!W}7#HhMUf@c`& zH`I@N#)(NO!fD3>hDfqG*&E2g+oG$+swM2Aqep+_=`CIWWxf=${GYcq`S!TdC7gw; zOdQb^27(F2{4Hik0;^G#3^((L&mo~UFGYV8bIeK~p$s5^XZ7|&l*V{> zma-qpU2DC_ieoE<9&mb`34Z_G-YE5plI-gO4MIB{9_@IRDblfFSz$)mys)jzIHYCG zngXY);?UYTPD~y7*^8$2f@WKD zL84w<+?_vFZpL)@_Fz`^)9bA#^G8FSf^n5Co-iL02y+U|kI*34E>V>fva&C#Zdbtz zt2nB$yi+K*ur@PMZO?S&1EFnP-RQ|iBAi+N!ymyLe-QP=mnpSX^o##2afVoWu^Q;+ zNn_~njdeYMKdEhahv)qI!Y3oH!qPSX2u#OwaM?eK`X~k)ort3{r!HFP!jfV)%u=Mn z4roH*j*T3qE{b4Er_Fs@WY)xZF|zG!@~mVx`btn?u}jsSfGx60*%x|1F8<6?WO>o( zBXc$m)Ok#+xeZ6wcX)-PZ!-h_y5FKK^Ki+r+B;aqMb&&3t@uFt>RH@U;DxtAD@xCX z#=?)$NaQgvUk0D{NLk*-9mn5WuO?4?J|ONQu8rafLkpH60b0D+t1vqjA20T;Sr;y) z6Ibn9S1AGV79_djXQ04fu_BA#&`}KvM@$s#5$N9t4Ja4qFe}*~k7SdWq&PW%Ce6oI z5dOKNp>VY>5ZX&J4&#>{4U~6ijEO}a)3*VFAdpN-zwMY}*i?No0V?S>E+MORu0qTR zpP7*~okpwEQXL8XctDmu=Ksqp=!kz8{qs&Jj8%*2!ri;4 z^p?lU2&~z4v)1!^k&@$ju{C0nzBvRmK^gWK_cIPOEBCPS#~*#H25AZ-oGG&q+&?K; zv>j`c)@jJUeV7Dk;9#SyiHlrK#S&Ymyv241)IJ~r>BBdfoY}4!ur3CMI6Lid#F3N@ zV3W(F+9U)p{T~7myC{zw@{heU_oGPpv^Y7+Y3#6;o`vO0^43>`I*FIB5Y*O)@sPYJ z&bUk%X%K?hDz)qPqhKPFN8P`c))x_IXp=(uU%hNiXA1jZZeeaJE;iG|cMwDozi7Rc z0s{0MwbyQx(n!hN5}Cn2qYgwvXJgf;nM)Fv8`;6=r;A9DFtVu0-5nVsm%u~m%_MoP zzNWGvyfRYwA74Nj&KCT3Eteo#=Kct!WdTGH`gXjuPVAW*4_Faobhv0a=TIEZ`&2Po z9tjQyl@m)QeuXvlU1D4*L?&$|_7L&POb16FQgoq?9#I(Yt6=tm;x^jrQy7kFFcEbA ze*qE;?ere3&Dg^9RxAWp!N2>tU8Y6^sfb#m0g)#pnKF4-X%rs->%Z3``Ua%p>adyw z?{+h0m_)LDL*>5E(*#mLfg;M~;p@Vr zZGPCb&h_Ow0lo+5z*^sn=Dw`;Nua+>;4ac$DFqlI93~*Ef~;Mp(WwSVtv2M%|A^Ea zc&WUJLwASs(UaA8V|LfbmpXPD4WVPazhi8Um$saMTD2p7G|&(@HYRIMj*IB&aM}T5cYS5e_p`5?I2F`-(Py~>d<|j|*d|>C0be5jIh@VF6-CJSi2>#pb2 zD3PfY^?xT4TlCHT#bQF$crspjxOSyqE!V6|*isRa0)f=D{_buX`-Z zL8(iosr+q-2&iWI)KHJ7#M)tMp--cY4Qrg-Oei|P*QW_#{Pi+wWB^WLd~7?Lb)n2N zowrk!`E_tCsRq5W+n|`EuKGLw3tp88|8hio@)x@(@hUfwtxE@1P8K`(D8Y&1N zNarYjc-1D^aC-fa=G#fc7E1?p09f4UD*EWf+r4@nEa^c3bh03IE2O7Fbu`^G`PDIp zpPa$Ahd_@9FQbu|qQWcH{icqnSzFqGkiy>Hn49xK^fP2jk#k0)mkW9)Z>84H9DDT` zM28(;Obc%SxvorP;?Bl(CTxE7xm6^UK(`#?9QQ4QkdORC3q1`KvKKdSVf5qG$(9q6 zKP6ft=xT?m>gbU3A=u77opn9)9iOe~rq!6eQOpNznT*<3X;Lx&h42|c1)q~uR$2a& z0bo?&UrhkmWn^7|U0;=hrLHsFLJ1dci;m&|b`8YBJfMob1m~ni0#0VzU#6^B9{&R2 z-xJO$ih)1t+Vcb2(gE8(pDTKrS}!{h#w4UPI5B!m-*+OVV&8~s5tTU{u`E%_NY#I9G-K6;>92p{b?Yym(7NM>rw2?a>|IN+bAtiOMgGCttu;&Fr0Y@^a&9I#m+Jz zqQW(}D7aEd?}E~~cT0(>=c)&Q*~n6pv=|b^)0LQ6UeN{bx$8K#0hh%7OIuJ%EBx)g zqYqf4mVM%HlVbYeTbh&(k9yy_))+V=qqdIW2^RtEiyDd8mD9lQaO}76L}ty+qQW%+ zqf4`Ojs!`$ra^r@xhHGSAU5EkA5LPaRR!cC0TTBzW#v=0q*ZvE2HWyeu4S~JudeA( zZJ!HtJJg1A?kc_z=fUJsD|JIGu2XICbelIe+m+QwhIhrlxwEmor+fMNUyDohp*C3) ze=;>Q18MB?MTw~sI8>j|fm>t)cWGha`E&;AVwIE2Ew7eWlC5h*ZR$dqP;m%AeC|? z_1@0<0g&Ug9sVf0X&vnK4}Fiy0hT!0etl&^xXt;Kna9i}<94!EmfWaA{$Ti0p1{!2BG`lsVrwUEByi$ zm7_UyBezb{fY9}vzV>KKR!$qSRQ;+==Aemo)7KKf7QcD_d}JF%nHEbOeC0^Kce_Yw zOe!7M?%#Rjme7+-SG~BHU)EE#*feZ&tZoZDYBNK1I9!$KcZob%tZ;4IzkY7M;OYja zY5}UoyWxhd*)6%dAl(C5=Sop4;W{Np`B_2*Z>51438S!fv$04QxX{x7VpjnauWYT7 zoNxCw=ltWMSr->c(E2h`y7xm^Ddl}58}jL+vTGCbEWy(1A$&1)mDD-Z&}V>K;9)rj zCU(Z;EAZ#k8!IiD_v$5EiXtY#Q1JvvlBl|5yAF_os+@Qt>ay5Y0fRy<@J2OeV5-|%FY$F>sVfpS!VG$g;_Dr&Z9Ss{=z&;Bb z^-yHYQy*Ay*W@hERY$M~OH~yPB2W`0P?^6jq&JF!`6UBZLWaX1?>2*hyme>}CEs7J z9;-;ho0lTh)TchPm`~F6Q#pzq%uy#p9q-YBWNQPh=;LeJ`U3r-Ld7oI;A@FGP1i27 zTHltPcSC{30*4Fh&4PuQ`*cM$5DYakDz|Bkb>#)9DvzXKVABw*HB-tFFBDI&T6d3! zcF7IXR)-V%rM9MW_Xyp*Zuu8x>%p+;UM9N$j`ut54LfjuE>%otB^!l%j}@}D!tK$h zW?XH}V?X#>xHIFDJHjmRya-o9Y;9j3h&NUqs%RvRuHJGf zM>9(LX1h=r?Us-$XT02MQUKnEh>5-Nz|HmuuA@arEDA{s`>Uty z4(JrClZmFNrnW*dF1#5+)p|N~c|!)oIFTZ&lT#r1az-rcYjwoC-vG=-m26jiTHFI7 zW2xKWhY1rux7;-;D6SbzAzk_?5@CN&rLqTFN9PwPl&yEi4)eepM*N%`W2MlVkf2h}5;J5~7RJ0i=xQCb;B+|$XqNKq`+rC@r9wB2KHWZ|Od{n+-z zcG9tJ+qP}nwr$%^CY~e{8xz~k1UGvh+Pv8AQ4rIWF%?f2Nl)XCD>`df%IaxyeF{U`MH&(Xg@Z~quto4Wkx%irUF-{ERw zW9ssstemmEt*s&8AGq8E7lXKr2_O4Ff@SM4msp0o`egkwC zo(>kKcHa)2)juUV8&hZJe{ytomUgE9vq|Uhea!YI00$daXMiKX(bd%1#nRsHdtmQk zYGP#bpM!rp)c>Pk=WJ?gX>4!v{Z407x9=lyw)6lv+ZZ}q{HJZ_;%*Oc1-ROom^wKd z+dG+lQ+MwFhTQ?YOr7lit9bVh-|oMPcP#&Mjs0)&j)mnvh`Vp`j){r!`-=E)#5-mN zHqQS?@vhcW*`rjq-83i4_EN=W!)!#Z%IIRXZ92+!gN^!IzpFS~e17IE&+qTH@A|#u zw}NXO7s~jBJ&Wl3B*~D8kiiM6q}j@pH7>b)L4o7XJH0H zT8!MtzUCULr4eJvo#hCk0tW|JBo-ccY6^&)o}ONVDIg-YHk)^LaSB}b*Pti7RWbwdLqaG zzJbBzRiu|wvkNN=o4=Sv;H%gh+Q4|YeEq-zkO7sweXaZEh`6>u0@lLP6vh3}KI^hJ zpOWLt+ei0dOB7F%Wd{3yP7Ev%TU^0>#8i>cztr>M%--Vsjk$sN4Fh5)j%7)3gv3vc;2~sSI-UjD)sW!)|PJf@3H;te9Y$r!o!Q9lRYua%-}c1=JFe51K0Y= z^qz}OWsQmhgu35JTS7~5KkGcdjimL@neddo~2aQ7u^ z`u4?__=Q9IX^;HUFS`B3@A#!#{B?-@_0@OmUykA4)RMB${)QXie~C44oHW-C;dAvP zfcDRIQR8C!*N)FaZ9tmc7kj;bf34kny~`KCL@Dkq-xj%v?IR^DE;=tYIq_T{XjTyS z#LA`w$c2UFd$mAqzo$!r?yAV$96003#LZLFX_=k#~K_}9c$R2pXNM|_H1Hbo-fjr zv^M)NH{YLj3^vQ?%;eiQ`g^e>L$mi2aqx@C=&k;q-B;YZfJPuYF)uOkH2L8gu)nkV zWeMc-#g5HrEsRs#A6#-#VQ>4u>HTH-0*k}7w&5@J`J3yd=8J#ks|Uo`Slw87HB}Tx zI8Wd{NkW!ARNsrUJe@GVU8YNyr?w!Dqt z@BAVp32#Ok+Lq*KdgqHCsY>sqv)xA zXuZP7GHuPP{+(V$cVvz;_o5WOEus%>GIh~|Cjxdrg0&O;yd?4*eqJS5FRVN)tG=LX z-SOhd=%B)*#qo!^9#ZcMbF#lb`?hb`52~5Ng-3+Mn!V7af~umqw>OGVkxzvm*szt) zz+nqd35aHS#Rf%#v3{igN-*fKI12Lc(<)L-q(VO>XvK?GGXHf^eeC+aNriFxOJ`1? z<7ZfeXe3$^NZa%drBzB$66pP@)}W(Ul2uI3cx6qZcS?kh>6jA1ac5-U;m`v z6%>ZphlTqC@%zvUxKd@(yneQ4nE?ARBv^U05tj>efBU{E8rmWYVi{kwPl%r?wP`HI z>fs2u^t#0W8htiHeFmOZUCW*1<2()10W`h;sUR=r~dG~#f^!waq z?bcc<@#s-J14RM5>*5Nba?AZlt)GN)(>X|q2t*ja7X4T@tK#_usN;5lS3_Z-8uy-t zc{eVgSeApTmpjMznF3Le>(6Zzx^w!brT{CuB^uEx>n4aJy;lQ->Ko=sFnusp@nNJ( zDufJPK)Egri1tRw6(_sS6b$XCf#;a`ldln;)&acCG~|VO=Pxh0YFjYQ%uD>3@@D5Z zAsab2GKdL1irpdc0%iGPabn7}BbmZDTi>e7w-jcTQ7xq!&A`Bs2t)KhFBCA!tVuBc za-(7vy-Mr0=IW@Cqhgz|y^PpK+DtFf_!tUV_tFq#$i{~g1>ro9Xru^`g2;0{P))Q`xsxJ+kIp+9Y!ePxq(up6ZFUB0bwwnY zDN1p>C7hztw>?I^Jo@rGQJ1fzrK}Obm38!pi7r&C12>#zv&kK6InbZ}bs7cnQ!nP` zeeCK}S^X#|h!5$T&o!uPgt^>3X`pjI6E?QyFAfcAJv-H?k%v25@=^%qxpE#dOkI{g zcy!n(#AHg&vH7wYoPU*3sAntr0^<}B(6Tatm!o3(J&HTa^JZFUiB+J-T+jLG77myG zS%o<}HAwD%bS>iTKg0Cq=5d&}Rxu2UK(p(^lqSTO8@5X(N##xH+NfR}Ry6LGS5nQe zM>p|UYmiN$P+_WOa%{Li(5-Lxh3Xsa>5|APWk-<-P}+UuXfR-?tCzQ{0+BL(jUliXMEnf1rw;V&L(~ITe?^0Q@An#aIL$JC*OJDAxy! z*;OdbMANI%)!&86-vduE?eqGa1c;jGGGo9yni`L;!$a1E{w4iwl(=;(2{0iACgVGL zaZ@*}f2Wr6Af#WGIPvMmuntSgx0EvF$ugos{Sg5{tg?vrcp*oraaei#8Uk1m56B}! z%_zK5$v3qGKWO4YWnsqRkVSOr!_dH|#;wFvnvheOVZJ6hjCvW61>ORLmtS{RXS&y?EeRxmrGH&U*AR>%NplXdkR#>6%ezHUbEDNH@ zfg6RW{1FeTsI>hGBUy;H+RY8-NvK?a$FK>aTnb=r4s!!$L)EDJ9iX+gytsj-oIt=u zAe&g{=fWV}L|BF4w~-O)t;$ABbtq5?%c+XKmrcn51aTsAGvv9~4`w0R@!5f+z~|%i zrIdXjjg=a>b$!Q{`O z$83eANHYjB5#vQkXOi5oi4x{~eLS%{VedDQczNbkf_w0y$%NLWgacnfL^5f{(lwRZ zk-?4+-$cu&vOOIW9PsW-JO2!DX0|ouY%AS_s)6R zmx->R#x3UwQcT94PRUJGaRL5JfxpeE2ks5RYMGC11}>>GqSAWgx$5G~I^p z%&eB_rxe=j=FkHyfGr4E8+o+jkm^)4POe=8@uU0C8J=!O-&AI}s=m*Wk=EcAcOroH z^G$E6o|x&TTjCB)DI@PCNV9=;Xf*9ZZuDcULs8IX(i^&}{5WZ&SP9Rtjsh!KE;i>7 z&$@%56)j;~+O+PEFoDdut=aZGL`g?nH|IMx%GO1gb7H46IeZQLKA0u%qZV5aWcbwj zrQ?)b%BzQ#%mtiJ4<=N+*$}TH&`0%K0#=P{T)_4lG$gtVSlAAGbU`yeb)_^|LUr{oj&H>Cc}lJ<#L8Pm_{{46X zSC-5DbvzIJu<%*TXVaM{SD0I#!q5xjK~yTeDSaF#(gA8pu#0plPbLLU|Nw^nXUlWErZ`ARvcHG;g{mOpXf8Y}|EKA+h=m)%0uQZDQfK4OJ}Lw` zaf}50lKIe&_BJom_f!v)8ck52*8)H2IFv+O%E5j(vuRQ;Q4;`f`q zqmRVV_oMKND8~!d3E=aM=~TSmVgt}dY4dU6z6GxC6<)}~+acb5Rj5EHwas`@>t=4? zapKh0ILBWXWs^ZWenIRNhwS)ABhr}28(jy*M{kBkUWzL4l3aB|{WUtH`X^_g9 z*LSZti}E;qH?D_6b9W?5$H5Dwp-FN`2T-r6rZf1%I<7CLm5ib==ux(JUyZ zz+#idsINRL2J$3aDW^2u4>93qk~c~qFBOCU&-v~FInxZ7wND(_Fr9=uL|Std&!|6* zsGDZ_Tas;+;GPf3boQ>OJgDus5VFbx#e!Z=+-2J|tG6>^wwCq|`_oSrD%BHl+T~84 zmvq)hzrz_NHWFxpT)m)6@eYd5-q@0_*28t#U2%DT3kh^(;Y`^!{F=Q^5uNr7{^RV> zI=Lf5#h*QTCR$JoF;gMbs$eD{MRjRt%j-m_rqa;{u`}AjUj8@WSW+&k9=*U4dZaUq z`G_*kf~^55G`SXwu3JQG)`;^EBECuqhV69u`9i3@8gSXep$mlh#AG86er`-?E@iQk z`BuBP&UAh$$rpE^1EqITK8aaLt&I!?zLhFSxb2v8r zk~IwMXv9Xv5u2qI_H%S4T!)SM2+d;N5+-)JHjGfhRr~7b?m&< z1H62T08WAxOJO?|aw?7puOHSF6(c$WEENQ_APB?4wVb!YNSL0asc{}n_x*MlXMzRZ zpB2P99L3Qa_`GwKHVP=hY_yGVoLGucs7&Oef~!kLl;>Ovs%Rw&`;CT*u0PgfoYWOh zS=UwelV!k8e}tY(J|cO+6x(8{&L9$D%e&|-g$z&lLO)lkVo}-FgRDJFl<0j{e;8IC z4UmLulSbo0=!akPo_ffRuB)Sshb|pbrH`xCph7ue;WZQ}V&3kLRuj%lJkSEt?nwuI zYf6joKXao_!!n6Dudux=usMmBR6Aq{qwCmOI~NjQpYW1>|KKeYR_WL|odpMSln_4w zOA3m2f;G`&z>~0XdaXwHTC*+1uHVwg%k$;g3XbRH5e=rzF`AM88P+MFhWqSU1ZZbC zoY1_yX29q+dLv7YcaDYN^aq=x_qUL}9!ra8)nB&ChX$bED4WIaiF!ozE}d2OPLCG; z%|W7ygPj1%YUHYAs$5)sbCOUurm7|n`J>_6QHQrxQ%Jm1CjD71(_DH=Hf?XJ=-ps=-boaT zrLUR4Mk+`fxfhv*Kq3{;zL4(gKz@f_>4p%8XbSQKl~m~bX|NLSkL6d1F8peIp67~4 zU9M(u0?`AHy20d{5Om`N{SG6qXVMcEb?16q3xnz*b2wKDMyD+~4aZ>;(2h zaew48QlD2sfr~<`vJ@}m>^BdkqZ84rqGFZ!(h^bo?7)8q${NbQ7{)Y%#4Lw8rB2X+#5Y=HoZ^gaT+R0rt;ee(YFMN-PI5F zXD+5f4D8M@QDEzkc_a2;ILg2*2qt38#$G+$|IHm_*k9n4ksezcwmmHJnLOd#xq;3% zXCp6vi2H>gvo*=W&R~yGq$)fXYhnHz9UGl6qMz&e9A_3}SVq5#XKKZF-GIB;Ylg!m zsz+Q8zKpC9tjuIjO6g6vs#9BB6TPT5!f{qUw*>nex}U~;NMDzUBc7IIdGC&=t96P! zKEo8D)FSZ0+BrB!L$L#XdM;RymTZ27xAC~fEaIJ57s*uB$_j~I`Z<)hl&M2J)03cc zY&IlNq&d=4$3;1?L5!;OxyUq~F`ggOq@nlPI$&#-w%>F5aq+0@ckm(i*xcM?KS ztYYcJ8Fv$fPZcxQh&RBl_I;m(*KWx)O6U`ZON>f9rMOPsJnFCAUrL=9bgCbGxkd8< zza;Ww45)d4ZEgeo-=GPl@W`(;!6I!0S{3EsdC^l9G+n(_iqYi04*w3a?|w{0??x@# zx^f2jq)S{%K_Xf;0l5n2RArEPP2Qy0oXSyVt9uBE3!8G|v){C5y&PC~2XxVb7Efrg+?xS3ep-JX&k|ytU5s3Zh5p)$5%0dZF*go~R_zU}_?W&<5 z(Jsj20zab_f)R1uy?MgYF8VUNsIQ+Ug72IC?jGSwJ=MLo1^^nTj3+WZ66rLumfh(O zhA_Aod1qWiQTTdFrAoK?(`QQ8qQIn?kzp-dZe}xoGo@xAv@4AJ3zL|>hi(U+K<^AG zUw9wBAh`Wfw z6rcW0@O$IV^V$NNvqz$>bd0h((U0?85ruvPi<@oc%uX%LlkhFA#Zk z*cn{?S!&ed>ZigVSGq0ShwKe=v1M@z!O!$$kTop4KRo;B0Kbe%e|zP_iIv*(NvD<1j&17M4wv>y#epu*4;Ok zpH(1&a18x~aoaRCf#Kdf;_ex4fU)ZjAecM}@(URsg<+{4spJ~9S;_%NQqycZwixYD z$B)@-p`y_wF6X(fp(vyGupOG)Qa>w3A2sH}iNFfAI%Xa@A4#Ioayh<0*}XkZxc9%< z6v@&qV=iEJhYC~{Ai6guZzc$Dqe6}Fu7-G#ID94VKs;lAx0rqMQLvaaq6e;?R#RKUpY zK%wjfr?~r=uU%~haTor!Dlj4CP{!mQAI4xYS2oRptwm(bY_<3tI;;#xDJD6qyGrDl zPL543Xznh0D)@fJk-qlE?;57#xhcg!-L|h5fhmWUnK@oru{4-oS8kuJv@a9Lnbn>nF6jm>tXJNV#-rzr;Z_Z94*$^tr4xNPcfU_A6 z(q^iBz*43d3Fi@*5e+l63Cf&@_sG^YSdJ!3G!{!7+yV zs-QHJXRFD$TS`--@yru0W1e_G_%>tb$}l|qeHg2neHI0}cbeR6%&;Bxgmpc1UX}<4 zn$hWb9fIGF6~@L~AB0vrv8~LTcgcGU-!Yt%HJ#q<$KCzW;0&~nuzDCUP_O;G;J8G9e}Md;CM&AGen!2l z2wx_sEaKonP34uiwFbWtV+laxh>XdKzC3zqIat@*BKC>3j9Qkp|Jk-4RGI-tOkh+P zJYDSGH%3gf=6n}tJ@J-1S9L-5 zN>6-tbgtmhU|pQU%Fd*p0p?~Y#vH*Z@}$!nRNUYVVv}2a%yc^CH*gg1mp&MxwX4`m z$5x`41ep0;8CQn=@K4)ywb;&#M08?uXNq@o3p>}@@2eQQW&CqTQ51+~Df9ZNkbyhU z_Ddn+Eg%Z`Z`6bgB)5~QBuC?|?hK+UYb;V%B~ah`QEpKn_kO#u${!F+DG(`Z3$)FN zr(Q76AmHR(B$(~`GBs?6&p9Wh;8obPND4XPTzvl~YCuDy8j^!k&bE!^Ji6w){ z>>ycv8Zpj&F(k>f?1Uc+#~4r!cbR$&&BU zrKoT)#@7*f?Fz~!9BqeFHozPa{9u9LI%62#z#YDy;)-$qfsqP*L_C#2B%ghD`DcdX zQQ1*KLpY`j<}O!r8>zC3r^*Gr-iU3|iRI;4gs#16=6UkRkneDvyB^tnzPQoHwe5UL zjRtK6pQyPXJvA`dN}Q@3l7tlXfwXpyl5<;`06FP#;{XA?S_|!j#29Wu#3YW>5gFL` zJv2CHHN6eqC#-X0{H`lJ+ZR578`I$8pSHTBF_8P6B|v7FW$Q1vluDsnS5;`zv&&}R zCeVV(y@OxQSPvY{etg-=%`Uf{)gAE(x|eNmA;=l%=k+NvWlNL?=d)3RmP(y$#v9$K znIh6hM8lA)nNF#X!eb|vLCy8!C0q_zoy63X>cT|Fq`jwJcxJE*sy(kpoYtp!*sT#o zB6qJE_yRU5@x;n6bX>WJ!f-)US+G}Tv?oow^IoMEk%Sk_%yu$Ruk=4tsHcQn=rDU1 zem0zGczobqKWDNIW|3$rhe$y;Zl@c8WMWSpLU{Y&A^o1e64Y)(cy@$)9J$@)UrcKT z#p}L6??^75;%1zmvEFj;a&@2;k_p6_j$%iSJ4I)j`{hDUY4_2_kzRf}qgagJq^~zk zba_mBjsc~-qJm;=H@ty^?jthe+Cy4;V4JiK`=`!alVuM><3N+;v7J501WhT-&f4jP3xEgg^{x4=09bNq>x}G?O zSLl&=&mRN`Nf{BQcxhhO>M{HZa=LywhD$=?rE1^dvYS^UN3$Qklf0nqb6VV7M?JZx zeCtf{`sxiprSmKBS%9^3dlch|W(YSa%?OSs^Y-7wue-Fz6N-`!c}XMk-BgK$pis2% z@~>@|qy-Y*HlJv>vk(OV$QA8xBJ&SCwwwTFmR{TbANvpT2BA%MEWBI z8eKFAwa_MF#xgCs1?z7ROT{Os--}w8iL7gE9B`JI4lPSU`WPC1Jrt-=k*;q;a9B6! z$N`@dL`O89>=dcvqGEF$^RBVht*Nz*Bmc5R5}Cmd>N1xV$1fgh&0tiSjuwQN-tWi5 zC#4>oJh6Ye7Oabcx`{@iwr4{_qGM1P7`ak|2Yv_p(fK(f8?$1>5KL+G>aX z`)lHl+LA0iFJ5I;rQmE$a~q=_ddBpO%ttLHzaajDNQl8kyr8+adg*tO>8<>-?osyjzMQq)pI1Yp2~eNUf+T%yatHN2ZI zI?4+?6hfqrN#4#?pmKhI1f|gDa?8BFzfq-G5X8-o6TQEt_`t+$navhX($rEWAh)ge zPcRSO!Z*%w*2Jl4PStpPE@t2aPuxzsAe1emNY+0|yOnibs$(MS2fZKh5?lQky93sU z9r90YYEV_Gf~z32$X?m~P^ckWn0#5)Sz5P2=X^0Cls}#VCcn)o9FLsS2<&BAiD%`L zSpdzb`Sf@cM+G^Ffp#hqz}&4y;qXk!EiJ6x&EV28U-??j61fB+O$qw9Zk84BQZO7O zy2fR4Cuya1?p#|0HwgSELHgK{TV!_8_7<^@0Le9}MR6x2iuI}VgS%#GecBnZr)HLj zH@8mX)CZ#-GFmt(ug+F<{gCCV)onB8lAC?3?Yr$G1M|8EF2=21Z8hO#i%}ZBTx_u) zV&BLB$*)$*#0om)wk*68hMVZdm<=$XUj9$ z;RpCx&ak*B@+lvGK6kCr&u~!(Z=_YJZaU+9u8i>J2X4TjJgmWg zF0b8Oa2yUEphsrxxNTTxt*h^<<&258DYRZ^_feJb+#28rk;c{}wmEESmHzh?LE>JH4p) z9sAjI@E~y$>ZHDZ2uv@b%q`X#>i#ibe3%mbw-{cAfa^+Mc%S;kQ-S?WRmoB%rs&QO zPO69feFhz71~C<4P*#~P26kfZo^|3@^x$N3Yfv5U!PL)_0Cp-w?))bP(Z&8VZNjmb zO}~Qmlgp{~zVd1j58Kr&%Eq(3)`)djKP=vun^|pC(tHQ*^hjCzUvVKtb94oWhtN}E ztUq8Aj-1m+69$cB2BDF~-1%CAA!Qi(WOTE?&^B=4^c+0oN%U+Gg_*QlR%!2Wi?bhj zlyqP&n!^LP)xC@4$#+~qn81Z;q0O=E_kLqsEVJbYV>b(cf;4Du>c3T3zATq0JhsWQ z=itexyJrQxkaZh&l3gR8fb5M)X!rMx*OuE=8NnrA5j5G;N-Ao-U_2#qv6&z~k)|M7 ze;GRJ>``#rmGLBgFNUI+H2Ts&jevCbLI{amXSXUTjjLxl`po14#`1Ij?O-v&h-vWf zNn=_myIMa4{@mYNG0eD332zbBjD`(W`p)N^>rVK61bKBc_{LGp(NH#>DC^!n-;hC8JOb6YBWmYiT`fsE*M#&h1?(GR*pc+GqEgyB@~oQn;d3RJhQ@6 zktA-i9o8qgHUNfw)izi3MPs~DH-)v04<7T(cykFaDH3+O%JmAu0IVuzo|M zoZbi8HT9m}Px#e?Q3#}oGAVCVQSZt8r>&T^pg@&}?V>^()qqLZH^qbet+D!KfxrOK zW1@sEtqXO%tAYWfCGv#(x~;RR6C!V~a(HNdh-imqV-&>LKD~m6`*WDPM;^62HepZz z3mC#)vH%}xXU#24?1g;tGr^X_%Zs7NUk%Ei(n}%K#VXj;=03=PlaLfEZO*@WyV_;^ zydsN7Z)}9jcux8KSTIL2P}0j*dH5>fPT!Ly(fX4o_cp55ssaaKT~{V zKc_8)ev{F_K+&shm0{=jc3)Y($kEiX#i|(Ps5?}1EpUwR*cJ7^5vEEW)>&X{A43B~ z%&(Qhn_wEl(K!l|wQFS}Gbz$9LhXn3Q~4WS`hqt0i!Vz~=5lH(m@Vww`+QwiF$OBB zk4T;SPZ`)AcB4gVBSFq8w0~&~2T8V0krK0mfEWKJ`@yNN1XynOjRtjbA+s!%^--8n zz+pis7sACN!1o~kq2k1Q&+SXF>o4Hr`Rms^(UE3L-8~6d#de=&oj)>H4)2+C>ro9; zT1KuKyBxa4)e;lxON(E>?w`50qSJ&I#kP)K&<#*yE5I(LZ&SK4xt776igNi|^MDT9 z*O?k7O5&A~m~w%cu33HL%9VR&2nG%}+p~f+I{ZTN8w>vz$>Tok|P`2^D3YgwapjtwAsmOR2%{mRl- zBh=?}gC_~bE_jprPT%mj;ThmLL}%xcR@0dY-`fL6HfO9};l^0(^nqk5kqujR&1dz~ z8ictZ5BJmNNGgAYoYi~cVA*oRzw9X93z=~*fmn-EjrdEF@t&I@0rAYZ-5Qp=0+gET@=|>F z=4^`j#2@0a-5^Vwe1pkGTk+^KbA586agzjhw3^v;RJnl9%}c5<%rm_R+$;?i?-#vG zCTRCg*B6~^f&T{YRDlZi*CL=nUvCNr@^EHP!E093Qgw%sZXmkqz`8OuUlLBE;I(<$ zn)uSKT0H%}Icw@|(<)3AHN?S zy+G3~+?Z>E7M}kVQrUz2O0ytFs*L7!!&oGeAY{fTIf2zDe+5a>6<}SyO~?&Hy$y|@ zGOk_0!lMd474cRyX)F3 zzw(ugwj|H8#fO7F2coWeK7qTCcj9%s?0p<6i+4pY)76Yd&RU>*l@NvAx<|;Alk6mP3R_p9aB~uCnxO{LiqnI#b zu|zt1iB{&S1Ajn%tNUI{z=*~i^!=EWfM1;nsTA-W3PqqeO9@E6BOPnhAMApq9##k!#e#&TEi z7_S~siD*;LI4HjgS0*w2u8(fesUMdOc$0_eiS%?*$nABT45KFb#r%=oq!Ow?1 zbLvUl(-4h^bq{s_5v_@i=Mi^&JfM2(2TO%&45rtab9(9{8tLbBvqojSDS7^T*0a$* zem`0fs!J|4FtYG8OyiE>ykal?mQ?&7j*%xsG9s}qgkMKpA{EB!%`1KvSdTaWkTQ{~ z$qnlX3f_YWQsGH9hAzLYy}4GkQKN$aCz8VMKu2`3}dQ9rb2dJZax2?(5Sg20QIlKseF&GaGqxt2O~4Lz`e zsb))lzvm2LgTWzLZp*rh_LNTpxb^vy3VaB3Jm1@pGBK3DAI@#Fd4mJ|tD@r0?#?7{ ze^?N-{&GyaZ^zkH(yf6Z{i%y1_XTw`nJJp$0~Tyo!sxJu)_;L~)^)BL*Q>6jSJkg& zB{SWMOyc3q-)@g@Z?9MC!7&K-Yr9J;9Pw#Vp8GiQoq)xkE2mAeBUTMK-N#6@sf_5i zx+00<7M97&n$DyzNhK9KPI~u}p}Z+SWfGRjvh4^s;i_`Ddx$KS7lrQ>3bMmEtbIWt zt>!&GG0S>h!G4#u5bGP+63lo1IG;MPzD7$eV{k8jqK4#)-AhHtA|KCA@U7B3S6PZ) zg)nhvT^RjHyzyql+%QJnw}wrROMX}^S}fv*dxX_o9sP|mz6HG6R?}>}2t&d#Yi^70 zL*Kx8z=Di1s+(XL8r4SD=H5CCL_StRtIj=! z5bLNaGFg|>MkT+2LgIAf#9yT)|NWswSAnv4F0?liqO`_4nCB&TKx0*ug05=>jPQ<& zARqlKZf2*f+4k2BAcwar#P6pabU)?Gd#{9(H!U6qa47*|HWQ^9tz#ENHdXy-!E3>{}1k+##Y$ zrP1kW4WE9AybZCT5c7=M$UL_2NDk?F^CPIVVs8@i!PPX#pE}tLF=c)15+0ql8Q{|X z+=3~YH$7UjFOc{^W*~DFO4nHyX_%DnwT)d=6mFGw z2OEbQF!{Mg0H7bUb;I@?@i?;clRH|ntUgDK5>{aNPDq1$Xu$otCNOZ(5QUg^HFby{ zcDWwp=)5Wdupd9gyc<5M@S3mjlYe?@d|VzCTf}-7A}`~Edd|3#o;HmU`VFMPpK#d7 zMgCxV8Kt^+87PE`l^mLWGx>%4<`fe4rt}=`;fOheOgig?pLcnIY^f1A@|Tp{w{u8= zgiaL|5YQePh)4Wc`dpxL&fDa9z4XdvNchRiA=iAU#Ew9Q*0;8o-H_IybDX!J9DuxM zYCPR(+9dtS9!WF!P$+?G6Q`)gHZr5|*}khl<6=nHR5|Y zgpH=f%OYXVst8Hd+7*v9Nfo&nAeu@SdaH(1U+GLd2rN9wu_JO)49DH_xpmrya|S_r z1p}Y6d;Myw>Agm@cyDBc8?~#Cly7b0*d;1z?RV3UFmsuENG&ny#Jq+cu|^|>MdWxh zW?N=7P&@6;`h>!cJt>8N{#1#CDBwtQw2U;g79;fN*#R4_`G>S%oe;egAcc`LQ2$tJ z=R`NbQ4eK%XUZRe!^{)v!%NegcnBxv-gB=n4hrZ!>MHr5E}#y6fHlwN_YsFNppm{- z)`OHwHoz;|sGMkI?0lWiV`&E6SJWSFze^yT`{-EHeY6UBGz&V?-mhv!Bgv8vo5tL3S{U~;0akpaTe^Y z!WW(0HhOBZR|27n#}1;YhVXb`WJ%{_q+A06+RDz@San9lXVAW&Q6;FV=slaQ<(l zm%OC9nuO+mQ+m-U+Zfup=rgjh|Nq>4(Q(26lwC}1)d>H`=t~$N0uTd;f9GB@09k+> z;2*JXeRX9Qf8Fi-_o?IhG2icFKc`WB zTD7@qxkmN7(=rl8_agePb`m;bTS<7CK~WI}wx=d%Cj{3J&&-W&iS<7l&cGovbt1Epp)L9o)% zZS~Xo+X7>CeW1SHxG*p`LMZs~a0JuZ+SCdx#}S}?8H=MMLH)6S0l~`F3<4sCiP|YS zAOliCxw8U-PGBAXEQS)L5SC^p6j+9XYH|Zo1dXx108abT019AR7BlltJsP+fBs&0N z0OD8;3NRzEBUC3Ge*#1x7{E5QGdVlFctB)u0?Ay!*WmHb49r0on8CNWFul3@F|FcGJls%B;!lB^%`M>0g0L4WmDjW_yyv3+0@*>;NZm2%=W4d;R58H5EBi1BoB#FOZ`>(dJb|=PxSJ_j0>;2Nf=1b?n%y5? zXP8vh#yCLC3;h2qn}%})pZp1smh^drKN3R%|E+9-GJ*R|X}|x1j3V&JubjE-FMsd_ z9{HsX_Nkxv{3XBXzjD&Av-h?0_x*ZtPcAL(4nmCp{wAIi^aYCrVmTmQ6Ep$*oz;dG z{sPz^9+&yg*P)exsoCk%4(HcjJNQ}trccBf|L`wlq4D(tVInUxH;5L<$%V(!?E2DTlHo(kTvZr&0s!}&%ZwWIT;zB@XD;LpjsMVr4WDl2@_i9`d4lW zH+Ik&qJB|HSw}8>vM)ScPe&2x?pBidg$o!3+gXB@_qlZ6GYsTSsjoqIRrVm*}&KrzyFuk=_gKX2J7tTNj;yEBTEC@ zn?>&z%R4w|?!_fP+Lt%BkILuo$DMQ_Feh-}-Si{dfS$l3s?*B2rB%&f~=2g z&jRcfO8k~dso02FuNLBI`&4X2SAbEuh9(ePrOO^=u8xD*%ZPnS z0t|u*(plu>`ERY}DgVS*!!G9PZEK^E2Mx1oS+=$yn9J^Lbd8Xb$~%ftFSnpltKWt{&t-0 zBstfhhfE61a}uuFZ>Y(q1D%-LG;YpAki3$+2u-C?jrs8!Z>8px3G-_zow#mO-%6H~ ztd}B%k!#L*w!HV@t#opbH=O>*b#?|0jk73xefN{-GM9rCQ#xl^5H$y1?ufZxDYB28 zO4k~1$YMlPPX+B}h;T0G$*@<1s{Gb?TG<_DAAk0$FA{1&j}4bq7J`13`q6*PTb%YNXCBT)akbgcg1WKEgL-m0Bx@uk0NYU~8L2C}kB1u=pwe_?HGS@{cHyCCs%2Z%5z9<^Qq!V+ke?Gnn zFwtTYVKwjWsQ82vm+r^-vd{;QXEU=)?fmvx`5-u``}eI-=7QxL7h~6~G_s{;iMjQy zE!qQr37OX>6^uVWo7BW)%Z^>JR_nHsFOuBxKFqXs2iPbhZkyumNE?p0fytRAW#UAA zVbaNnV0!<0=`H8};X#8FzFHyqRuFdwH0%_xT;42RX$tE4>$EdQ27*zV^C;R(#H2j|$ccFGJM$m!`|6;es|1yBc`Z_vzI1B6h1Div1wEmN9F~`RwF%Cxizz z)=xEqlhd@47-CHXQ7)Gi4=iiejaH^ug)o5Q)F-74rO8@MX>XOSs; z{FX6r_`aoLKAr|DM8nJAbFnAdm`oJmu2H%MvK(AQ%`%PK%ZaL)H~%?j#HN_WZE~!Y zfezu7c@68iVW<0qRY|3=8K*Y3Gy#VIFO>p zVn;maBi=kwU(q6dP08*VOrr9}`n8EEMb4Mn%(Jk?>{HJ>!f5cN1;mR-J;ICO8iSP7 z{{tFJWjvk!zQ`HxAVT&0tZhfh7t&iB&z)YGaYTgXt)O0|IT$bUiYW;0u0^(X_qy=G{)0_PJnMKM0yV4d%~gXhD9pEfpH=Y&A`_>)5v)bv z3XS=_B})gJRO4%DjFm3$C$q&peG>7bw{(UAE%GPs>;y!1_>EnRhb2w7TrC^DPisK< zX2G%sPc>c&D%Y$WjkJa-!s8DCj|O0ZS~;RKnm+*YJTi4X`5a#g0^pc*_v=X()~$Ah zuLaP>bGQkHHD)un?4vSEOCSqcN|2i09QyebvvBWhjtF~iX!_LHIX@GP3)>XYDa*9)+|DR^5MunOYwWopJ=ij`?ebr|!Huqt$mLN2BU+0GtP?2Sc05c45vFE!GYRO2Y9QHvCn3fF}E zlf;qCO%HB=XF>KBrKAFH8(r`NIt^T6wAFH}8xMb=In|>NEq${edy~MhW_0@8*JZ6z z+Q909a+Nn5{s#?LvaQHnS|Xzo^jyn5f@!=#9Gh>h)9DS$&z2(!VBN1k!VX3VVbAdy z*efQy2y1RaJIAXHdC|FuyE|(uk*Y+z%4b%7qal5#XMSyE3ew6d$-{ie;&nsGNwrwG zjtu2OIz{@S3{`ZlSA_l_gSD93%936=bD5L3r`@nKo`dsjpyi`2n!h}idCcz!PJ@SV zl=2-A=`$3#J<&DZNntVAWWle=A+rF$-QQ~q;3P-dR>P#<*`=W}_Rl*gV^94r*1iO+ zrtWK;gcMPkNmojf>dyC8rb?3{no(%D&66e~MTTb4C{m<>GK3;YX_5$K3dxv68kD*4 z?Q_n(b?(`h-|zc>|Mz*H$8DW`)?U+IYwfl7KD+H^V=~2IPNMwtadBorLLLgQDR&lZ zJ(^fNK6-4F!OAPA-%J$q`>qE*a9AtYwRIkB|IPU#9)%fvxx5b$LGxrg?{~*}gmd>hH5l-&%fEU$`jhFM-7;>koep^v^_}`m{{k5w{>#LCQ8GukMtXS|7_kS+p_d`6Iar zQXL*8$u*)E5|mO@)iO6eq&MF<9)I;qA1f=_J8Cvvf%8l`-ZJ!}7x&Y@_eX(f1D>qkl20b?dDoiS5ohVm8~8tWQmRbxLu) zlGaq?UBNoJ3g;7)%=&gmWw(?Soqbn#Y`Uw_0pSRlv=`fBk4;H*F;RFDymp+?xlva8 zmaZ~rWL^37L1*sl^_jmfJNU`7ir02MX+`-hpUj*!t~o+GWtEW8WRK4gV*S8fF9wTPTZ3?Y&5AM<|h>5YTlTGr} zEKAsbDntLqgMm--bBl^DFk{3!x1Zv^1+#=!+76bCcXBTrxSIRJK{tU#K3tj*NP1?UleFxs*XFKq+A{W{ zF5$MLdOwt}n{ISqLRy6G$k*1(&Uw@vU!G+yw|0wrn97l>vp!VPl(ZJBE;;TZ|A!Nx zGcz+~gHM=Y(3PK_56;WgOdi4XFJD&h+&Z7!H1po#Ej@viKf9)yr*}Mll5)*-eo|zn zgtw=;)KqfM`GVZTBf=todda?B8By&c8)Nj|^k~VqEW1dly^gAjek=-@DxNmMI#*<- zLh-ZK(TrF2M_1IJ&&lo@8C}q^+;aA%>w)*jKgtR`BknMH>ieGc!B;NNnr4R;qI9{aJIax0zf&VJ8+e zbJFG*iPj@6g|C-WlS49N#X>XNibyuw-zhPDPsV$0m53Psb3~$N@O7o)9^s?f*H_sV z%^sNXy}DD%B%P686`#iRY$+3JC_mvtwL1E>p2Al0q z2l|4U`lGborOQyx9@;(jadh;mbv_EMSr^COf49Z|4t@5ME!oip&xI~a8jGat8DSXK zH7)C>Hs{JgiO*Y<7y26nkct;RdRn_+(@Oo%)uaIW`EMb4lX81(o=TSLEZLc2bK$-8 zEwd)w{LkG+PrVHnzRd5ZI10VC%5W;scU^fSFRVFSYW-+Z<_1;D$pg!Gts9|J@$L8fsJ&`S(#_^2dRnCy zB<%NXC@wntBh06rGB4~1=g1NpZ?DLKBW6b>Y$T*y3)(KnIqa*F-m0c6CcWYQBV)~Y zmD3k8cNEy)4%sp>an5w*P`{-1l?&-ICmok3?z}z!XlUp6?<8%BXVawpB7^ECMfkW_ zzMiXEo}=B_KK|}X(ZrwIb~c7jwBA(j67=?NiB$H+2&=EMBX62Z-+KGxrDo;YU5f2H zN^4|nd;F;5M_IPL)4X)~x%|mnMy3@xm-cLtviK2tY_Ml$+uHS;rC(`CcHE$EQG0yj zu%6BGx0EM)Hr4rdK2-f6r2aWF{O%%uTl&JhP44Ba^nHVe=YgeCxx@9TUUz2Rt)ZZ;OznHI^EbHEz4jN;G50bY zC$cE5wQ=uQjV+tfyL8_#o@@2(?Dr3gnMJ||KIH6ngMGmXS`U}C7~B$JUl{q^;7Phs z#oY%l%!P7$f|Ctq`^!`2{rb?SUc}m+a&Mmg_VUVn{cnp3Zb+S1^kZ~+`o3(Du~F_0 zyWRhWp*Qu7&4mRwyjG-6Vl~x{H2EQK$cWw`x$n^Jgqmkfc85nx4@}9EuF+GE&3SwA zSzd_Vl}psk=i3`A$(=QqDEIQbKPaeN@Y}KC%cLr^2fD$`$**ePojCr%d5e3V$ zYjfpyXJ9IGLy8XP^A%pwR zBPUD0xpCU?Qjz4sz|z=_@3hqm8~2y&iRx@lUh?{0*L7267h~ZK@g1p;r!A`55O966 zcYoZb=-jE6?z0b%vC29fRiHewl;e7$ucG+enX|#=U)mJ{f0vI*j!UKf@F;H_d%oz% z%~J`cIi1~`%9|uiN5`(plNHzdIZASU`Q#n73sYx~da}x-v~W&mSd_>WX4~P{?$ZX{ zpZSX@|MuHhT~w)RqI@KJ{j{IEcJVO@fQ}>UTr>OXXs<9uuty8O8b1q?g_uncxi7aE^$Bj+vA6v zTaEB+6;th1@;8smJc>X6t#hy3m1U1Luhx&-9niF`_x-~&Q^uFO?tiq-W4GP-wWAXZ zRicl|Q}XVp+^K)KUGdYo5#BC)M~>Ow!04FtpgU~6{4I~L$E2&B_rh~c?@+&Hm1Nyn zZ5PlkHf68>nO9ymMG;Xhl;w)+KhL{u{-l!nYQMRBWPD$=FR9^e-G#5;m+A#ROt2C0 z-QXAZFvIRertzo<$?>4~%ZOpNV#x|cIj^dr>sPk`{#a}MH zzwGlsd&7ck1DU-B3m>mJ{WaG=YamaUc2?=D>z7y`^O;hSx=B@QP8?`4Q*NB6L~_y^ zIrqRLRn{9e`TDP%s7A7iz?ZhlCqt=_Ne=A{o`ExJ8;q4ve% z^rt7~C#3{~6nv_K#kYd>U%&6!_sY?sQZ;Yx=q_IdTTdtRQ=j#$dkK{(JDvrp1UqO& zmMsLIAqpw-oN9hTD#y(IVOOY@`NbVOSY!p!c-eO+0&gU@+}%^HdAD|T-Mc;CYez)w z3;!tP^S(i>XzJp@z$CM`C1Q_Wyk_2dFlS%+%@+|5@9QmmJ*tEnG|IDTaixr7!8fHU zW>tQ9yvvYh=hv&NWzCmnv^{#ZhLcjg#I1MmocMmF zqABXHpM@n$tsIpe-)1oXbp+|sm9GI^T^_GVlXGXBei1~?_B=_SzR zann_PCAD|OYTs1J`CeKI6N4wmo7EYS7 zYVIcE#vQ)KlMT+^KTztCq1d5uH1YlVo>S%7)cl;pU7xZU8&95Jw}v@)da{e=&t=LS zusbwgh zRxNt6DMF&&^y65AL(X>hNJq>kLm332kLy^c?1=N?v{d$Fc1QblWw z&#$WkTT*vR8-GgMxWzKFr(E&$%pd9>bq1cb<=wejHvQg<2dxqy9jwgTUlKg0Te$s$ z<+E*fA9pqS3s-bnq;aO4Q;+svx2|rdQrxOnUXD*Ro@dCEWq!Ch!>xbP9(va0w7`=- ze^%MMnpu+nWZY<)^UP=Ii}SN7xhk`C=S2AcgBPOX zPFC&gF3@^(dT@ir*A35VvNGfqUw#@i9ms!iGk&>BU$b~oQLdtrWK4W_@dkrm(@dS$ zR<^XBKfaW-dqsM_AIYb=*06Q6tGNhU^VlWwJ-cvu`|uHAXXa%4Zhijg#mzUIJF6P@ z3ni|<@JR7%OYSkZxf@Pu%lpPI<>a#AsH8>!@Lub;l^>6f!q+F{kW$GOo2tB&Ecgf!3MM^TDL@EK8uS7#YBws zpd8cwA{0AEHYuyx??*#*lBHB^V28BS&-Ly7lh2e6x`Z%8*FBuRqCGDya%b5_>Whn} zkDqA@m)?Zb8~jZ;a{C4w=9ssHl{+lCv9!k~CfUok?put^nuCqo_jrnxE#99tXN{cf zR_S%MW5Vu=U%#+RQOc$D+=?QJ?1j;03uQQtjG%k(8p7=7e2Ono{`Pi5i?>6?y0Kar z-@mw8>2uaj)7rIK*D>=*MbRuu)8#*lOeT#p+VtDduhdoUa%SY86NNfCW*Hjt9+w@{ zJ3a;9aL%Nzs4f|4wA^>p9m7D$*4JLQ3*=r|es~z(uJY)Ce82|P`kjlm4L&Hi?fB`} z?1Ph%HvTM;&yjtS?QwkDr{ud0OqH~T6`E6wR1&iiE;JXAN)DZ|em~c8d7}UL$yvK& z4BJ)ySnIR?N;>aPH~6&cPa$y_};{ zNwxhACZTsy9p2oH&po(yw!Tl~3k&&`QjSJpp!KY4+A*k$T8dieOh*Xq6GXA)a>ok_Xtvce*t86Pd>GN-$I zMTKo0^~KDilSSsNJti~uY;cF1^42LX@moht87nXRxjMDYmYwwKkz|crr`DMAK-B{v2ug)-~a2UF|g=<3yh+^JH#~HMkcx7?<2ReXsE$ll zHs5t3CU}~*1Sg@)-PpXaTUF4*S~pO&GYI?p2Arm9o9Ul z^T5^B<2{|Pf}{Lhh11`j{5&D0o1<|e&CkldVfpOklEXfW<=P#{MAio$l0W!BX2)gc zy~bs}k($qKwK!GOKi@rLOoL6gcDai;&D>pY7&@mWwQ0f^N;|TY-%Oo=?1F)x>5=Edl4^ znqPR^3GGYvSvb%A;;O^uq2`C?`R=uAzCbn&dK~<+>Zixtl6{>6GS1{O%URoWpj-!?rZQnQzQdHIRWbr#)L2Brsoex7nTIqm51RezXp&AMv(WA^>4MiPp3!j&WHjC2%k z-5AgiQaa&Y79_THoy=eaYwrT{7k2e+yHa94Znq+v`|q7Mrq)!ci{>+abd5?I&SJmGW4Oz;7C zN~hU2z4K)K82zi|ebcpzCZ~0XJFCr1(kY!Pd&PYFpX{(%fe(}-#+aOP@7eK6Zw5!% zl_O;xrM}iDX7Xe|}b`^hTqN zlM)y)FBVKYoN4hX@`KAj%I|2(?px)%EgVYopIQ|SB#geGt~J>>c(%2o)iZ6s<_O8{ zxdX4eCuhDct-*3z3p0N1(+k1(f-#YOFbJe;A3)I&gd*N-`C|dpP;PujW<|ixR zL)oJq6dM^Aw2L|Cyjd{aOk1bxm(^FzAI@o)V>=|s(w1qj&Q5$S|LIyVd;EbWhfhD- zv;C}o21(aSoYgwDqD@w9-{Ea-BPUA~xxRmYfAnqYQ;+Hs##guK55`J==p?nt?;E@` zP^j_r*%YZ0tICR%E}n>Sknl2GpqE_pYawhFq6CA7aTkpGW zGFsf3rd>0)-(<_L-3$IqUs^?pxRifO^!&$Qv9kFlpJ(n*Dhh2p-kt2TXJY6Q2MnpQ=iI@Ea5k^~y@FOVW!CnvNo%g< zg!$)4`=9L6soGPtE}L^;(TNXVKDfEf3W+|RQ}z2twLMw9h*bl z-RvB+{@S>MR}E{np6JM*8c;P;CGqPv7lp8ll$Ox6i@z=E_ZMXMUGJE-GQCl_X;(wt zc;ywkH`B9cOYb>Rc5+;Rthwn%;PCoU#~2CrJ;ke&lI~N*=P$p0kGxZx zOrJ4+jA5alPr!_dAF-FfA#%d|Bj-ln)(FeZiA`;CeRlI|mSyKOwoBk*_xLkczf;TKELf~C5K*8~cv0-E`u1CS z=ls{6mN}epz38lJ&u2O6loX!~o3*n@%8SaY zpH-wpzC2yL|ZrWLI+45w*>DN_FYf}Gs#_u+s*6mVi)tH`b zPN^m*o^1Hi?x=2InmzOBhn32(-&HU;YWJ?`#0y(%SVsZ^m&xnw?;zB`R)Ah!_>$O9fRXt zN(z#rZhhWSH!8hrg$Si`L`#Ulz|#5+63(TEejCPSibcX& zot(q##Zz~mG+kJ`NIlZ*nF@`ZP~C9gGFeS$^I~z~$M1@b6#7G4mRp|uUOa)3sG_jJ zuW@HMew`w8}$n`0`yK7Pqh1&jEH zz0-Cy{VJ-p54cwm6gU5SwcCe`kc+~?zPGMVug`5-Dv)qHivF(>*w38}ieF{7`UR#y_yx*&( zBpjt{PM-PYj4~p3pdimy=hI%8uuGQS>fNPhCTJmSDg@i-av=qKqDt+tPK zI4;AQUj4MoVN~Cbg+1T)|ELqy>hG0(cVT;p%~XS>=8LcHQ~#Q}U;5t7xbx-S&$B*1 zE?EPbBC!4S{-|lJnGf>EizVP@?}0ee7j+b!&C3K zZ0)kXt^>bLWi;-Ml|I@tf)cM~IH4lgBu;)qdUm|&iOw0Z)_3Q+YU>5oFT4C|;N8N+ zOEyoMo@l0Ssveno>BH4m>X)*DIZNa%607sB1!X$<_^t00KL6Bm--81aE8>p@r!@x8 z+oqZ1BH|cwUwpdwg~ZFp@{_Er>8Czwy)Nwy(zR#)a@!m{_mbO0r_Qq6H3J_L+D@kw zmi_iT+w{h5_Pk0nzo=IF{;#@Xh96H%b8>Q-o>%(j0VjI_d5&H5(KRFF>t9>TYbmHr z={hy@ghG@TS=r`%-*MNiB_H-*bh(hi-2GK-{*_me4szF?IqYt`w0|3|uz6{P$LUow z95ko3Y-+nJ^W5dWMRdC=`^2kn$H%Vowl~=zQlCF#6(xRI%b3c2TJFyuwb2*(O&jfh zM!VRqOvs||sARp}>8dg-n+G@Mf4BJa#P#vyYm+ti3+1>*91fIo^eEBjYZKR)*m{_J z|CMUSlPB%7Zcm9CdnzeP?ubXdX27d>T5rfk(Z<-U_6Y4m!lXCiMvZ~aKN8hu9vn*^ zh%wX;X#GvOYI}BYhM3!=!(YU&blfcgd@S^~)EQ2F)EU(=VT`&}yGMLkd9G!Eb3fsLN1-{p?zT^IwPbg6 zXVd;4O_Nd_-^^0>d;%65FCETfeQCdyH!|(o)YR9X+OI`@Eb9I?`HG159!IyU-d`8Y zit(!+k+$jM)jg&bS?|Y*I8VvF`!vOC+|Iyui|>eqB~`oP1w z2{ysWi_d*Gr*_1}7*m$j^xbMSF8VmaJ!6T=+ulHT|PfDR$C_o2=8h0 zJu5$`T)g;~rMJ0!b)~t(#iI!eRgKrA1pHYQcxe4pC6n7~LATE<<;?#XJT`%@GV{Jx zBrUK%T1$3!l%2MQ<;6EA?7Y|e@47DgS$WSg&fBypBaPdlL+Yw5k2hrg35XJtJi`j5 zy-CXGYZ&N`RXumI*WSWh{P~fl2}b$m59$7o4031m*e$)FsdKA2NNdtQu=7X0U~#ef z_&bNsZ|rX`+aw~>a9-V_Ey8hR-Q9(f`yREJy!*k3d!v}5S{3!c-q$UD(UAxT$5bKv zqo-6_Y8w|kHkZli4&8TAF))1Mq1|f69JVXf^xTPF=i|AyLc4@VNtYe!DWD{6s1e!>2frJ?y57m~g(0Xug+Rb>^wua(uQ!dUv?ES%2!E)*8#Yb3iLSJ)_?p&&+ zn%=W))~tW1uNI9a?s*El+@DJHq(fV@+YNsQUuv6_tvUtXt=-gI`BQBN=3*Gqjc*Wg***3#Lr zk?o3$#n*+JG(4&E=ntBjEK^#!Z~gP>4jH-*EiI`g)J@^8dY2a)k2$GzI4A6*f`@JA z?Fb8zcA4x;Q&v5U_ix$Tqpy~zzWVd8{vM~?7l+2!m(x1bvi1v;eZ;Q(@zY-6*0RA} z?PzQI>lN=6CUhhy8yh@bU9xobqWqYHvo#ch#xMI*zUdn?#5M4fQX+kG@8xfaZVeOO z_3IUkBjsAWTUwyjsn$PNJ=n%$=`jP=mfxRl`<|<^=Eu#ik5_$vM!a42O6rvH7g$z*%2vOT^sKer?sj6Y zh>}ASIQ#Rlf8ArZ!UQin^>u4PI{ldL9n_h9S9YAfbmGhVT;GjF%=_iUpa%2s+Tw0QA~W8EEzoO$g{{a&f>T#rpScPV7;n%jZ3uJ>;_oz^HCVZGMP z!1r_az}ipaGe>DDwV$_L?!4f`-81hSO%JVpQZZsS?c!Fo4Xe}8k7 z|33EnpamuG%Vus?8l~ecRJT|2VYT;jmv6m;lcP8GeoDzb>ObR)SJ(8Yg?+~Q{^8?d zS)r{a`^0S0HYurmj1x~Tc&1rqz3a+ASAqQI*VGyMznX4|PnZ4i^xfM(03~> zoH@?%{MvImK<7q>xG6BOEY}?HcC^)?voMb;*QtU-Ys7_cl_AGx3wKsCEL!P zYG@Xg)ASj4N+jXI9l51Jp9&J3<|Ti8_$B9Z))z^6{}~^0BwqSo`F<|jH*I(JEQ|H6 z_2Uki?A&QQResq+(~ALKS36H$HR`v&d)M%YgR*I={wT*?HC?i6b2hy!5T*|H?06b7 z=2m{bh5ix;gB2|A2|;_;vzi?ah<`h<+uUm6fu}!jymntE9`@*QR?y9FoCUsFx0%Je zo1!im-YGm{I@{Y|I!k2YhuOymBXz!q_wVj)-*xBIg=Uo=PKE^Y!T5XKvbE%|#R{8~ zTTWiQDYv!bRLPF?_vXht9q!v*rsp+pb^no5@pj3I3H{f81#P#FvEA|GZAbgmz?+JsmU4A_SrY}RL5<-+#N2aeKjySQo8(8 zjHup-g}Fx(K7q5PE-wxqtoPb9P&785UAy;C;imL)TGJAgPY3soA*~U4F~gGl-Dje% zOs8SNjCALZ#vRwHRWH7lY+qsK@B5>tDMwPVV@%5Dj|$%_E^eOuR(Y+^-bq5ey=%@K z*4Pt%^0(psKO%F-UhF-8Hf{SllBrYk>M35zSGRCp&RuEcwKDj)#Dq3!>tN^zX^q$ zj@UcnwAf6WTe-iA&RXqVpq1aeo~f37q%C$tPEgsOeD-c-xf;qw!@VYd)*ezQVVQoH zyz}*NbJ6X2re~jp8=Xta?_1&cFd}iQw%x9acyd)-@dEvD!KPvt)Ex>Y)SbYS-z}N{IpBtPtLi$*Iieg-NUTv z+`nq1QrEkjYr$pG1(XDpjPIhlFB6TQ>%VtiN3}Y>EzTjMeADL9j#)k-#+HNr4=-L4 z`h9iFSM>n3kJh5fy|Ohft7qjEM<4n2`_TG;U*^s7b5ALLw{$9Sw93lzS~uEY=7bW% z>b~lbhg-KrCcBLsIJN%6uUrNHO|M?u2+@5LE5E&|zRqmJuZ>UI=`~8O-})CB`U^?x z8%@5Rp%A-NV$RhI^{by{{%Q@iNTkV5JoQvcYt`)scS>d|Y(8NZ%LtoWy*jb1W*Pmg z7ODJKV#E@mXD@9Yjv40=YdT+OZqFr=>ga>7ZQPumSKd`y^lizlvgB0Pl?mV9DTdsu zN$EbhxRjZ4yzk`189#I)mpY#FWf<);-&HNOCi2m-yv|}LZL#T76rUHk2bj@-zC-ddl+@~kK-xd~hYW=tDYc*19%7jNVg~~kZc8T;>Q#T}x-yxbZVTF1`iGlRG#c|s^ zrmc&6yiO{iIqKe9T7%d1pHG!-b+xbQ7za8ek_t7wdk0kSzn{Eg+0sI@!K*t*926QO zHdjn-FxhEc#=e!Z&t9$sUtSX#?DsqpxMZBWQ?c;Y(u)1YZ}qOGmuN5gacG*>-O10F zKXbjp7QP$mDtRhs!re8OHLQcPvzELu67N%)H?8DZW2WQfhnq9V(LahVYKCgoPVe5U zzsYY)t4H1ShS;;xsgnmdn&Z?nA1`cqI=l6wzkg5U+#8QZtEsA;3I3IOwxnKKKeRnV zrCQ56WwBFqzRN?)!j3oB?n+r+@JQ?3YkN>gXTv=;mvhFXX%-JA*cwji@1K$#y#1{6 zyvi|V-M$CLm*&NZDm|S?*LtumVsrSOTNC|1s<+8ib+t3sKb)NB_I_5x!J?}DQ}SGv zt880fqg$VBs(0mrw$G?v$)WO-d+lU1RG+*1%cebUeLH#XuAZtEYjKCx_@2(#Hw7^x#?>}vl*|~^a9uuaiE3@E?ZwC$g`H6~ zTaJn7>v+G5Ts(m^M`+hm-?d+x)zuU_Yc%|t!;DW(jS>4c->_*gVZLA3$W5sVr@=?C zOa?kHL_c28>5~8CCL`*h?V&RtFFNT}1c%-zxjx-!-N4j=2X5nc3Ju;P&l4>--VkD; ze6*yUvu$2UW25}D3FjtG++t~Aeq-l|id6NAPi>`_jc<(J_Mo@x+L@y*RihGRBrPe5 zK|bC~3S*j<)F1Dec2MzYa`&H+?hnp;3OX^&!ku&dPbY@;SFBpTR$su0VWR+h&%d1& z)*z`;S!5E03~u?>;JY7^36B5b?uSJF9J(KpqCw-oA5xV9?uEn-3nTYR+Hh}`q|?Ez zlDb1TL?TCp^>BxUdG|sh$AoeBKRT*ocOl}ga`bkx2bUr8-QtKGB_>?lh@2_rzq1j$ zo^g{pa=aM3S}{O9z}1h#QO7P+{MRjt$Qfh4Q^yoGqzyf9M;|9QZxCyBAoWs!SK8oLw{x$#lm z2i#4GFoCgy-f8KKTyTlr9f{r|iCut+3WRsLB=4F@^omRDYE0fWn7qp?!BwE}Rh}dk z1Am(*iA_~E!=3WRF7(7*(Mi&vq1Sj0-O`D_>JxX1{3WOtcQzEukFLknBVkFGfb2kAu4?lZxDyiTql) zP*fcoV}H>qji%1o;^=AbHH2H;JJ8Dk+{o$X;;ruFfP!Etf}Zl6FbjY1@r20Z%^vEUk5QS~8e z5t*5Zs{e~x5Ip|3)c)%dVYhYppa~C&%H;mbLdC}CL^WV1`rma*Wpj~gphi!k zkx~7TXc(&`8Vw_cMu$43G4YpIVy*a8IHPenqOrJtv$_9jpe_T1Y*Zq6PU$E; z{1*J*bxOyEHHi1dG^po5ddpkkac zXxxA4TsS5Xe5XtSfswCM5E2C&5)*Y!W_-v{Q~QV5XaF1647qZkqBdnl!qg1p!nFiU z7-k?qqRQg$1(uU(V1OsMtsR&@>cU9eA&)o&5(VR$H!{FT8&3bQXG0XbfeYqAd(>D( z)wRJ-E}|h3aGmxlKTZ&Miupo3IzG?GMTc4fijK~Eoi{Xjf1~IyQxR2P$=NbYH4ZuY zoIoq;xWM2Bv| z0!2>adUL^2rlA(V6AR`c@G3-~6Ohw}RY?1%3VHbuMmd)cJmmruiVba)a$fEym~vi} z;v&cRz#&JU6DX&0y){rMmCN{Fkn<^&%Lg7g@|=i#SfSK^DwLO;V3c$Dz#&JU6Oj)q zlo!DSQ;rR3oeTqx z@WlN05N3=A9A;RT8bf1KgUhi%VQX;tK~0cLKMpUfMvWmYvU$!)keg+5xxw%fRfs<2 zmjrugL}H1pt02v_Y)c0?LkBQeCm-u14=u>_YkkbsOH2=(KxQPIlUQ81>ys+Nr zLwdu~;lJ1~UoHcsG6FIg`jFoKnaA*@F;EsGAc+~yVg8xI@MSPi0)sx~x3l5&<)7IL zU-H5weptQ&QkUV(<)4WQZ#s_JFO;^RPx5z~7my6`G zfl2_%O9Tuw%<+L#4f{c)6UBqkIZPT89Y#FjR@!?Z3n_}rd>mEH1MK|*lt|!75nRIICa9p$;W5+?ghtH? z;8Jt;1DZlGqPoTl=r8R3y-yrIe&Hb!5iC3blm|F?s+k3PsyR8hA!PAM6Yv0PWB`n% zB|P3RFv>H|HXQvp_5mF2zyKcuKQ|{`KOcX8D|=5jK&6|Hw=O84`uTVQR2q0O{THvG z-QbKC>jsApwQ^XH|A|#ht|$RKWc*UZk5k_8LUn|H2cZtDj&g;AJ;WOija%WucR2hU zMSwRz6v0X#Z*z{Xy`Q~jqAM!SM6AQlBn=YIHU7sL(KQ}N&jhy_!Q*2r(@F|KC)eKQG!vvrb zL>i(3A)p6vevu$-3bGCSdq}Ms5Jo5Cn1P<7q~Y|BG{BU-%FoBy&68u|<6`3G!SQr+ z_3?2+u;DE1-;EK}c>f1l>w_ApfuDV_HM%zdAr2q*;07oPfhL7?&67WuQJ&xkoj|g~ zCn0!qLb~_#0cPUuvdRa9J##R=5qn1?%aB^2CJ2q_DkL{G0B8(>cyvODNerRSu$GaEkIf?)`!a)N|Z#Q%l0>`fF_oLF`lsgiilre_;jCOWH=1mpycKW(ng?R2EP^jr6Ec*uBDs5kvG`70CEEm zj{p|@nB#kfzKBzgCpxtGvO79=tqSE9dX6BVkWmc^kk?^nD`p0{Z82J@hI+tB6Yx#HugGAfHMYSYZ_-1#Wa6 z;W>r@Cn`P+`pEo)fz`YPAOMfi_pvmIC>WSru3U&+037@hLX1q1gh1xv#5b2!{{21^lo`4n@7M$Vu2YPwg`vvo~#Fa5tQo%$dpaqHr^KL{b5vb;h zNH7k5Dg7;{_7C(60;vU$LQIEPU5iH`u>nRO&I*DYeS-KAU}ZrJ0pTh7HZN;(bhY;d z>9H~j#HyeqMK^CJ&K5N?a3GkMBMLzf$wM#kbB!pJXdAv@Vukg`WdQ?#{;1r=XhjSH zTo{eJHqM1mkv7}_jkTd65I#I~1Om;Bc%5<)(FryzC~w7HVIb(Z7KK5W2n4OGkhs`b z0K&6OtPLB1aI+B%qJcoT5fz0XykIF6UcOjk&?$zRN}vVmi1@JLAMaHlJ}NH} z!Foix#L9ELHi-DJ;vo-$hz~1H@*s!=u-XYkDAFsJPzHfgL8%)?1tLGJ_{e(~ksnqX zWco1H+?L^{NXWD{rJL<`)_NH|I;h!(I#Ha;YX46&6w!3-e= zhC@#9f@n7S4}K6;@XBF0EQl)D+);r8BdWkwEBX3FRKc5B;94W9z*a2rtr3TXDgQ70 z0FrPF5xgb(=HK~2oEIHivE@U8Xo6RH7^aYlXo6S4!+{Y^U`x1sNDxh6Yu0>VM1UJVh|^b?Ihp>16441rGsJIh`WUc z9O82sWHkQ%g&{x^jug=mxB(52gcB~Ekl*tym%}zkM|8nUhlY{T5nb>yARHLc1uqT4 zfe~HsvJM;=(FJeW1_wrDh-DChRfN!l=ZHm6k)V)|LyzbJTLI?7g6M)*i5_kZC`XP( zq03D;D548GH!sD35nW&l#dy>VM21)u0b0Y^CoB15c>Etn$)pb5_rA>-jYD*ziE1JMPxj)cboNTkA1 z5l~3Qf+D^xAdt!{F$^;g@KT{z2DC%P+{#~g0dEcSLeLH026u=PG;N2XBo&wm6^cwq z1foKLi3$Wsg#r*2aS^=2$Pjx}#8|PYB#;yS=mT2wSsC9xa+niD_}p#MIAH+c(|A>p zVLE{DX;46-0x{B{c!aQrxnrD+k+4Iz8X|niVIfuoxho{j&|oMcHmq(Tm=QqCuu6zQ22FAQ$_V1mX}l`&5F<#4p+Rnq zjtC!eUvxzHyrRf321NLfPopDZ!(5s`PWYn>Xw5%L{u%%2i0~oDMMs3ss|62HhYVJT zX$B&EXg;)_>c!? zAi{?{FcME_&?Ey1Cp6423*>}9nt;~)D*0!;M`8&La>0N&Dr8$sMEKC;g^36sn!7L& z;X^*0iHHqe#u!!^AZA!_pfx`u|BUlYMEFo7U?ReYA^{T-KDJpG-yb4;4Q{b(h$bc? zeD1Lk9BqJ7I_B90ssy2iuQeYhs4o9%T!0KJG=y0|_;e^}uz>LCP|#oj;nR7Q^dUxA zK=^cQvVtRx1qcN`5*Cm>omZtFZVURMLz5R4 zkUbrmyRZ=1LsJ*fl!}#i1oHui8D@kqL{Ovtt3KF>=y}EaA&S|E=%FyjMnunBejjd& zh@My79fl&Jhh{8nL~8$-uprdn7$IaSe7mQiEQO88o>$HtrUQ{ZG>2g$vWLPa8<9P) zG&zI;0I9qs!C@dGHZ0N#)CfY%Fe4g-sWE!$>#r)&K!ne$q7L_n2%lF;9fl&p=haS! zp@{H#<;`IzB7A7_qk)JGoBIgl1fd4U2_Z{C_rm|36GZrstJOe+4^2)q5aIJYLjbZx zNR5mvB~W=gV0bVf2P&^@#)BcQ7gL;I9*}`P+?Ics3kvGIwm^YXS*d@UV26Nhbq1ZUp3YGra4b!b-#KljJRw5A9t5 z+hc$@`B}#YPhRKP#FoiT0-4<9Dke8uVRE&}6ui?4Yy}wV5WgS97rz>cEmrbVf{%V& zO1QSb;Dau@fR*l5FB_K;7ZASu?cdmv`a=!BHOEO!>qB%?s}7G2BjX{?lgY$2WAr?jx{61v!!d4zUlP zS?8VW1rWqhAjgW(o#9L@p~c!GTlds0{W-kGqUxr;9B*xO;S4NyqiVq&7-gXw@_4oh zw%IuaI&%C-iYwfVEjTtLUnghqk19otPF4do8*uI*Fu>KvPfewSjPi<6*wftWtvnn zl}w?KnPf5<9K=^8GZe^V1<($#@}HVm_}TmVa-2x&`u3jw93TM;JsUNB@O>Kxdv9-q z4+~c}e-ii~<3|_Yt6p+OI4}3(10a7Jr(hv+u zT9N-q-dq?3Y~ux+An-5>o1%gE6+8_2jrbS>jDlqId@yj}8u0>n7{JFyCSrIP_)S4v zCIJRyN`O&V45T`PZ-?N6+5t5nP95J4{6@=Jd@yhj0I^;?4B%rSi9a3&e$$9@L10AQ z$Y6zB0DVkkI|KnA9SKSV7`iUP2Lt=?5%+?J0s7D?JRSyqGmscSfH9Go7#|EAi$LN& z9tQBCoBQxE@EZ+|L>Mwk`Cv2_`u8jFksGP zqMQ*J5;5`blEEYeNeS>U1Rt_n01pH2f{_Wsi0_iYWj>L2{2zfG6kKq5@AH!Ak*12 zWJ-u{2k@bpBpwE6LD#v6FlhXO6EmYt=l`1~Ja&nyje_c7sJIQEdKY^0FH*N#bLA*C-o4A6%b zTJbPI3tIrq8bn`0W`d1R1U?XaP#h#vHQ@LL*61L8fSn{Tedu?__~`>*XoAKESezr; zB$GuZ@&V|hAZuy_eCT)W2rw$-H^2;3fIc9f2vR9@-wF{QF*hTFgqEmt3X81)$41~L zVSdq4IA0$uu*gQ>4d7$L{s1hyLG}#RwFqO2%%ZV~eiGngA+;C2enC13=esl}j1O!H zfb`2oD<=ee0`fJmtV9@FK)Dpy{@4sCE|38qu>4p^8H2xHx&|y4@YyP&osz-s69~pa zcLDO_V=;;O21p%Qu>WHS;umD@MEbx+4j6`RSK;p$?1O;p090)VI;XHe!GWMl3X6rV zOyThX7z>Uc$Uq{}2iy>$Uy#~Tp>YXPE-3c_$|TwbcvpaJutCNF^(!DoX`p9O@O%Jo zPbKEN0EQlcBeY`>NYbN?cBpru*4mgR9RHyj+r7)5GRRkCd%9|))ng`Jb@*#q)fy@Wp zHqVa_Yy~IAEilbP7IFyf(0U*N#wOjzII58 zNt6K)J=~5-hUN=Ee8jvH7@C0jIh#$C3rJ4UQ+#~1fF&=auFnqx$rO=auq_#y8_+di zpAB|9LNWz=`yoES<}$b)m{1e@WoT$Xw!uV-Ed-ju(g!3L&?^*EfG2@+M-~m;_QEFv zkP$*-6}U;Hbj#Ncd=rqE*8z_M`$P&TNDz4gp9v(+e}S!``|AjOP>|v)0Y*jYmjoCM z**ismp(}(07`i{02!mt=5)NcNlfNAc{oDpW42(-+{z74)n}+z?fs_W4ABzsnAwX#a z_Tyl%LSq%KDS+uOkRXv}Ft334(4axJIgp?t3p)HXYoH(OB*LJv05k;C2hhP|A0&l@ zKES~s;@p%BJQ#8Qi%d)&XU`HP0i^1#? zvKKJZg~kFn6G5Dpf$1d;$_YU^0?N6lRFH-cd84r*e+8z$kX->7WLKc33fUDnWkj6! z0Q%59i2O1I`v?fR05CN+aSnmh;b5A<7f}iCBGX!^ZUII#oa6AI+LizxUu8{p{fHD+OZyIC)?I=)gfpkF}t6)}( zEPwLJfQBTu5DbnLG~kTkchT?R^5Fv+AvDJUu@=hffY*ThIDkQOY|t-M0|2}sE7g4c zf*qTX?*vmx$Zvq}89{R<8kmL>^+5xLWuiX7P=(?L*qch6Pm^gB^gHzY^a1w=(F{x% zk}23m0@H$ite1d~0gX#QA2AMsDGB;j5B_(VKp{l=fx-$grhrcdL-q{zDMB?Uu^9jNXNsshkB2QVmS0M&cgHrVL?I=-<0zCHo@L^`Oe zKw|+c8xUhM1F7m0#v6b^u^W6O1JWCqeLy+_qY|51wQvgTfAo+nW zQb0BdrtFaa1K1#c0M_52F%8b@5o@5JJc%Cj=a(}mwGjOk14&Sc@&juz#4*hP^%r6; z1z<#b0h|etJs7M|A0P!Gju|j>hHMC|=Rr9uG9@OCBXBYg$~yrJ$~zgrzd*bpPL?PG z5Vjy$0bfFl$zU}K$~VBu6O>zkGkj2P0bsCQff@=VD+Zh^gK7yhW_)if$9;UbO`AZEHOiN1u}lf zAAlJwG*&@KhWr6ANvP(*1QTlFSOqYs{tTwDP>v3&2hctv0E6-akeNYa3v5?``2dqx zqD_L70m`YtR2<69n8=0;qP>7`>_PekALJnB44@VX(+6A=jE@D48Dyvu{U3lqbqi3s zhUP*5Myyc)E1(eN3}OWps=a~=87yZopCOJnU{$bffciMp4s7>wgy;(@d2U^)j*{M^3NawKs8@5-Gb(CfIP_O zfSqbk4g&V}2x!NEYQso50^%3s3`7_ka7E-7RP-U61bglvUkp~p1hj+qbb$SiP>css zf$AGzA1G880M-ZjFtFbi%BjIL6pC+bFl8tDaghE&^BJ(;8*T@-BtY+ilplt{^CLFM z86cU0@If4xY%1)FK`IKj14UZsU9dC@!_bp+e0B=bSSaTLt7Xu-1~L^V=AEG04y~^u zDe(UkcJ{0d!$26`^DDe$PMyXeLn-9Lflh_4rEA9q+W!xIPE-6og^oEC%hKsiclW-M z-HvK**byW9qn$aVpd^Y}8+R0??Kjd(`60Ml_8XAj*6&jAV8*tfM+fBwPzTeO0Pz`j zrk&@HpgP~LVG6Mh3bhh`L{_HyP~+51{FlVpHKRt56mtN{P51{i5A#$(H8Kw^)IRME zYK1T=&TJ_LA&{E0{xXucFuAi2lCZE< zHg47GkqO^IHsyYV%zROxyR>O4;i~%}6PAUn-!;3QQ}FYM|7b_CKF7w!Af2Nm%lZXF z>pmKRgr29G{)m^%+yz;`eqsGQws`3mPKWeC89nwCm?^^ZkO@;qHl>e62D>)K0qUH4 z1x{S~C9-}8{c0Rk%`y+A9SrU413V!8F4cDV610{zEtp`c9U_A{oPCf_=bQr1XpKWJ zmLD$~h29y+P<;Su=6Zo`E4!T8SM@H$=+Y(r!2Lqt$gu%5-93-n%(*)Mn{T=gyShfc zA8gyb-EMpix8}JH625$W-jL&!`mf9I{?wLvdE74#`{Vw2z8 Date: Tue, 31 Oct 2023 06:18:12 -0700 Subject: [PATCH 4/6] start NEWS for develop --- NEWS.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/NEWS.md b/NEWS.md index 0c8f5c71..5c70c754 100644 --- a/NEWS.md +++ b/NEWS.md @@ -1,3 +1,10 @@ +develop +============== + +Changes: + +1. none yet + Cyclops v3.4.0 ============== From aa321ae20c3492e4eace10ba431f33367ce7a7cc Mon Sep 17 00:00:00 2001 From: Marc Suchard Date: Tue, 31 Oct 2023 13:11:31 -0700 Subject: [PATCH 5/6] fix GH actions badge --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 3db57215..6b2b6714 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@ Cyclops ======= -[![Build Status](https://github.com/ohdsi/Cyclops/workflows/R-CMD-check/badge.svg)](https://github.com/OHDSI/Cyclops/actions?query=workflow%3AR-CMD-check) +[![Build Status](https://github.com/ohdsi/Cyclops/actions/workflows/R_CMD_check_Hades.yaml/badge.svg)](https://github.com/OHDSI/Cyclops/actions?query=workflow%3AR-CMD-check) [![codecov.io](https://codecov.io/github/OHDSI/Cyclops/coverage.svg?branch=main)](https://codecov.io/github/OHDSI/Cyclops?branch=main) [![CRAN_Status_Badge](https://www.r-pkg.org/badges/version/Cyclops)](https://CRAN.R-project.org/package=Cyclops) [![CRAN_Status_Badge](https://cranlogs.r-pkg.org/badges/Cyclops)](https://cran.r-project.org/package=Cyclops) From 69275174900dd459a5d8dd22aaa54c663a5a9847 Mon Sep 17 00:00:00 2001 From: Marc Suchard Date: Tue, 31 Oct 2023 14:56:00 -0700 Subject: [PATCH 6/6] update website with GH action badge --- docs/index.html | 2 +- docs/pkgdown.yml | 2 +- docs/reference/confint.cyclopsFit.html | 651 ++------------ docs/reference/createControl.html | 268 ++++-- docs/reference/createPrior.html | 231 +++-- docs/reference/getHyperParameter.html | 1100 +++++++++++------------ docs/reference/logLik.cyclopsFit.html | 597 ++++++++++-- docs/reference/simulateCyclopsData.html | 220 ++--- 8 files changed, 1592 insertions(+), 1479 deletions(-) diff --git a/docs/index.html b/docs/index.html index 660ec66e..567eaf26 100644 --- a/docs/index.html +++ b/docs/index.html @@ -77,7 +77,7 @@

Cyclops

-

Build Status codecov.io CRAN_Status_Badge CRAN_Status_Badge

+

Build Status codecov.io CRAN_Status_Badge CRAN_Status_Badge

Cyclops is part of the HADES.

diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml index d55408be..68ce28c5 100644 --- a/docs/pkgdown.yml +++ b/docs/pkgdown.yml @@ -2,5 +2,5 @@ pandoc: 3.1.2 pkgdown: 2.0.7 pkgdown_sha: ~ articles: {} -last_built: 2023-10-31T13:12Z +last_built: 2023-10-31T21:54Z diff --git a/docs/reference/confint.cyclopsFit.html b/docs/reference/confint.cyclopsFit.html index 9cccd20d..1569fb0e 100644 --- a/docs/reference/confint.cyclopsFit.html +++ b/docs/reference/confint.cyclopsFit.html @@ -115,7 +115,7 @@

Examples

#Generate some simulated data:
 sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                            model = "poisson")
-#> Sparseness = 77 %
+#> Sparseness = 75.9 %
 cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                     addIntercept = TRUE)
 #> Sorting covariates by covariateId and rowId
@@ -128,594 +128,99 @@ 
Examples

 #Fit the model
 fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
 #> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1698757931] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Performing 10-fold cross-validation [seed = 1698789245] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
 #> Using 1 thread(s)
-#> Starting var = 0.23 (default)
-#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #1 Rep #1 pred log like = 267.858
-#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #2 Rep #1 pred log like = 210.218
-#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #3 Rep #1 pred log like = 247.642
-#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #4 Rep #1 pred log like = 268.625
-#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #5 Rep #1 pred log like = 234.92
-#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #6 Rep #1 pred log like = 256.935
-#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #7 Rep #1 pred log like = 237.206
-#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #8 Rep #1 pred log like = 203.575
-#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #9 Rep #1 pred log like = 268.979
-#> Running at Laplace(2.94884) None  Grid-point #1 at 0.23 	Fold #10 Rep #1 pred log like = 313.499
-#> AvgPred = 250.946 with stdev = 30.3841
-#> Completed at 0.23
-#> Next point at 2.3 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> 
-#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #1 Rep #1 pred log like = 267.817
-#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #2 Rep #1 pred log like = 210.18
-#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #3 Rep #1 pred log like = 247.667
-#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #4 Rep #1 pred log like = 268.65
-#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #5 Rep #1 pred log like = 234.965
-#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #6 Rep #1 pred log like = 256.945
-#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #7 Rep #1 pred log like = 237.151
-#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #8 Rep #1 pred log like = 203.606
-#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #9 Rep #1 pred log like = 268.987
-#> Running at Laplace(0.932505) None  Grid-point #2 at 2.3 	Fold #10 Rep #1 pred log like = 313.505
-#> AvgPred = 250.947 with stdev = 30.3849
-#> Completed at 2.3
-#> Next point at 23 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> 
-#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #1 Rep #1 pred log like = 267.803
-#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #2 Rep #1 pred log like = 210.168
-#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #3 Rep #1 pred log like = 247.674
-#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #4 Rep #1 pred log like = 268.657
-#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #5 Rep #1 pred log like = 234.98
-#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #6 Rep #1 pred log like = 256.948
-#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #7 Rep #1 pred log like = 237.134
-#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #8 Rep #1 pred log like = 203.616
-#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #9 Rep #1 pred log like = 268.988
-#> Running at Laplace(0.294884) None  Grid-point #3 at 23 	Fold #10 Rep #1 pred log like = 313.506
-#> AvgPred = 250.947 with stdev = 30.3852
-#> Completed at 23
-#> Next point at 230 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> 
-#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #1 Rep #1 pred log like = 267.799
-#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #2 Rep #1 pred log like = 210.165
-#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #3 Rep #1 pred log like = 247.677
-#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #4 Rep #1 pred log like = 268.66
-#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #5 Rep #1 pred log like = 234.984
-#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #6 Rep #1 pred log like = 256.948
-#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #7 Rep #1 pred log like = 237.128
-#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #8 Rep #1 pred log like = 203.619
-#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(0.0932505) None  Grid-point #4 at 230 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 230
-#> Next point at 2300 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #1 Rep #1 pred log like = 267.798
-#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #4 Rep #1 pred log like = 268.66
-#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #5 Rep #1 pred log like = 234.985
-#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #7 Rep #1 pred log like = 237.126
-#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(0.0294884) None  Grid-point #5 at 2300 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2300
-#> Next point at 23000 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #7 Rep #1 pred log like = 237.126
-#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(0.00932505) None  Grid-point #6 at 23000 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 23000
-#> Next point at 230000 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #7 Rep #1 pred log like = 237.126
-#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(0.00294884) None  Grid-point #7 at 230000 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 230000
-#> Next point at 2.3e+06 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(0.000932505) None  Grid-point #8 at 2.3e+06 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+06
-#> Next point at 2.3e+07 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(0.000294884) None  Grid-point #9 at 2.3e+07 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+07
-#> Next point at 2.3e+08 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(9.32505e-05) None  Grid-point #10 at 2.3e+08 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+08
-#> Next point at 2.3e+09 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(2.94884e-05) None  Grid-point #11 at 2.3e+09 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+09
-#> Next point at 2.3e+10 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(9.32505e-06) None  Grid-point #12 at 2.3e+10 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+10
-#> Next point at 2.3e+11 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> search[ 2.3e+10 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(2.94884e-06) None  Grid-point #13 at 2.3e+11 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+11
-#> Next point at 2.3e+12 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> search[ 2.3e+10 ] = 250.948(30.3853)
-#> search[ 2.3e+11 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(9.32505e-07) None  Grid-point #14 at 2.3e+12 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+12
-#> Next point at 2.3e+13 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> search[ 2.3e+10 ] = 250.948(30.3853)
-#> search[ 2.3e+11 ] = 250.948(30.3853)
-#> search[ 2.3e+12 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(2.94884e-07) None  Grid-point #15 at 2.3e+13 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+13
-#> Next point at 2.3e+14 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> search[ 2.3e+10 ] = 250.948(30.3853)
-#> search[ 2.3e+11 ] = 250.948(30.3853)
-#> search[ 2.3e+12 ] = 250.948(30.3853)
-#> search[ 2.3e+13 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(9.32505e-08) None  Grid-point #16 at 2.3e+14 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+14
-#> Next point at 2.3e+15 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> search[ 2.3e+10 ] = 250.948(30.3853)
-#> search[ 2.3e+11 ] = 250.948(30.3853)
-#> search[ 2.3e+12 ] = 250.948(30.3853)
-#> search[ 2.3e+13 ] = 250.948(30.3853)
-#> search[ 2.3e+14 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(2.94884e-08) None  Grid-point #17 at 2.3e+15 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+15
-#> Next point at 2.3e+16 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> search[ 2.3e+10 ] = 250.948(30.3853)
-#> search[ 2.3e+11 ] = 250.948(30.3853)
-#> search[ 2.3e+12 ] = 250.948(30.3853)
-#> search[ 2.3e+13 ] = 250.948(30.3853)
-#> search[ 2.3e+14 ] = 250.948(30.3853)
-#> search[ 2.3e+15 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(9.32505e-09) None  Grid-point #18 at 2.3e+16 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+16
-#> Next point at 2.3e+17 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> search[ 2.3e+10 ] = 250.948(30.3853)
-#> search[ 2.3e+11 ] = 250.948(30.3853)
-#> search[ 2.3e+12 ] = 250.948(30.3853)
-#> search[ 2.3e+13 ] = 250.948(30.3853)
-#> search[ 2.3e+14 ] = 250.948(30.3853)
-#> search[ 2.3e+15 ] = 250.948(30.3853)
-#> search[ 2.3e+16 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(2.94884e-09) None  Grid-point #19 at 2.3e+17 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+17
-#> Next point at 2.3e+18 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> search[ 2.3e+10 ] = 250.948(30.3853)
-#> search[ 2.3e+11 ] = 250.948(30.3853)
-#> search[ 2.3e+12 ] = 250.948(30.3853)
-#> search[ 2.3e+13 ] = 250.948(30.3853)
-#> search[ 2.3e+14 ] = 250.948(30.3853)
-#> search[ 2.3e+15 ] = 250.948(30.3853)
-#> search[ 2.3e+16 ] = 250.948(30.3853)
-#> search[ 2.3e+17 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(9.32505e-10) None  Grid-point #20 at 2.3e+18 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+18
-#> Next point at 2.3e+19 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> search[ 2.3e+10 ] = 250.948(30.3853)
-#> search[ 2.3e+11 ] = 250.948(30.3853)
-#> search[ 2.3e+12 ] = 250.948(30.3853)
-#> search[ 2.3e+13 ] = 250.948(30.3853)
-#> search[ 2.3e+14 ] = 250.948(30.3853)
-#> search[ 2.3e+15 ] = 250.948(30.3853)
-#> search[ 2.3e+16 ] = 250.948(30.3853)
-#> search[ 2.3e+17 ] = 250.948(30.3853)
-#> search[ 2.3e+18 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(2.94884e-10) None  Grid-point #21 at 2.3e+19 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+19
-#> Next point at 2.3e+20 with value 0 and continue = 1
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> search[ 2.3e+10 ] = 250.948(30.3853)
-#> search[ 2.3e+11 ] = 250.948(30.3853)
-#> search[ 2.3e+12 ] = 250.948(30.3853)
-#> search[ 2.3e+13 ] = 250.948(30.3853)
-#> search[ 2.3e+14 ] = 250.948(30.3853)
-#> search[ 2.3e+15 ] = 250.948(30.3853)
-#> search[ 2.3e+16 ] = 250.948(30.3853)
-#> search[ 2.3e+17 ] = 250.948(30.3853)
-#> search[ 2.3e+18 ] = 250.948(30.3853)
-#> search[ 2.3e+19 ] = 250.948(30.3853)
-#> 
-#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #1 Rep #1 pred log like = 267.797
-#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #2 Rep #1 pred log like = 210.163
-#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #3 Rep #1 pred log like = 247.678
-#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #4 Rep #1 pred log like = 268.661
-#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #5 Rep #1 pred log like = 234.986
-#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #6 Rep #1 pred log like = 256.949
-#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #7 Rep #1 pred log like = 237.125
-#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #8 Rep #1 pred log like = 203.62
-#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #9 Rep #1 pred log like = 268.989
-#> Running at Laplace(9.32505e-11) None  Grid-point #22 at 2.3e+20 	Fold #10 Rep #1 pred log like = 313.507
-#> AvgPred = 250.948 with stdev = 30.3853
-#> Completed at 2.3e+20
-#> Next point at 2.41831e+12 with value 250.948 and continue = 0
-#> search[ 0.23 ] = 250.946(30.3841)
-#> search[ 2.3 ] = 250.947(30.3849)
-#> search[ 23 ] = 250.947(30.3852)
-#> search[ 230 ] = 250.948(30.3853)
-#> search[ 2300 ] = 250.948(30.3853)
-#> search[ 23000 ] = 250.948(30.3853)
-#> search[ 230000 ] = 250.948(30.3853)
-#> search[ 2.3e+06 ] = 250.948(30.3853)
-#> search[ 2.3e+07 ] = 250.948(30.3853)
-#> search[ 2.3e+08 ] = 250.948(30.3853)
-#> search[ 2.3e+09 ] = 250.948(30.3853)
-#> search[ 2.3e+10 ] = 250.948(30.3853)
-#> search[ 2.3e+11 ] = 250.948(30.3853)
-#> search[ 2.3e+12 ] = 250.948(30.3853)
-#> search[ 2.3e+13 ] = 250.948(30.3853)
-#> search[ 2.3e+14 ] = 250.948(30.3853)
-#> search[ 2.3e+15 ] = 250.948(30.3853)
-#> search[ 2.3e+16 ] = 250.948(30.3853)
-#> search[ 2.3e+17 ] = 250.948(30.3853)
-#> search[ 2.3e+18 ] = 250.948(30.3853)
-#> search[ 2.3e+19 ] = 250.948(30.3853)
-#> search[ 2.3e+20 ] = 250.948(30.3853)
-#> 
-#> 
-#> Maximum predicted log likelihood (250.948) estimated at:
-#> 	2.41831e+12 (variance)
-#> 	9.09409e-07 (lambda)
+#> Starting var = 0.241 (default)
+#> Running at Laplace(2.88076) None  Grid-point #1 at 0.241 	Fold #1 Rep #1 pred log like = 558.834
+#> Running at Laplace(2.88076) None  Grid-point #1 at 0.241 	Fold #2 Rep #1 pred log like = 629.538
+#> Running at Laplace(2.88076) None  Grid-point #1 at 0.241 	Fold #3 Rep #1 pred log like = 578.237
+#> Running at Laplace(2.88076) None  Grid-point #1 at 0.241 	Fold #4 Rep #1 pred log like = 557.823
+#> Running at Laplace(2.88076) None  Grid-point #1 at 0.241 	Fold #5 Rep #1 pred log like = 639.232
+#> Running at Laplace(2.88076) None  Grid-point #1 at 0.241 	Fold #6 Rep #1 pred log like = 660.216
+#> Running at Laplace(2.88076) None  Grid-point #1 at 0.241 	Fold #7 Rep #1 pred log like = 493.902
+#> Running at Laplace(2.88076) None  Grid-point #1 at 0.241 	Fold #8 Rep #1 pred log like = 647.66
+#> Running at Laplace(2.88076) None  Grid-point #1 at 0.241 	Fold #9 Rep #1 pred log like = 873.862
+#> Running at Laplace(2.88076) None  Grid-point #1 at 0.241 	Fold #10 Rep #1 pred log like = 578.915
+#> AvgPred = 621.822 with stdev = 97.0547
+#> Completed at 0.241
+#> Next point at 2.41 with value 0 and continue = 1
+#> search[ 0.241 ] = 621.822(97.0547)
+#> 
+#> Running at Laplace(0.910975) None  Grid-point #2 at 2.41 	Fold #1 Rep #1 pred log like = 558.859
+#> Running at Laplace(0.910975) None  Grid-point #2 at 2.41 	Fold #2 Rep #1 pred log like = 629.492
+#> Running at Laplace(0.910975) None  Grid-point #2 at 2.41 	Fold #3 Rep #1 pred log like = 578.231
+#> Running at Laplace(0.910975) None  Grid-point #2 at 2.41 	Fold #4 Rep #1 pred log like = 557.829
+#> Running at Laplace(0.910975) None  Grid-point #2 at 2.41 	Fold #5 Rep #1 pred log like = 639.243
+#> Running at Laplace(0.910975) None  Grid-point #2 at 2.41 	Fold #6 Rep #1 pred log like = 660.233
+#> Running at Laplace(0.910975) None  Grid-point #2 at 2.41 	Fold #7 Rep #1 pred log like = 493.917
+#> Running at Laplace(0.910975) None  Grid-point #2 at 2.41 	Fold #8 Rep #1 pred log like = 647.677
+#> Running at Laplace(0.910975) None  Grid-point #2 at 2.41 	Fold #9 Rep #1 pred log like = 873.817
+#> Running at Laplace(0.910975) None  Grid-point #2 at 2.41 	Fold #10 Rep #1 pred log like = 578.913
+#> AvgPred = 621.821 with stdev = 97.0402
+#> Completed at 2.41
+#> Next point at 0.0241 with value 0 and continue = 1
+#> search[ 0.241 ] = 621.822(97.0547)
+#> search[ 2.41 ] = 621.821(97.0402)
+#> 
+#> Running at Laplace(9.10975) None  Grid-point #3 at 0.0241 	Fold #1 Rep #1 pred log like = 558.791
+#> Running at Laplace(9.10975) None  Grid-point #3 at 0.0241 	Fold #2 Rep #1 pred log like = 629.679
+#> Running at Laplace(9.10975) None  Grid-point #3 at 0.0241 	Fold #3 Rep #1 pred log like = 578.253
+#> Running at Laplace(9.10975) None  Grid-point #3 at 0.0241 	Fold #4 Rep #1 pred log like = 557.797
+#> Running at Laplace(9.10975) None  Grid-point #3 at 0.0241 	Fold #5 Rep #1 pred log like = 639.192
+#> Running at Laplace(9.10975) None  Grid-point #3 at 0.0241 	Fold #6 Rep #1 pred log like = 660.188
+#> Running at Laplace(9.10975) None  Grid-point #3 at 0.0241 	Fold #7 Rep #1 pred log like = 493.85
+#> Running at Laplace(9.10975) None  Grid-point #3 at 0.0241 	Fold #8 Rep #1 pred log like = 647.622
+#> Running at Laplace(9.10975) None  Grid-point #3 at 0.0241 	Fold #9 Rep #1 pred log like = 873.997
+#> Running at Laplace(9.10975) None  Grid-point #3 at 0.0241 	Fold #10 Rep #1 pred log like = 578.914
+#> AvgPred = 621.828 with stdev = 97.0986
+#> Completed at 0.0241
+#> Next point at 0.00241 with value 0 and continue = 1
+#> search[ 0.0241 ] = 621.828(97.0986)
+#> search[ 0.241 ] = 621.822(97.0547)
+#> search[ 2.41 ] = 621.821(97.0402)
+#> 
+#> Running at Laplace(28.8076) None  Grid-point #4 at 0.00241 	Fold #1 Rep #1 pred log like = 558.629
+#> Running at Laplace(28.8076) None  Grid-point #4 at 0.00241 	Fold #2 Rep #1 pred log like = 630.036
+#> Running at Laplace(28.8076) None  Grid-point #4 at 0.00241 	Fold #3 Rep #1 pred log like = 578.386
+#> Running at Laplace(28.8076) None  Grid-point #4 at 0.00241 	Fold #4 Rep #1 pred log like = 557.741
+#> Running at Laplace(28.8076) None  Grid-point #4 at 0.00241 	Fold #5 Rep #1 pred log like = 638.953
+#> Running at Laplace(28.8076) None  Grid-point #4 at 0.00241 	Fold #6 Rep #1 pred log like = 660.184
+#> Running at Laplace(28.8076) None  Grid-point #4 at 0.00241 	Fold #7 Rep #1 pred log like = 493.637
+#> Running at Laplace(28.8076) None  Grid-point #4 at 0.00241 	Fold #8 Rep #1 pred log like = 647.6
+#> Running at Laplace(28.8076) None  Grid-point #4 at 0.00241 	Fold #9 Rep #1 pred log like = 874.31
+#> Running at Laplace(28.8076) None  Grid-point #4 at 0.00241 	Fold #10 Rep #1 pred log like = 578.792
+#> AvgPred = 621.827 with stdev = 97.2197
+#> Completed at 0.00241
+#> Next point at 0.0010937 with value 621.827 and continue = 0
+#> search[ 0.00241 ] = 621.827(97.2197)
+#> search[ 0.0241 ] = 621.828(97.0986)
+#> search[ 0.241 ] = 621.822(97.0547)
+#> search[ 2.41 ] = 621.821(97.0402)
+#> 
+#> 
+#> Maximum predicted log likelihood (621.827) estimated at:
+#> 	0.0010937 (variance)
+#> 	42.7628 (lambda)
 #> 
 #> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(9.09409e-07) None 
+#> Using prior: Laplace(42.7628) None 
 
 #Find out what the optimal hyperparameter was:
 getHyperParameter(fit)
-#> [1] 2.418308e+12
+#> [1] 0.0010937
 
 #Extract the current log-likelihood, and coefficients
 logLik(fit)
-#> 'log Lik.' -1953.765 (df=3)
+#> 'log Lik.' -2134.836 (df=3)
 coef(fit)
 #> (Intercept)           1           2 
-#> -4.19783727  0.30746087  0.02797239 
+#> -3.70113314  0.01674055  0.00000000 
 
 #We can only retrieve the confidence interval for unregularized coefficients:
 confint(fit, c(0))
 #> Using 1 thread(s)
 #>             covariate     2.5 %    97.5 % evaluations
-#> (Intercept)         0 -4.236526 -4.159602          22
+#> (Intercept)         0 -3.729976 -3.673209          23
diff --git a/docs/reference/createControl.html b/docs/reference/createControl.html index 6f9278ee..016b0d87 100644 --- a/docs/reference/createControl.html +++ b/docs/reference/createControl.html @@ -186,7 +186,7 @@

Examples

#Generate some simulated data:
 sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                            model = "poisson")
-#> Sparseness = 75.05 %
+#> Sparseness = 75.6 %
 cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                     addIntercept = TRUE)
 #> Sorting covariates by covariateId and rowId
@@ -199,118 +199,204 @@ 
Examples

 #Fit the model
 fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
 #> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1698757933] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Performing 10-fold cross-validation [seed = 1698789247] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
 #> Using 1 thread(s)
-#> Starting var = 0.2495 (default)
-#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #1 Rep #1 pred log like = 693.612
-#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #2 Rep #1 pred log like = 727.871
-#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #3 Rep #1 pred log like = 856.472
-#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #4 Rep #1 pred log like = 872.52
-#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #5 Rep #1 pred log like = 757.649
-#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #6 Rep #1 pred log like = 752.08
-#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #7 Rep #1 pred log like = 777.327
-#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #8 Rep #1 pred log like = 670.9
-#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #9 Rep #1 pred log like = 778.766
-#> Running at Laplace(2.83126) None  Grid-point #1 at 0.2495 	Fold #10 Rep #1 pred log like = 958.317
-#> AvgPred = 784.551 with stdev = 83.2879
-#> Completed at 0.2495
-#> Next point at 2.495 with value 0 and continue = 1
-#> search[ 0.2495 ] = 784.551(83.2879)
+#> Starting var = 0.244 (default)
+#> Running at Laplace(2.86299) None  Grid-point #1 at 0.244 	Fold #1 Rep #1 pred log like = 103.184
+#> Running at Laplace(2.86299) None  Grid-point #1 at 0.244 	Fold #2 Rep #1 pred log like = 130.249
+#> Running at Laplace(2.86299) None  Grid-point #1 at 0.244 	Fold #3 Rep #1 pred log like = 160.028
+#> Running at Laplace(2.86299) None  Grid-point #1 at 0.244 	Fold #4 Rep #1 pred log like = 151.655
+#> Running at Laplace(2.86299) None  Grid-point #1 at 0.244 	Fold #5 Rep #1 pred log like = 175.354
+#> Running at Laplace(2.86299) None  Grid-point #1 at 0.244 	Fold #6 Rep #1 pred log like = 161.803
+#> Running at Laplace(2.86299) None  Grid-point #1 at 0.244 	Fold #7 Rep #1 pred log like = 130.623
+#> Running at Laplace(2.86299) None  Grid-point #1 at 0.244 	Fold #8 Rep #1 pred log like = 137.887
+#> Running at Laplace(2.86299) None  Grid-point #1 at 0.244 	Fold #9 Rep #1 pred log like = 173.734
+#> Running at Laplace(2.86299) None  Grid-point #1 at 0.244 	Fold #10 Rep #1 pred log like = 190.477
+#> AvgPred = 151.499 with stdev = 24.8369
+#> Completed at 0.244
+#> Next point at 2.44 with value 0 and continue = 1
+#> search[ 0.244 ] = 151.499(24.8369)
 #> 
-#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #1 Rep #1 pred log like = 693.629
-#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #2 Rep #1 pred log like = 727.901
-#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #3 Rep #1 pred log like = 856.465
-#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #4 Rep #1 pred log like = 872.541
-#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #5 Rep #1 pred log like = 757.617
-#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #6 Rep #1 pred log like = 752.117
-#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #7 Rep #1 pred log like = 777.31
-#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #8 Rep #1 pred log like = 670.913
-#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #9 Rep #1 pred log like = 778.729
-#> Running at Laplace(0.895323) None  Grid-point #2 at 2.495 	Fold #10 Rep #1 pred log like = 958.301
-#> AvgPred = 784.552 with stdev = 83.2805
-#> Completed at 2.495
-#> Next point at 24.95 with value 0 and continue = 1
-#> search[ 0.2495 ] = 784.551(83.2879)
-#> search[ 2.495 ] = 784.552(83.2805)
+#> Running at Laplace(0.905357) None  Grid-point #2 at 2.44 	Fold #1 Rep #1 pred log like = 103.166
+#> Running at Laplace(0.905357) None  Grid-point #2 at 2.44 	Fold #2 Rep #1 pred log like = 130.248
+#> Running at Laplace(0.905357) None  Grid-point #2 at 2.44 	Fold #3 Rep #1 pred log like = 160.03
+#> Running at Laplace(0.905357) None  Grid-point #2 at 2.44 	Fold #4 Rep #1 pred log like = 151.647
+#> Running at Laplace(0.905357) None  Grid-point #2 at 2.44 	Fold #5 Rep #1 pred log like = 175.309
+#> Running at Laplace(0.905357) None  Grid-point #2 at 2.44 	Fold #6 Rep #1 pred log like = 161.801
+#> Running at Laplace(0.905357) None  Grid-point #2 at 2.44 	Fold #7 Rep #1 pred log like = 130.578
+#> Running at Laplace(0.905357) None  Grid-point #2 at 2.44 	Fold #8 Rep #1 pred log like = 137.837
+#> Running at Laplace(0.905357) None  Grid-point #2 at 2.44 	Fold #9 Rep #1 pred log like = 173.718
+#> Running at Laplace(0.905357) None  Grid-point #2 at 2.44 	Fold #10 Rep #1 pred log like = 190.449
+#> AvgPred = 151.478 with stdev = 24.8369
+#> Completed at 2.44
+#> Next point at 0.0244 with value 0 and continue = 1
+#> search[ 0.244 ] = 151.499(24.8369)
+#> search[ 2.44 ] = 151.478(24.8369)
 #> 
-#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #1 Rep #1 pred log like = 693.634
-#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #2 Rep #1 pred log like = 727.911
-#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #3 Rep #1 pred log like = 856.462
-#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #4 Rep #1 pred log like = 872.547
-#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #5 Rep #1 pred log like = 757.606
-#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #6 Rep #1 pred log like = 752.129
-#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #7 Rep #1 pred log like = 777.305
-#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #8 Rep #1 pred log like = 670.917
-#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #9 Rep #1 pred log like = 778.718
-#> Running at Laplace(0.283126) None  Grid-point #3 at 24.95 	Fold #10 Rep #1 pred log like = 958.296
-#> AvgPred = 784.552 with stdev = 83.2781
-#> Completed at 24.95
-#> Next point at 249.5 with value 0 and continue = 1
-#> search[ 0.2495 ] = 784.551(83.2879)
-#> search[ 2.495 ] = 784.552(83.2805)
-#> search[ 24.95 ] = 784.552(83.2781)
+#> Running at Laplace(9.05357) None  Grid-point #3 at 0.0244 	Fold #1 Rep #1 pred log like = 103.24
+#> Running at Laplace(9.05357) None  Grid-point #3 at 0.0244 	Fold #2 Rep #1 pred log like = 130.205
+#> Running at Laplace(9.05357) None  Grid-point #3 at 0.0244 	Fold #3 Rep #1 pred log like = 160.006
+#> Running at Laplace(9.05357) None  Grid-point #3 at 0.0244 	Fold #4 Rep #1 pred log like = 151.671
+#> Running at Laplace(9.05357) None  Grid-point #3 at 0.0244 	Fold #5 Rep #1 pred log like = 175.49
+#> Running at Laplace(9.05357) None  Grid-point #3 at 0.0244 	Fold #6 Rep #1 pred log like = 161.794
+#> Running at Laplace(9.05357) None  Grid-point #3 at 0.0244 	Fold #7 Rep #1 pred log like = 130.755
+#> Running at Laplace(9.05357) None  Grid-point #3 at 0.0244 	Fold #8 Rep #1 pred log like = 138.031
+#> Running at Laplace(9.05357) None  Grid-point #3 at 0.0244 	Fold #9 Rep #1 pred log like = 173.692
+#> Running at Laplace(9.05357) None  Grid-point #3 at 0.0244 	Fold #10 Rep #1 pred log like = 190.557
+#> AvgPred = 151.544 with stdev = 24.8316
+#> Completed at 0.0244
+#> Next point at 0.00244 with value 0 and continue = 1
+#> search[ 0.0244 ] = 151.544(24.8316)
+#> search[ 0.244 ] = 151.499(24.8369)
+#> search[ 2.44 ] = 151.478(24.8369)
 #> 
-#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #1 Rep #1 pred log like = 693.635
-#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #2 Rep #1 pred log like = 727.913
-#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #3 Rep #1 pred log like = 856.461
-#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #4 Rep #1 pred log like = 872.549
-#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #5 Rep #1 pred log like = 757.603
-#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #6 Rep #1 pred log like = 752.132
-#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #7 Rep #1 pred log like = 777.303
-#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #8 Rep #1 pred log like = 670.918
-#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #9 Rep #1 pred log like = 778.714
-#> Running at Laplace(0.0895323) None  Grid-point #4 at 249.5 	Fold #10 Rep #1 pred log like = 958.294
-#> AvgPred = 784.552 with stdev = 83.2774
-#> Completed at 249.5
-#> Next point at 2495 with value 0 and continue = 1
-#> search[ 0.2495 ] = 784.551(83.2879)
-#> search[ 2.495 ] = 784.552(83.2805)
-#> search[ 24.95 ] = 784.552(83.2781)
-#> search[ 249.5 ] = 784.552(83.2774)
+#> Running at Laplace(28.6299) None  Grid-point #4 at 0.00244 	Fold #1 Rep #1 pred log like = 103.378
+#> Running at Laplace(28.6299) None  Grid-point #4 at 0.00244 	Fold #2 Rep #1 pred log like = 130.133
+#> Running at Laplace(28.6299) None  Grid-point #4 at 0.00244 	Fold #3 Rep #1 pred log like = 159.943
+#> Running at Laplace(28.6299) None  Grid-point #4 at 0.00244 	Fold #4 Rep #1 pred log like = 151.618
+#> Running at Laplace(28.6299) None  Grid-point #4 at 0.00244 	Fold #5 Rep #1 pred log like = 175.676
+#> Running at Laplace(28.6299) None  Grid-point #4 at 0.00244 	Fold #6 Rep #1 pred log like = 161.739
+#> Running at Laplace(28.6299) None  Grid-point #4 at 0.00244 	Fold #7 Rep #1 pred log like = 131.127
+#> Running at Laplace(28.6299) None  Grid-point #4 at 0.00244 	Fold #8 Rep #1 pred log like = 137.975
+#> Running at Laplace(28.6299) None  Grid-point #4 at 0.00244 	Fold #9 Rep #1 pred log like = 173.61
+#> Running at Laplace(28.6299) None  Grid-point #4 at 0.00244 	Fold #10 Rep #1 pred log like = 190.596
+#> AvgPred = 151.579 with stdev = 24.7953
+#> Completed at 0.00244
+#> Next point at 0.000244 with value 0 and continue = 1
+#> search[ 0.00244 ] = 151.579(24.7953)
+#> search[ 0.0244 ] = 151.544(24.8316)
+#> search[ 0.244 ] = 151.499(24.8369)
+#> search[ 2.44 ] = 151.478(24.8369)
 #> 
-#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #1 Rep #1 pred log like = 693.636
-#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #2 Rep #1 pred log like = 727.914
-#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #3 Rep #1 pred log like = 856.461
-#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #4 Rep #1 pred log like = 872.55
-#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #5 Rep #1 pred log like = 757.602
-#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #6 Rep #1 pred log like = 752.133
-#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #7 Rep #1 pred log like = 777.302
-#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #8 Rep #1 pred log like = 670.918
-#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #9 Rep #1 pred log like = 778.713
-#> Running at Laplace(0.0283126) None  Grid-point #5 at 2495 	Fold #10 Rep #1 pred log like = 958.294
-#> AvgPred = 784.552 with stdev = 83.2771
-#> Completed at 2495
-#> Next point at 146.811 with value 784.553 and continue = 0
-#> search[ 0.2495 ] = 784.551(83.2879)
-#> search[ 2.495 ] = 784.552(83.2805)
-#> search[ 24.95 ] = 784.552(83.2781)
-#> search[ 249.5 ] = 784.552(83.2774)
-#> search[ 2495 ] = 784.552(83.2771)
+#> Running at Laplace(90.5357) None  Grid-point #5 at 0.000244 	Fold #1 Rep #1 pred log like = 103.378
+#> Running at Laplace(90.5357) None  Grid-point #5 at 0.000244 	Fold #2 Rep #1 pred log like = 130.133
+#> Running at Laplace(90.5357) None  Grid-point #5 at 0.000244 	Fold #3 Rep #1 pred log like = 159.943
+#> Running at Laplace(90.5357) None  Grid-point #5 at 0.000244 	Fold #4 Rep #1 pred log like = 151.618
+#> Running at Laplace(90.5357) None  Grid-point #5 at 0.000244 	Fold #5 Rep #1 pred log like = 175.676
+#> Running at Laplace(90.5357) None  Grid-point #5 at 0.000244 	Fold #6 Rep #1 pred log like = 161.739
+#> Running at Laplace(90.5357) None  Grid-point #5 at 0.000244 	Fold #7 Rep #1 pred log like = 131.206
+#> Running at Laplace(90.5357) None  Grid-point #5 at 0.000244 	Fold #8 Rep #1 pred log like = 137.975
+#> Running at Laplace(90.5357) None  Grid-point #5 at 0.000244 	Fold #9 Rep #1 pred log like = 173.61
+#> Running at Laplace(90.5357) None  Grid-point #5 at 0.000244 	Fold #10 Rep #1 pred log like = 190.596
+#> AvgPred = 151.587 with stdev = 24.7888
+#> Completed at 0.000244
+#> Next point at 2.44e-05 with value 0 and continue = 1
+#> search[ 0.000244 ] = 151.587(24.7888)
+#> search[ 0.00244 ] = 151.579(24.7953)
+#> search[ 0.0244 ] = 151.544(24.8316)
+#> search[ 0.244 ] = 151.499(24.8369)
+#> search[ 2.44 ] = 151.478(24.8369)
 #> 
+#> Running at Laplace(286.299) None  Grid-point #6 at 2.44e-05 	Fold #1 Rep #1 pred log like = 103.378
+#> Running at Laplace(286.299) None  Grid-point #6 at 2.44e-05 	Fold #2 Rep #1 pred log like = 130.133
+#> Running at Laplace(286.299) None  Grid-point #6 at 2.44e-05 	Fold #3 Rep #1 pred log like = 159.943
+#> Running at Laplace(286.299) None  Grid-point #6 at 2.44e-05 	Fold #4 Rep #1 pred log like = 151.618
+#> Running at Laplace(286.299) None  Grid-point #6 at 2.44e-05 	Fold #5 Rep #1 pred log like = 175.676
+#> Running at Laplace(286.299) None  Grid-point #6 at 2.44e-05 	Fold #6 Rep #1 pred log like = 161.739
+#> Running at Laplace(286.299) None  Grid-point #6 at 2.44e-05 	Fold #7 Rep #1 pred log like = 131.206
+#> Running at Laplace(286.299) None  Grid-point #6 at 2.44e-05 	Fold #8 Rep #1 pred log like = 137.975
+#> Running at Laplace(286.299) None  Grid-point #6 at 2.44e-05 	Fold #9 Rep #1 pred log like = 173.61
+#> Running at Laplace(286.299) None  Grid-point #6 at 2.44e-05 	Fold #10 Rep #1 pred log like = 190.596
+#> AvgPred = 151.587 with stdev = 24.7888
+#> Completed at 2.44e-05
+#> Next point at 1.62865e-05 with value 151.591 and continue = 0
+#> search[ 2.44e-05 ] = 151.587(24.7888)
+#> search[ 0.000244 ] = 151.587(24.7888)
+#> search[ 0.00244 ] = 151.579(24.7953)
+#> search[ 0.0244 ] = 151.544(24.8316)
+#> search[ 0.244 ] = 151.499(24.8369)
+#> search[ 2.44 ] = 151.478(24.8369)
 #> 
-#> Maximum predicted log likelihood (784.553) estimated at:
-#> 	146.811 (variance)
-#> 	0.116718 (lambda)
+#> 
+#> Maximum predicted log likelihood (151.591) estimated at:
+#> 	1.62865e-05 (variance)
+#> 	350.43 (lambda)
 #> 
 #> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(0.116718) None 
+#> Using prior: Laplace(350.43) None 
 
 #Find out what the optimal hyperparameter was:
 getHyperParameter(fit)
-#> [1] 146.8106
+#> [1] 1.62865e-05
 
 #Extract the current log-likelihood, and coefficients
 logLik(fit)
-#> 'log Lik.' -2194.845 (df=3)
+#> 'log Lik.' -1858.348 (df=3)
 coef(fit)
 #> (Intercept)           1           2 
-#> -3.56117384  0.03211331 -0.01937822 
+#>   -4.261846    0.000000    0.000000 
 
 #We can only retrieve the confidence interval for unregularized coefficients:
 confint(fit, c(0))
 #> Using 1 thread(s)
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
 #>             covariate     2.5 %    97.5 % evaluations
-#> (Intercept)         0 -3.590514 -3.532095          22
+#> (Intercept)         0 -4.295195 -4.228855          24
diff --git a/docs/reference/createPrior.html b/docs/reference/createPrior.html index e8aaf3b1..77192583 100644 --- a/docs/reference/createPrior.html +++ b/docs/reference/createPrior.html @@ -120,7 +120,7 @@

Examples

#Generate some simulated data:
 sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                            model = "poisson")
-#> Sparseness = 76.2 %
+#> Sparseness = 76.6 %
 cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                     addIntercept = TRUE)
 #> Sorting covariates by covariateId and rowId
@@ -133,81 +133,190 @@ 
Examples

 #Fit the model
 fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
 #> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1698757934] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Performing 10-fold cross-validation [seed = 1698789248] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
 #> Using 1 thread(s)
-#> Starting var = 0.238 (default)
-#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #1 Rep #1 pred log like = 898.631
-#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #2 Rep #1 pred log like = 1378.61
-#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #3 Rep #1 pred log like = 1439.51
-#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #4 Rep #1 pred log like = 1227.83
-#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #5 Rep #1 pred log like = 1717.57
-#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #6 Rep #1 pred log like = 1272.34
-#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #7 Rep #1 pred log like = 1047.47
-#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #8 Rep #1 pred log like = 1266.38
-#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #9 Rep #1 pred log like = 1253.53
-#> Running at Laplace(2.89886) None  Grid-point #1 at 0.238 	Fold #10 Rep #1 pred log like = 1346.96
-#> AvgPred = 1284.88 with stdev = 208.341
-#> Completed at 0.238
-#> Next point at 2.38 with value 0 and continue = 1
-#> search[ 0.238 ] = 1284.88(208.341)
-#> 
-#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #1 Rep #1 pred log like = 898.623
-#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #2 Rep #1 pred log like = 1378.57
-#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #3 Rep #1 pred log like = 1439.49
-#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #4 Rep #1 pred log like = 1227.81
-#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #5 Rep #1 pred log like = 1717.55
-#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #6 Rep #1 pred log like = 1272.36
-#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #7 Rep #1 pred log like = 1047.55
-#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #8 Rep #1 pred log like = 1266.43
-#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #9 Rep #1 pred log like = 1253.54
-#> Running at Laplace(0.916698) None  Grid-point #2 at 2.38 	Fold #10 Rep #1 pred log like = 1346.91
-#> AvgPred = 1284.88 with stdev = 208.324
-#> Completed at 2.38
-#> Next point at 23.8 with value 0 and continue = 1
-#> search[ 0.238 ] = 1284.88(208.341)
-#> search[ 2.38 ] = 1284.88(208.324)
-#> 
-#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #1 Rep #1 pred log like = 898.62
-#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #2 Rep #1 pred log like = 1378.56
-#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #3 Rep #1 pred log like = 1439.48
-#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #4 Rep #1 pred log like = 1227.81
-#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #5 Rep #1 pred log like = 1717.54
-#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #6 Rep #1 pred log like = 1272.37
-#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #7 Rep #1 pred log like = 1047.58
-#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #8 Rep #1 pred log like = 1266.45
-#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #9 Rep #1 pred log like = 1253.54
-#> Running at Laplace(0.289886) None  Grid-point #3 at 23.8 	Fold #10 Rep #1 pred log like = 1346.9
-#> AvgPred = 1284.88 with stdev = 208.318
-#> Completed at 23.8
-#> Next point at 5.37835 with value 1284.88 and continue = 0
-#> search[ 0.238 ] = 1284.88(208.341)
-#> search[ 2.38 ] = 1284.88(208.324)
-#> search[ 23.8 ] = 1284.88(208.318)
-#> 
-#> 
-#> Maximum predicted log likelihood (1284.88) estimated at:
-#> 	5.37835 (variance)
-#> 	0.609804 (lambda)
+#> Starting var = 0.234 (default)
+#> Running at Laplace(2.92353) None  Grid-point #1 at 0.234 	Fold #1 Rep #1 pred log like = 600.677
+#> Running at Laplace(2.92353) None  Grid-point #1 at 0.234 	Fold #2 Rep #1 pred log like = 519.924
+#> Running at Laplace(2.92353) None  Grid-point #1 at 0.234 	Fold #3 Rep #1 pred log like = 621.534
+#> Running at Laplace(2.92353) None  Grid-point #1 at 0.234 	Fold #4 Rep #1 pred log like = 429.156
+#> Running at Laplace(2.92353) None  Grid-point #1 at 0.234 	Fold #5 Rep #1 pred log like = 455.987
+#> Running at Laplace(2.92353) None  Grid-point #1 at 0.234 	Fold #6 Rep #1 pred log like = 569.073
+#> Running at Laplace(2.92353) None  Grid-point #1 at 0.234 	Fold #7 Rep #1 pred log like = 445.111
+#> Running at Laplace(2.92353) None  Grid-point #1 at 0.234 	Fold #8 Rep #1 pred log like = 680.122
+#> Running at Laplace(2.92353) None  Grid-point #1 at 0.234 	Fold #9 Rep #1 pred log like = 513.724
+#> Running at Laplace(2.92353) None  Grid-point #1 at 0.234 	Fold #10 Rep #1 pred log like = 579.541
+#> AvgPred = 541.485 with stdev = 78.608
+#> Completed at 0.234
+#> Next point at 2.34 with value 0 and continue = 1
+#> search[ 0.234 ] = 541.485(78.608)
+#> 
+#> Running at Laplace(0.9245) None  Grid-point #2 at 2.34 	Fold #1 Rep #1 pred log like = 600.62
+#> Running at Laplace(0.9245) None  Grid-point #2 at 2.34 	Fold #2 Rep #1 pred log like = 519.914
+#> Running at Laplace(0.9245) None  Grid-point #2 at 2.34 	Fold #3 Rep #1 pred log like = 621.499
+#> Running at Laplace(0.9245) None  Grid-point #2 at 2.34 	Fold #4 Rep #1 pred log like = 429.072
+#> Running at Laplace(0.9245) None  Grid-point #2 at 2.34 	Fold #5 Rep #1 pred log like = 455.985
+#> Running at Laplace(0.9245) None  Grid-point #2 at 2.34 	Fold #6 Rep #1 pred log like = 569.055
+#> Running at Laplace(0.9245) None  Grid-point #2 at 2.34 	Fold #7 Rep #1 pred log like = 445.068
+#> Running at Laplace(0.9245) None  Grid-point #2 at 2.34 	Fold #8 Rep #1 pred log like = 680.096
+#> Running at Laplace(0.9245) None  Grid-point #2 at 2.34 	Fold #9 Rep #1 pred log like = 513.724
+#> Running at Laplace(0.9245) None  Grid-point #2 at 2.34 	Fold #10 Rep #1 pred log like = 579.472
+#> AvgPred = 541.45 with stdev = 78.6096
+#> Completed at 2.34
+#> Next point at 0.0234 with value 0 and continue = 1
+#> search[ 0.234 ] = 541.485(78.608)
+#> search[ 2.34 ] = 541.45(78.6096)
+#> 
+#> Running at Laplace(9.245) None  Grid-point #3 at 0.0234 	Fold #1 Rep #1 pred log like = 600.805
+#> Running at Laplace(9.245) None  Grid-point #3 at 0.0234 	Fold #2 Rep #1 pred log like = 519.924
+#> Running at Laplace(9.245) None  Grid-point #3 at 0.0234 	Fold #3 Rep #1 pred log like = 621.649
+#> Running at Laplace(9.245) None  Grid-point #3 at 0.0234 	Fold #4 Rep #1 pred log like = 429.416
+#> Running at Laplace(9.245) None  Grid-point #3 at 0.0234 	Fold #5 Rep #1 pred log like = 456.004
+#> Running at Laplace(9.245) None  Grid-point #3 at 0.0234 	Fold #6 Rep #1 pred log like = 569.073
+#> Running at Laplace(9.245) None  Grid-point #3 at 0.0234 	Fold #7 Rep #1 pred log like = 445.152
+#> Running at Laplace(9.245) None  Grid-point #3 at 0.0234 	Fold #8 Rep #1 pred log like = 680.134
+#> Running at Laplace(9.245) None  Grid-point #3 at 0.0234 	Fold #9 Rep #1 pred log like = 513.725
+#> Running at Laplace(9.245) None  Grid-point #3 at 0.0234 	Fold #10 Rep #1 pred log like = 579.753
+#> AvgPred = 541.564 with stdev = 78.598
+#> Completed at 0.0234
+#> Next point at 0.00234 with value 0 and continue = 1
+#> search[ 0.0234 ] = 541.564(78.598)
+#> search[ 0.234 ] = 541.485(78.608)
+#> search[ 2.34 ] = 541.45(78.6096)
+#> 
+#> Running at Laplace(29.2353) None  Grid-point #4 at 0.00234 	Fold #1 Rep #1 pred log like = 600.805
+#> Running at Laplace(29.2353) None  Grid-point #4 at 0.00234 	Fold #2 Rep #1 pred log like = 519.924
+#> Running at Laplace(29.2353) None  Grid-point #4 at 0.00234 	Fold #3 Rep #1 pred log like = 621.874
+#> Running at Laplace(29.2353) None  Grid-point #4 at 0.00234 	Fold #4 Rep #1 pred log like = 430.035
+#> Running at Laplace(29.2353) None  Grid-point #4 at 0.00234 	Fold #5 Rep #1 pred log like = 456.006
+#> Running at Laplace(29.2353) None  Grid-point #4 at 0.00234 	Fold #6 Rep #1 pred log like = 569.073
+#> Running at Laplace(29.2353) None  Grid-point #4 at 0.00234 	Fold #7 Rep #1 pred log like = 445.152
+#> Running at Laplace(29.2353) None  Grid-point #4 at 0.00234 	Fold #8 Rep #1 pred log like = 680.134
+#> Running at Laplace(29.2353) None  Grid-point #4 at 0.00234 	Fold #9 Rep #1 pred log like = 513.725
+#> Running at Laplace(29.2353) None  Grid-point #4 at 0.00234 	Fold #10 Rep #1 pred log like = 580.157
+#> AvgPred = 541.688 with stdev = 78.5522
+#> Completed at 0.00234
+#> Next point at 0.000234 with value 0 and continue = 1
+#> search[ 0.00234 ] = 541.688(78.5522)
+#> search[ 0.0234 ] = 541.564(78.598)
+#> search[ 0.234 ] = 541.485(78.608)
+#> search[ 2.34 ] = 541.45(78.6096)
+#> 
+#> Running at Laplace(92.45) None  Grid-point #5 at 0.000234 	Fold #1 Rep #1 pred log like = 600.805
+#> Running at Laplace(92.45) None  Grid-point #5 at 0.000234 	Fold #2 Rep #1 pred log like = 519.924
+#> Running at Laplace(92.45) None  Grid-point #5 at 0.000234 	Fold #3 Rep #1 pred log like = 621.874
+#> Running at Laplace(92.45) None  Grid-point #5 at 0.000234 	Fold #4 Rep #1 pred log like = 430.035
+#> Running at Laplace(92.45) None  Grid-point #5 at 0.000234 	Fold #5 Rep #1 pred log like = 456.006
+#> Running at Laplace(92.45) None  Grid-point #5 at 0.000234 	Fold #6 Rep #1 pred log like = 569.073
+#> Running at Laplace(92.45) None  Grid-point #5 at 0.000234 	Fold #7 Rep #1 pred log like = 445.152
+#> Running at Laplace(92.45) None  Grid-point #5 at 0.000234 	Fold #8 Rep #1 pred log like = 680.134
+#> Running at Laplace(92.45) None  Grid-point #5 at 0.000234 	Fold #9 Rep #1 pred log like = 513.725
+#> Running at Laplace(92.45) None  Grid-point #5 at 0.000234 	Fold #10 Rep #1 pred log like = 580.157
+#> AvgPred = 541.688 with stdev = 78.5522
+#> Completed at 0.000234
+#> Next point at 3.23147e-23 with value 542.287 and continue = 0
+#> search[ 0.000234 ] = 541.688(78.5522)
+#> search[ 0.00234 ] = 541.688(78.5522)
+#> search[ 0.0234 ] = 541.564(78.598)
+#> search[ 0.234 ] = 541.485(78.608)
+#> search[ 2.34 ] = 541.45(78.6096)
+#> 
+#> 
+#> Maximum predicted log likelihood (542.287) estimated at:
+#> 	3.23147e-23 (variance)
+#> 	2.4878e+11 (lambda)
 #> 
 #> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(0.609804) None 
+#> Using prior: Laplace(2.4878e+11) None 
 
 #Find out what the optimal hyperparameter was:
 getHyperParameter(fit)
-#> [1] 5.37835
+#> [1] 3.231474e-23
 
 #Extract the current log-likelihood, and coefficients
 logLik(fit)
-#> 'log Lik.' -2158.207 (df=3)
+#> 'log Lik.' -2122.09 (df=3)
 coef(fit)
 #> (Intercept)           1           2 
-#> -3.92974607 -0.02127371  1.41692709 
+#>   -3.777662    0.000000    0.000000 
 
 #We can only retrieve the confidence interval for unregularized coefficients:
 confint(fit, c(0))
 #> Using 1 thread(s)
-#>             covariate     2.5 %  97.5 % evaluations
-#> (Intercept)         0 -3.962925 -3.8969          22
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#> 
+#> Warning: BLR gradient is ill-conditioned
+#> Enforcing convergence!
+#>             covariate     2.5 %    97.5 % evaluations
+#> (Intercept)         0 -3.803731 -3.751804          24
diff --git a/docs/reference/getHyperParameter.html b/docs/reference/getHyperParameter.html index 961106f3..72672f11 100644 --- a/docs/reference/getHyperParameter.html +++ b/docs/reference/getHyperParameter.html @@ -71,7 +71,7 @@

Examples

#Generate some simulated data:
 sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                            model = "poisson")
-#> Sparseness = 73.85 %
+#> Sparseness = 76.45 %
 cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                     addIntercept = TRUE)
 #> Sorting covariates by covariateId and rowId
@@ -84,594 +84,594 @@ 
Examples

 #Fit the model
 fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
 #> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1698757937] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Performing 10-fold cross-validation [seed = 1698789251] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
 #> Using 1 thread(s)
-#> Starting var = 0.2615 (default)
-#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #1 Rep #1 pred log like = 372.484
-#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #2 Rep #1 pred log like = 427.249
-#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #3 Rep #1 pred log like = 468.957
-#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #4 Rep #1 pred log like = 505.492
-#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #5 Rep #1 pred log like = 364.273
-#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #6 Rep #1 pred log like = 433.21
-#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #7 Rep #1 pred log like = 443.256
-#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #8 Rep #1 pred log like = 438.388
-#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #9 Rep #1 pred log like = 475.904
-#> Running at Laplace(2.76553) None  Grid-point #1 at 0.2615 	Fold #10 Rep #1 pred log like = 470.303
-#> AvgPred = 439.952 with stdev = 42.2492
-#> Completed at 0.2615
-#> Next point at 2.615 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
+#> Starting var = 0.2355 (default)
+#> Running at Laplace(2.9142) None  Grid-point #1 at 0.2355 	Fold #1 Rep #1 pred log like = 1071.67
+#> Running at Laplace(2.9142) None  Grid-point #1 at 0.2355 	Fold #2 Rep #1 pred log like = 887.72
+#> Running at Laplace(2.9142) None  Grid-point #1 at 0.2355 	Fold #3 Rep #1 pred log like = 989.777
+#> Running at Laplace(2.9142) None  Grid-point #1 at 0.2355 	Fold #4 Rep #1 pred log like = 1248.9
+#> Running at Laplace(2.9142) None  Grid-point #1 at 0.2355 	Fold #5 Rep #1 pred log like = 1083.64
+#> Running at Laplace(2.9142) None  Grid-point #1 at 0.2355 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(2.9142) None  Grid-point #1 at 0.2355 	Fold #7 Rep #1 pred log like = 1009.42
+#> Running at Laplace(2.9142) None  Grid-point #1 at 0.2355 	Fold #8 Rep #1 pred log like = 927.842
+#> Running at Laplace(2.9142) None  Grid-point #1 at 0.2355 	Fold #9 Rep #1 pred log like = 1098.02
+#> Running at Laplace(2.9142) None  Grid-point #1 at 0.2355 	Fold #10 Rep #1 pred log like = 1089.69
+#> AvgPred = 1049.11 with stdev = 96.3088
+#> Completed at 0.2355
+#> Next point at 2.355 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
 #> 
-#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #1 Rep #1 pred log like = 372.478
-#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #2 Rep #1 pred log like = 427.302
-#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #3 Rep #1 pred log like = 468.968
-#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #4 Rep #1 pred log like = 505.462
-#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #5 Rep #1 pred log like = 364.28
-#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #6 Rep #1 pred log like = 433.206
-#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #7 Rep #1 pred log like = 443.204
-#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #8 Rep #1 pred log like = 438.398
-#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #9 Rep #1 pred log like = 475.914
-#> Running at Laplace(0.874539) None  Grid-point #2 at 2.615 	Fold #10 Rep #1 pred log like = 470.313
-#> AvgPred = 439.952 with stdev = 42.2447
-#> Completed at 2.615
-#> Next point at 26.15 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
+#> Running at Laplace(0.921551) None  Grid-point #2 at 2.355 	Fold #1 Rep #1 pred log like = 1071.67
+#> Running at Laplace(0.921551) None  Grid-point #2 at 2.355 	Fold #2 Rep #1 pred log like = 887.711
+#> Running at Laplace(0.921551) None  Grid-point #2 at 2.355 	Fold #3 Rep #1 pred log like = 989.76
+#> Running at Laplace(0.921551) None  Grid-point #2 at 2.355 	Fold #4 Rep #1 pred log like = 1248.86
+#> Running at Laplace(0.921551) None  Grid-point #2 at 2.355 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(0.921551) None  Grid-point #2 at 2.355 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(0.921551) None  Grid-point #2 at 2.355 	Fold #7 Rep #1 pred log like = 1009.42
+#> Running at Laplace(0.921551) None  Grid-point #2 at 2.355 	Fold #8 Rep #1 pred log like = 927.82
+#> Running at Laplace(0.921551) None  Grid-point #2 at 2.355 	Fold #9 Rep #1 pred log like = 1098
+#> Running at Laplace(0.921551) None  Grid-point #2 at 2.355 	Fold #10 Rep #1 pred log like = 1089.79
+#> AvgPred = 1049.11 with stdev = 96.3073
+#> Completed at 2.355
+#> Next point at 23.55 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
 #> 
-#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #2 Rep #1 pred log like = 427.318
-#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #3 Rep #1 pred log like = 468.971
-#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #4 Rep #1 pred log like = 505.453
-#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #5 Rep #1 pred log like = 364.282
-#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #6 Rep #1 pred log like = 433.205
-#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #7 Rep #1 pred log like = 443.188
-#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #8 Rep #1 pred log like = 438.4
-#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #9 Rep #1 pred log like = 475.917
-#> Running at Laplace(0.276553) None  Grid-point #3 at 26.15 	Fold #10 Rep #1 pred log like = 470.316
-#> AvgPred = 439.953 with stdev = 42.243
-#> Completed at 26.15
-#> Next point at 261.5 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
+#> Running at Laplace(0.29142) None  Grid-point #3 at 23.55 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(0.29142) None  Grid-point #3 at 23.55 	Fold #2 Rep #1 pred log like = 887.709
+#> Running at Laplace(0.29142) None  Grid-point #3 at 23.55 	Fold #3 Rep #1 pred log like = 989.755
+#> Running at Laplace(0.29142) None  Grid-point #3 at 23.55 	Fold #4 Rep #1 pred log like = 1248.84
+#> Running at Laplace(0.29142) None  Grid-point #3 at 23.55 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(0.29142) None  Grid-point #3 at 23.55 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(0.29142) None  Grid-point #3 at 23.55 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(0.29142) None  Grid-point #3 at 23.55 	Fold #8 Rep #1 pred log like = 927.813
+#> Running at Laplace(0.29142) None  Grid-point #3 at 23.55 	Fold #9 Rep #1 pred log like = 1097.99
+#> Running at Laplace(0.29142) None  Grid-point #3 at 23.55 	Fold #10 Rep #1 pred log like = 1089.83
+#> AvgPred = 1049.11 with stdev = 96.3071
+#> Completed at 23.55
+#> Next point at 235.5 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
 #> 
-#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #2 Rep #1 pred log like = 427.323
-#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #4 Rep #1 pred log like = 505.45
-#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #5 Rep #1 pred log like = 364.282
-#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #7 Rep #1 pred log like = 443.182
-#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #8 Rep #1 pred log like = 438.401
-#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #9 Rep #1 pred log like = 475.917
-#> Running at Laplace(0.0874539) None  Grid-point #4 at 261.5 	Fold #10 Rep #1 pred log like = 470.317
-#> AvgPred = 439.953 with stdev = 42.2425
-#> Completed at 261.5
-#> Next point at 2615 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
+#> Running at Laplace(0.0921551) None  Grid-point #4 at 235.5 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(0.0921551) None  Grid-point #4 at 235.5 	Fold #2 Rep #1 pred log like = 887.708
+#> Running at Laplace(0.0921551) None  Grid-point #4 at 235.5 	Fold #3 Rep #1 pred log like = 989.753
+#> Running at Laplace(0.0921551) None  Grid-point #4 at 235.5 	Fold #4 Rep #1 pred log like = 1248.84
+#> Running at Laplace(0.0921551) None  Grid-point #4 at 235.5 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(0.0921551) None  Grid-point #4 at 235.5 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(0.0921551) None  Grid-point #4 at 235.5 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(0.0921551) None  Grid-point #4 at 235.5 	Fold #8 Rep #1 pred log like = 927.81
+#> Running at Laplace(0.0921551) None  Grid-point #4 at 235.5 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(0.0921551) None  Grid-point #4 at 235.5 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 235.5
+#> Next point at 2355 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #4 Rep #1 pred log like = 505.449
-#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #5 Rep #1 pred log like = 364.282
-#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #7 Rep #1 pred log like = 443.181
-#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(0.0276553) None  Grid-point #5 at 2615 	Fold #10 Rep #1 pred log like = 470.317
-#> AvgPred = 439.953 with stdev = 42.2423
-#> Completed at 2615
-#> Next point at 26150 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
+#> Running at Laplace(0.029142) None  Grid-point #5 at 2355 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(0.029142) None  Grid-point #5 at 2355 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(0.029142) None  Grid-point #5 at 2355 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(0.029142) None  Grid-point #5 at 2355 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(0.029142) None  Grid-point #5 at 2355 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(0.029142) None  Grid-point #5 at 2355 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(0.029142) None  Grid-point #5 at 2355 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(0.029142) None  Grid-point #5 at 2355 	Fold #8 Rep #1 pred log like = 927.81
+#> Running at Laplace(0.029142) None  Grid-point #5 at 2355 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(0.029142) None  Grid-point #5 at 2355 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2355
+#> Next point at 23550 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #4 Rep #1 pred log like = 505.449
-#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(0.00874539) None  Grid-point #6 at 26150 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2423
-#> Completed at 26150
-#> Next point at 261500 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
+#> Running at Laplace(0.00921551) None  Grid-point #6 at 23550 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(0.00921551) None  Grid-point #6 at 23550 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(0.00921551) None  Grid-point #6 at 23550 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(0.00921551) None  Grid-point #6 at 23550 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(0.00921551) None  Grid-point #6 at 23550 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(0.00921551) None  Grid-point #6 at 23550 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(0.00921551) None  Grid-point #6 at 23550 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(0.00921551) None  Grid-point #6 at 23550 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(0.00921551) None  Grid-point #6 at 23550 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(0.00921551) None  Grid-point #6 at 23550 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 23550
+#> Next point at 235500 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(0.00276553) None  Grid-point #7 at 261500 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 261500
-#> Next point at 2.615e+06 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
+#> Running at Laplace(0.0029142) None  Grid-point #7 at 235500 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(0.0029142) None  Grid-point #7 at 235500 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(0.0029142) None  Grid-point #7 at 235500 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(0.0029142) None  Grid-point #7 at 235500 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(0.0029142) None  Grid-point #7 at 235500 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(0.0029142) None  Grid-point #7 at 235500 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(0.0029142) None  Grid-point #7 at 235500 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(0.0029142) None  Grid-point #7 at 235500 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(0.0029142) None  Grid-point #7 at 235500 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(0.0029142) None  Grid-point #7 at 235500 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 235500
+#> Next point at 2.355e+06 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(0.000874539) None  Grid-point #8 at 2.615e+06 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+06
-#> Next point at 2.615e+07 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
+#> Running at Laplace(0.000921551) None  Grid-point #8 at 2.355e+06 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(0.000921551) None  Grid-point #8 at 2.355e+06 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(0.000921551) None  Grid-point #8 at 2.355e+06 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(0.000921551) None  Grid-point #8 at 2.355e+06 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(0.000921551) None  Grid-point #8 at 2.355e+06 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(0.000921551) None  Grid-point #8 at 2.355e+06 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(0.000921551) None  Grid-point #8 at 2.355e+06 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(0.000921551) None  Grid-point #8 at 2.355e+06 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(0.000921551) None  Grid-point #8 at 2.355e+06 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(0.000921551) None  Grid-point #8 at 2.355e+06 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+06
+#> Next point at 2.355e+07 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(0.000276553) None  Grid-point #9 at 2.615e+07 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+07
-#> Next point at 2.615e+08 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
+#> Running at Laplace(0.00029142) None  Grid-point #9 at 2.355e+07 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(0.00029142) None  Grid-point #9 at 2.355e+07 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(0.00029142) None  Grid-point #9 at 2.355e+07 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(0.00029142) None  Grid-point #9 at 2.355e+07 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(0.00029142) None  Grid-point #9 at 2.355e+07 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(0.00029142) None  Grid-point #9 at 2.355e+07 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(0.00029142) None  Grid-point #9 at 2.355e+07 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(0.00029142) None  Grid-point #9 at 2.355e+07 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(0.00029142) None  Grid-point #9 at 2.355e+07 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(0.00029142) None  Grid-point #9 at 2.355e+07 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+07
+#> Next point at 2.355e+08 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(8.74539e-05) None  Grid-point #10 at 2.615e+08 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+08
-#> Next point at 2.615e+09 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
+#> Running at Laplace(9.21551e-05) None  Grid-point #10 at 2.355e+08 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(9.21551e-05) None  Grid-point #10 at 2.355e+08 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(9.21551e-05) None  Grid-point #10 at 2.355e+08 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(9.21551e-05) None  Grid-point #10 at 2.355e+08 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(9.21551e-05) None  Grid-point #10 at 2.355e+08 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(9.21551e-05) None  Grid-point #10 at 2.355e+08 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(9.21551e-05) None  Grid-point #10 at 2.355e+08 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(9.21551e-05) None  Grid-point #10 at 2.355e+08 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(9.21551e-05) None  Grid-point #10 at 2.355e+08 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(9.21551e-05) None  Grid-point #10 at 2.355e+08 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+08
+#> Next point at 2.355e+09 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(2.76553e-05) None  Grid-point #11 at 2.615e+09 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+09
-#> Next point at 2.615e+10 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
+#> Running at Laplace(2.9142e-05) None  Grid-point #11 at 2.355e+09 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(2.9142e-05) None  Grid-point #11 at 2.355e+09 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(2.9142e-05) None  Grid-point #11 at 2.355e+09 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(2.9142e-05) None  Grid-point #11 at 2.355e+09 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(2.9142e-05) None  Grid-point #11 at 2.355e+09 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(2.9142e-05) None  Grid-point #11 at 2.355e+09 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(2.9142e-05) None  Grid-point #11 at 2.355e+09 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(2.9142e-05) None  Grid-point #11 at 2.355e+09 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(2.9142e-05) None  Grid-point #11 at 2.355e+09 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(2.9142e-05) None  Grid-point #11 at 2.355e+09 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+09
+#> Next point at 2.355e+10 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(8.74539e-06) None  Grid-point #12 at 2.615e+10 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+10
-#> Next point at 2.615e+11 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
-#> search[ 2.615e+10 ] = 439.953(42.2422)
+#> Running at Laplace(9.21551e-06) None  Grid-point #12 at 2.355e+10 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(9.21551e-06) None  Grid-point #12 at 2.355e+10 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(9.21551e-06) None  Grid-point #12 at 2.355e+10 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(9.21551e-06) None  Grid-point #12 at 2.355e+10 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(9.21551e-06) None  Grid-point #12 at 2.355e+10 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(9.21551e-06) None  Grid-point #12 at 2.355e+10 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(9.21551e-06) None  Grid-point #12 at 2.355e+10 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(9.21551e-06) None  Grid-point #12 at 2.355e+10 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(9.21551e-06) None  Grid-point #12 at 2.355e+10 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(9.21551e-06) None  Grid-point #12 at 2.355e+10 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+10
+#> Next point at 2.355e+11 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
+#> search[ 2.355e+10 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(2.76553e-06) None  Grid-point #13 at 2.615e+11 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+11
-#> Next point at 2.615e+12 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
-#> search[ 2.615e+10 ] = 439.953(42.2422)
-#> search[ 2.615e+11 ] = 439.953(42.2422)
+#> Running at Laplace(2.9142e-06) None  Grid-point #13 at 2.355e+11 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(2.9142e-06) None  Grid-point #13 at 2.355e+11 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(2.9142e-06) None  Grid-point #13 at 2.355e+11 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(2.9142e-06) None  Grid-point #13 at 2.355e+11 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(2.9142e-06) None  Grid-point #13 at 2.355e+11 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(2.9142e-06) None  Grid-point #13 at 2.355e+11 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(2.9142e-06) None  Grid-point #13 at 2.355e+11 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(2.9142e-06) None  Grid-point #13 at 2.355e+11 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(2.9142e-06) None  Grid-point #13 at 2.355e+11 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(2.9142e-06) None  Grid-point #13 at 2.355e+11 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+11
+#> Next point at 2.355e+12 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
+#> search[ 2.355e+10 ] = 1049.11(96.307)
+#> search[ 2.355e+11 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(8.74539e-07) None  Grid-point #14 at 2.615e+12 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+12
-#> Next point at 2.615e+13 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
-#> search[ 2.615e+10 ] = 439.953(42.2422)
-#> search[ 2.615e+11 ] = 439.953(42.2422)
-#> search[ 2.615e+12 ] = 439.953(42.2422)
+#> Running at Laplace(9.21551e-07) None  Grid-point #14 at 2.355e+12 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(9.21551e-07) None  Grid-point #14 at 2.355e+12 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(9.21551e-07) None  Grid-point #14 at 2.355e+12 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(9.21551e-07) None  Grid-point #14 at 2.355e+12 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(9.21551e-07) None  Grid-point #14 at 2.355e+12 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(9.21551e-07) None  Grid-point #14 at 2.355e+12 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(9.21551e-07) None  Grid-point #14 at 2.355e+12 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(9.21551e-07) None  Grid-point #14 at 2.355e+12 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(9.21551e-07) None  Grid-point #14 at 2.355e+12 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(9.21551e-07) None  Grid-point #14 at 2.355e+12 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+12
+#> Next point at 2.355e+13 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
+#> search[ 2.355e+10 ] = 1049.11(96.307)
+#> search[ 2.355e+11 ] = 1049.11(96.307)
+#> search[ 2.355e+12 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(2.76553e-07) None  Grid-point #15 at 2.615e+13 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+13
-#> Next point at 2.615e+14 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
-#> search[ 2.615e+10 ] = 439.953(42.2422)
-#> search[ 2.615e+11 ] = 439.953(42.2422)
-#> search[ 2.615e+12 ] = 439.953(42.2422)
-#> search[ 2.615e+13 ] = 439.953(42.2422)
+#> Running at Laplace(2.9142e-07) None  Grid-point #15 at 2.355e+13 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(2.9142e-07) None  Grid-point #15 at 2.355e+13 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(2.9142e-07) None  Grid-point #15 at 2.355e+13 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(2.9142e-07) None  Grid-point #15 at 2.355e+13 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(2.9142e-07) None  Grid-point #15 at 2.355e+13 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(2.9142e-07) None  Grid-point #15 at 2.355e+13 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(2.9142e-07) None  Grid-point #15 at 2.355e+13 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(2.9142e-07) None  Grid-point #15 at 2.355e+13 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(2.9142e-07) None  Grid-point #15 at 2.355e+13 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(2.9142e-07) None  Grid-point #15 at 2.355e+13 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+13
+#> Next point at 2.355e+14 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
+#> search[ 2.355e+10 ] = 1049.11(96.307)
+#> search[ 2.355e+11 ] = 1049.11(96.307)
+#> search[ 2.355e+12 ] = 1049.11(96.307)
+#> search[ 2.355e+13 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(8.74539e-08) None  Grid-point #16 at 2.615e+14 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+14
-#> Next point at 2.615e+15 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
-#> search[ 2.615e+10 ] = 439.953(42.2422)
-#> search[ 2.615e+11 ] = 439.953(42.2422)
-#> search[ 2.615e+12 ] = 439.953(42.2422)
-#> search[ 2.615e+13 ] = 439.953(42.2422)
-#> search[ 2.615e+14 ] = 439.953(42.2422)
+#> Running at Laplace(9.21551e-08) None  Grid-point #16 at 2.355e+14 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(9.21551e-08) None  Grid-point #16 at 2.355e+14 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(9.21551e-08) None  Grid-point #16 at 2.355e+14 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(9.21551e-08) None  Grid-point #16 at 2.355e+14 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(9.21551e-08) None  Grid-point #16 at 2.355e+14 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(9.21551e-08) None  Grid-point #16 at 2.355e+14 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(9.21551e-08) None  Grid-point #16 at 2.355e+14 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(9.21551e-08) None  Grid-point #16 at 2.355e+14 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(9.21551e-08) None  Grid-point #16 at 2.355e+14 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(9.21551e-08) None  Grid-point #16 at 2.355e+14 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+14
+#> Next point at 2.355e+15 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
+#> search[ 2.355e+10 ] = 1049.11(96.307)
+#> search[ 2.355e+11 ] = 1049.11(96.307)
+#> search[ 2.355e+12 ] = 1049.11(96.307)
+#> search[ 2.355e+13 ] = 1049.11(96.307)
+#> search[ 2.355e+14 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(2.76553e-08) None  Grid-point #17 at 2.615e+15 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+15
-#> Next point at 2.615e+16 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
-#> search[ 2.615e+10 ] = 439.953(42.2422)
-#> search[ 2.615e+11 ] = 439.953(42.2422)
-#> search[ 2.615e+12 ] = 439.953(42.2422)
-#> search[ 2.615e+13 ] = 439.953(42.2422)
-#> search[ 2.615e+14 ] = 439.953(42.2422)
-#> search[ 2.615e+15 ] = 439.953(42.2422)
+#> Running at Laplace(2.9142e-08) None  Grid-point #17 at 2.355e+15 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(2.9142e-08) None  Grid-point #17 at 2.355e+15 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(2.9142e-08) None  Grid-point #17 at 2.355e+15 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(2.9142e-08) None  Grid-point #17 at 2.355e+15 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(2.9142e-08) None  Grid-point #17 at 2.355e+15 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(2.9142e-08) None  Grid-point #17 at 2.355e+15 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(2.9142e-08) None  Grid-point #17 at 2.355e+15 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(2.9142e-08) None  Grid-point #17 at 2.355e+15 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(2.9142e-08) None  Grid-point #17 at 2.355e+15 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(2.9142e-08) None  Grid-point #17 at 2.355e+15 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+15
+#> Next point at 2.355e+16 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
+#> search[ 2.355e+10 ] = 1049.11(96.307)
+#> search[ 2.355e+11 ] = 1049.11(96.307)
+#> search[ 2.355e+12 ] = 1049.11(96.307)
+#> search[ 2.355e+13 ] = 1049.11(96.307)
+#> search[ 2.355e+14 ] = 1049.11(96.307)
+#> search[ 2.355e+15 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(8.74539e-09) None  Grid-point #18 at 2.615e+16 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+16
-#> Next point at 2.615e+17 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
-#> search[ 2.615e+10 ] = 439.953(42.2422)
-#> search[ 2.615e+11 ] = 439.953(42.2422)
-#> search[ 2.615e+12 ] = 439.953(42.2422)
-#> search[ 2.615e+13 ] = 439.953(42.2422)
-#> search[ 2.615e+14 ] = 439.953(42.2422)
-#> search[ 2.615e+15 ] = 439.953(42.2422)
-#> search[ 2.615e+16 ] = 439.953(42.2422)
+#> Running at Laplace(9.21551e-09) None  Grid-point #18 at 2.355e+16 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(9.21551e-09) None  Grid-point #18 at 2.355e+16 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(9.21551e-09) None  Grid-point #18 at 2.355e+16 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(9.21551e-09) None  Grid-point #18 at 2.355e+16 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(9.21551e-09) None  Grid-point #18 at 2.355e+16 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(9.21551e-09) None  Grid-point #18 at 2.355e+16 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(9.21551e-09) None  Grid-point #18 at 2.355e+16 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(9.21551e-09) None  Grid-point #18 at 2.355e+16 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(9.21551e-09) None  Grid-point #18 at 2.355e+16 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(9.21551e-09) None  Grid-point #18 at 2.355e+16 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+16
+#> Next point at 2.355e+17 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
+#> search[ 2.355e+10 ] = 1049.11(96.307)
+#> search[ 2.355e+11 ] = 1049.11(96.307)
+#> search[ 2.355e+12 ] = 1049.11(96.307)
+#> search[ 2.355e+13 ] = 1049.11(96.307)
+#> search[ 2.355e+14 ] = 1049.11(96.307)
+#> search[ 2.355e+15 ] = 1049.11(96.307)
+#> search[ 2.355e+16 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(2.76553e-09) None  Grid-point #19 at 2.615e+17 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+17
-#> Next point at 2.615e+18 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
-#> search[ 2.615e+10 ] = 439.953(42.2422)
-#> search[ 2.615e+11 ] = 439.953(42.2422)
-#> search[ 2.615e+12 ] = 439.953(42.2422)
-#> search[ 2.615e+13 ] = 439.953(42.2422)
-#> search[ 2.615e+14 ] = 439.953(42.2422)
-#> search[ 2.615e+15 ] = 439.953(42.2422)
-#> search[ 2.615e+16 ] = 439.953(42.2422)
-#> search[ 2.615e+17 ] = 439.953(42.2422)
+#> Running at Laplace(2.9142e-09) None  Grid-point #19 at 2.355e+17 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(2.9142e-09) None  Grid-point #19 at 2.355e+17 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(2.9142e-09) None  Grid-point #19 at 2.355e+17 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(2.9142e-09) None  Grid-point #19 at 2.355e+17 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(2.9142e-09) None  Grid-point #19 at 2.355e+17 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(2.9142e-09) None  Grid-point #19 at 2.355e+17 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(2.9142e-09) None  Grid-point #19 at 2.355e+17 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(2.9142e-09) None  Grid-point #19 at 2.355e+17 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(2.9142e-09) None  Grid-point #19 at 2.355e+17 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(2.9142e-09) None  Grid-point #19 at 2.355e+17 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+17
+#> Next point at 2.355e+18 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
+#> search[ 2.355e+10 ] = 1049.11(96.307)
+#> search[ 2.355e+11 ] = 1049.11(96.307)
+#> search[ 2.355e+12 ] = 1049.11(96.307)
+#> search[ 2.355e+13 ] = 1049.11(96.307)
+#> search[ 2.355e+14 ] = 1049.11(96.307)
+#> search[ 2.355e+15 ] = 1049.11(96.307)
+#> search[ 2.355e+16 ] = 1049.11(96.307)
+#> search[ 2.355e+17 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(8.74539e-10) None  Grid-point #20 at 2.615e+18 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+18
-#> Next point at 2.615e+19 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
-#> search[ 2.615e+10 ] = 439.953(42.2422)
-#> search[ 2.615e+11 ] = 439.953(42.2422)
-#> search[ 2.615e+12 ] = 439.953(42.2422)
-#> search[ 2.615e+13 ] = 439.953(42.2422)
-#> search[ 2.615e+14 ] = 439.953(42.2422)
-#> search[ 2.615e+15 ] = 439.953(42.2422)
-#> search[ 2.615e+16 ] = 439.953(42.2422)
-#> search[ 2.615e+17 ] = 439.953(42.2422)
-#> search[ 2.615e+18 ] = 439.953(42.2422)
+#> Running at Laplace(9.21551e-10) None  Grid-point #20 at 2.355e+18 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(9.21551e-10) None  Grid-point #20 at 2.355e+18 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(9.21551e-10) None  Grid-point #20 at 2.355e+18 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(9.21551e-10) None  Grid-point #20 at 2.355e+18 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(9.21551e-10) None  Grid-point #20 at 2.355e+18 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(9.21551e-10) None  Grid-point #20 at 2.355e+18 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(9.21551e-10) None  Grid-point #20 at 2.355e+18 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(9.21551e-10) None  Grid-point #20 at 2.355e+18 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(9.21551e-10) None  Grid-point #20 at 2.355e+18 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(9.21551e-10) None  Grid-point #20 at 2.355e+18 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+18
+#> Next point at 2.355e+19 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
+#> search[ 2.355e+10 ] = 1049.11(96.307)
+#> search[ 2.355e+11 ] = 1049.11(96.307)
+#> search[ 2.355e+12 ] = 1049.11(96.307)
+#> search[ 2.355e+13 ] = 1049.11(96.307)
+#> search[ 2.355e+14 ] = 1049.11(96.307)
+#> search[ 2.355e+15 ] = 1049.11(96.307)
+#> search[ 2.355e+16 ] = 1049.11(96.307)
+#> search[ 2.355e+17 ] = 1049.11(96.307)
+#> search[ 2.355e+18 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(2.76553e-10) None  Grid-point #21 at 2.615e+19 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+19
-#> Next point at 2.615e+20 with value 0 and continue = 1
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
-#> search[ 2.615e+10 ] = 439.953(42.2422)
-#> search[ 2.615e+11 ] = 439.953(42.2422)
-#> search[ 2.615e+12 ] = 439.953(42.2422)
-#> search[ 2.615e+13 ] = 439.953(42.2422)
-#> search[ 2.615e+14 ] = 439.953(42.2422)
-#> search[ 2.615e+15 ] = 439.953(42.2422)
-#> search[ 2.615e+16 ] = 439.953(42.2422)
-#> search[ 2.615e+17 ] = 439.953(42.2422)
-#> search[ 2.615e+18 ] = 439.953(42.2422)
-#> search[ 2.615e+19 ] = 439.953(42.2422)
+#> Running at Laplace(2.9142e-10) None  Grid-point #21 at 2.355e+19 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(2.9142e-10) None  Grid-point #21 at 2.355e+19 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(2.9142e-10) None  Grid-point #21 at 2.355e+19 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(2.9142e-10) None  Grid-point #21 at 2.355e+19 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(2.9142e-10) None  Grid-point #21 at 2.355e+19 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(2.9142e-10) None  Grid-point #21 at 2.355e+19 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(2.9142e-10) None  Grid-point #21 at 2.355e+19 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(2.9142e-10) None  Grid-point #21 at 2.355e+19 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(2.9142e-10) None  Grid-point #21 at 2.355e+19 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(2.9142e-10) None  Grid-point #21 at 2.355e+19 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+19
+#> Next point at 2.355e+20 with value 0 and continue = 1
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
+#> search[ 2.355e+10 ] = 1049.11(96.307)
+#> search[ 2.355e+11 ] = 1049.11(96.307)
+#> search[ 2.355e+12 ] = 1049.11(96.307)
+#> search[ 2.355e+13 ] = 1049.11(96.307)
+#> search[ 2.355e+14 ] = 1049.11(96.307)
+#> search[ 2.355e+15 ] = 1049.11(96.307)
+#> search[ 2.355e+16 ] = 1049.11(96.307)
+#> search[ 2.355e+17 ] = 1049.11(96.307)
+#> search[ 2.355e+18 ] = 1049.11(96.307)
+#> search[ 2.355e+19 ] = 1049.11(96.307)
 #> 
-#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #1 Rep #1 pred log like = 372.477
-#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #2 Rep #1 pred log like = 427.325
-#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #3 Rep #1 pred log like = 468.972
-#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #4 Rep #1 pred log like = 505.448
-#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #5 Rep #1 pred log like = 364.283
-#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #6 Rep #1 pred log like = 433.204
-#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #7 Rep #1 pred log like = 443.18
-#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #8 Rep #1 pred log like = 438.402
-#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #9 Rep #1 pred log like = 475.918
-#> Running at Laplace(8.74539e-11) None  Grid-point #22 at 2.615e+20 	Fold #10 Rep #1 pred log like = 470.318
-#> AvgPred = 439.953 with stdev = 42.2422
-#> Completed at 2.615e+20
-#> Next point at 3.27402e+12 with value 439.953 and continue = 0
-#> search[ 0.2615 ] = 439.952(42.2492)
-#> search[ 2.615 ] = 439.952(42.2447)
-#> search[ 26.15 ] = 439.953(42.243)
-#> search[ 261.5 ] = 439.953(42.2425)
-#> search[ 2615 ] = 439.953(42.2423)
-#> search[ 26150 ] = 439.953(42.2423)
-#> search[ 261500 ] = 439.953(42.2422)
-#> search[ 2.615e+06 ] = 439.953(42.2422)
-#> search[ 2.615e+07 ] = 439.953(42.2422)
-#> search[ 2.615e+08 ] = 439.953(42.2422)
-#> search[ 2.615e+09 ] = 439.953(42.2422)
-#> search[ 2.615e+10 ] = 439.953(42.2422)
-#> search[ 2.615e+11 ] = 439.953(42.2422)
-#> search[ 2.615e+12 ] = 439.953(42.2422)
-#> search[ 2.615e+13 ] = 439.953(42.2422)
-#> search[ 2.615e+14 ] = 439.953(42.2422)
-#> search[ 2.615e+15 ] = 439.953(42.2422)
-#> search[ 2.615e+16 ] = 439.953(42.2422)
-#> search[ 2.615e+17 ] = 439.953(42.2422)
-#> search[ 2.615e+18 ] = 439.953(42.2422)
-#> search[ 2.615e+19 ] = 439.953(42.2422)
-#> search[ 2.615e+20 ] = 439.953(42.2422)
+#> Running at Laplace(9.21551e-11) None  Grid-point #22 at 2.355e+20 	Fold #1 Rep #1 pred log like = 1071.68
+#> Running at Laplace(9.21551e-11) None  Grid-point #22 at 2.355e+20 	Fold #2 Rep #1 pred log like = 887.707
+#> Running at Laplace(9.21551e-11) None  Grid-point #22 at 2.355e+20 	Fold #3 Rep #1 pred log like = 989.752
+#> Running at Laplace(9.21551e-11) None  Grid-point #22 at 2.355e+20 	Fold #4 Rep #1 pred log like = 1248.83
+#> Running at Laplace(9.21551e-11) None  Grid-point #22 at 2.355e+20 	Fold #5 Rep #1 pred log like = 1083.66
+#> Running at Laplace(9.21551e-11) None  Grid-point #22 at 2.355e+20 	Fold #6 Rep #1 pred log like = 1084.42
+#> Running at Laplace(9.21551e-11) None  Grid-point #22 at 2.355e+20 	Fold #7 Rep #1 pred log like = 1009.43
+#> Running at Laplace(9.21551e-11) None  Grid-point #22 at 2.355e+20 	Fold #8 Rep #1 pred log like = 927.809
+#> Running at Laplace(9.21551e-11) None  Grid-point #22 at 2.355e+20 	Fold #9 Rep #1 pred log like = 1097.98
+#> Running at Laplace(9.21551e-11) None  Grid-point #22 at 2.355e+20 	Fold #10 Rep #1 pred log like = 1089.84
+#> AvgPred = 1049.11 with stdev = 96.307
+#> Completed at 2.355e+20
+#> Next point at 5.19595e+12 with value 1049.11 and continue = 0
+#> search[ 0.2355 ] = 1049.11(96.3088)
+#> search[ 2.355 ] = 1049.11(96.3073)
+#> search[ 23.55 ] = 1049.11(96.3071)
+#> search[ 235.5 ] = 1049.11(96.307)
+#> search[ 2355 ] = 1049.11(96.307)
+#> search[ 23550 ] = 1049.11(96.307)
+#> search[ 235500 ] = 1049.11(96.307)
+#> search[ 2.355e+06 ] = 1049.11(96.307)
+#> search[ 2.355e+07 ] = 1049.11(96.307)
+#> search[ 2.355e+08 ] = 1049.11(96.307)
+#> search[ 2.355e+09 ] = 1049.11(96.307)
+#> search[ 2.355e+10 ] = 1049.11(96.307)
+#> search[ 2.355e+11 ] = 1049.11(96.307)
+#> search[ 2.355e+12 ] = 1049.11(96.307)
+#> search[ 2.355e+13 ] = 1049.11(96.307)
+#> search[ 2.355e+14 ] = 1049.11(96.307)
+#> search[ 2.355e+15 ] = 1049.11(96.307)
+#> search[ 2.355e+16 ] = 1049.11(96.307)
+#> search[ 2.355e+17 ] = 1049.11(96.307)
+#> search[ 2.355e+18 ] = 1049.11(96.307)
+#> search[ 2.355e+19 ] = 1049.11(96.307)
+#> search[ 2.355e+20 ] = 1049.11(96.307)
 #> 
 #> 
-#> Maximum predicted log likelihood (439.953) estimated at:
-#> 	3.27402e+12 (variance)
-#> 	7.81582e-07 (lambda)
+#> Maximum predicted log likelihood (1049.11) estimated at:
+#> 	5.19595e+12 (variance)
+#> 	6.20415e-07 (lambda)
 #> 
 #> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(7.81582e-07) None 
+#> Using prior: Laplace(6.20415e-07) None 
 
 #Find out what the optimal hyperparameter was:
 getHyperParameter(fit)
-#> [1] 3.274021e+12
+#> [1] 5.19595e+12
 
 #Extract the current log-likelihood, and coefficients
 logLik(fit)
-#> 'log Lik.' -2097.62 (df=3)
+#> 'log Lik.' -2307.763 (df=3)
 coef(fit)
 #> (Intercept)           1           2 
-#> -3.87566911  0.05844875  0.01875022 
+#> -3.54550102  0.31433174 -0.03279651 
 
 #We can only retrieve the confidence interval for unregularized coefficients:
 confint(fit, c(0))
 #> Using 1 thread(s)
 #>             covariate     2.5 %    97.5 % evaluations
-#> (Intercept)         0 -3.910302 -3.841399          22
+#> (Intercept)         0 -3.573019 -3.518211          22
diff --git a/docs/reference/logLik.cyclopsFit.html b/docs/reference/logLik.cyclopsFit.html index 5f68c200..40951e17 100644 --- a/docs/reference/logLik.cyclopsFit.html +++ b/docs/reference/logLik.cyclopsFit.html @@ -76,7 +76,7 @@

Examples

#Generate some simulated data:
 sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                            model = "poisson")
-#> Sparseness = 77.4 %
+#> Sparseness = 75.25 %
 cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                     addIntercept = TRUE)
 #> Sorting covariates by covariateId and rowId
@@ -89,81 +89,558 @@ 
Examples

 #Fit the model
 fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
 #> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1698757939] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Performing 10-fold cross-validation [seed = 1698789252] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
 #> Using 1 thread(s)
-#> Starting var = 0.226 (default)
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #1 Rep #1 pred log like = 424.312
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #2 Rep #1 pred log like = 286.112
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #3 Rep #1 pred log like = 542.244
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #4 Rep #1 pred log like = 462.595
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #5 Rep #1 pred log like = 523.632
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #6 Rep #1 pred log like = 390.675
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #7 Rep #1 pred log like = 360.237
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #8 Rep #1 pred log like = 399.312
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #9 Rep #1 pred log like = 395.077
-#> Running at Laplace(2.97482) None  Grid-point #1 at 0.226 	Fold #10 Rep #1 pred log like = 331.197
-#> AvgPred = 411.539 with stdev = 76.2186
-#> Completed at 0.226
-#> Next point at 2.26 with value 0 and continue = 1
-#> search[ 0.226 ] = 411.539(76.2186)
-#> 
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #1 Rep #1 pred log like = 424.271
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #2 Rep #1 pred log like = 286.187
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #3 Rep #1 pred log like = 542.304
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #4 Rep #1 pred log like = 462.57
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #5 Rep #1 pred log like = 523.608
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #6 Rep #1 pred log like = 390.669
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #7 Rep #1 pred log like = 360.212
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #8 Rep #1 pred log like = 399.333
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #9 Rep #1 pred log like = 395.126
-#> Running at Laplace(0.940721) None  Grid-point #2 at 2.26 	Fold #10 Rep #1 pred log like = 331.12
-#> AvgPred = 411.54 with stdev = 76.2193
-#> Completed at 2.26
-#> Next point at 22.6 with value 0 and continue = 1
-#> search[ 0.226 ] = 411.539(76.2186)
-#> search[ 2.26 ] = 411.54(76.2193)
-#> 
-#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #1 Rep #1 pred log like = 424.258
-#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #2 Rep #1 pred log like = 286.211
-#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #3 Rep #1 pred log like = 542.322
-#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #4 Rep #1 pred log like = 462.562
-#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #5 Rep #1 pred log like = 523.601
-#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #6 Rep #1 pred log like = 390.667
-#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #7 Rep #1 pred log like = 360.204
-#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #8 Rep #1 pred log like = 399.34
-#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #9 Rep #1 pred log like = 395.142
-#> Running at Laplace(0.297482) None  Grid-point #3 at 22.6 	Fold #10 Rep #1 pred log like = 331.095
-#> AvgPred = 411.54 with stdev = 76.2195
-#> Completed at 22.6
-#> Next point at 7.08693 with value 411.54 and continue = 0
-#> search[ 0.226 ] = 411.539(76.2186)
-#> search[ 2.26 ] = 411.54(76.2193)
-#> search[ 22.6 ] = 411.54(76.2195)
-#> 
-#> 
-#> Maximum predicted log likelihood (411.54) estimated at:
-#> 	7.08693 (variance)
-#> 	0.531234 (lambda)
+#> Starting var = 0.2475 (default)
+#> Running at Laplace(2.84268) None  Grid-point #1 at 0.2475 	Fold #1 Rep #1 pred log like = 764.157
+#> Running at Laplace(2.84268) None  Grid-point #1 at 0.2475 	Fold #2 Rep #1 pred log like = 802.169
+#> Running at Laplace(2.84268) None  Grid-point #1 at 0.2475 	Fold #3 Rep #1 pred log like = 809.884
+#> Running at Laplace(2.84268) None  Grid-point #1 at 0.2475 	Fold #4 Rep #1 pred log like = 829.664
+#> Running at Laplace(2.84268) None  Grid-point #1 at 0.2475 	Fold #5 Rep #1 pred log like = 803.191
+#> Running at Laplace(2.84268) None  Grid-point #1 at 0.2475 	Fold #6 Rep #1 pred log like = 774.997
+#> Running at Laplace(2.84268) None  Grid-point #1 at 0.2475 	Fold #7 Rep #1 pred log like = 771.955
+#> Running at Laplace(2.84268) None  Grid-point #1 at 0.2475 	Fold #8 Rep #1 pred log like = 809.568
+#> Running at Laplace(2.84268) None  Grid-point #1 at 0.2475 	Fold #9 Rep #1 pred log like = 730.503
+#> Running at Laplace(2.84268) None  Grid-point #1 at 0.2475 	Fold #10 Rep #1 pred log like = 661.936
+#> AvgPred = 775.802 with stdev = 46.7085
+#> Completed at 0.2475
+#> Next point at 2.475 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> 
+#> Running at Laplace(0.898933) None  Grid-point #2 at 2.475 	Fold #1 Rep #1 pred log like = 764.135
+#> Running at Laplace(0.898933) None  Grid-point #2 at 2.475 	Fold #2 Rep #1 pred log like = 802.181
+#> Running at Laplace(0.898933) None  Grid-point #2 at 2.475 	Fold #3 Rep #1 pred log like = 809.903
+#> Running at Laplace(0.898933) None  Grid-point #2 at 2.475 	Fold #4 Rep #1 pred log like = 829.66
+#> Running at Laplace(0.898933) None  Grid-point #2 at 2.475 	Fold #5 Rep #1 pred log like = 803.233
+#> Running at Laplace(0.898933) None  Grid-point #2 at 2.475 	Fold #6 Rep #1 pred log like = 774.984
+#> Running at Laplace(0.898933) None  Grid-point #2 at 2.475 	Fold #7 Rep #1 pred log like = 771.951
+#> Running at Laplace(0.898933) None  Grid-point #2 at 2.475 	Fold #8 Rep #1 pred log like = 809.56
+#> Running at Laplace(0.898933) None  Grid-point #2 at 2.475 	Fold #9 Rep #1 pred log like = 730.492
+#> Running at Laplace(0.898933) None  Grid-point #2 at 2.475 	Fold #10 Rep #1 pred log like = 661.932
+#> AvgPred = 775.803 with stdev = 46.7144
+#> Completed at 2.475
+#> Next point at 24.75 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> 
+#> Running at Laplace(0.284268) None  Grid-point #3 at 24.75 	Fold #1 Rep #1 pred log like = 764.128
+#> Running at Laplace(0.284268) None  Grid-point #3 at 24.75 	Fold #2 Rep #1 pred log like = 802.185
+#> Running at Laplace(0.284268) None  Grid-point #3 at 24.75 	Fold #3 Rep #1 pred log like = 809.909
+#> Running at Laplace(0.284268) None  Grid-point #3 at 24.75 	Fold #4 Rep #1 pred log like = 829.658
+#> Running at Laplace(0.284268) None  Grid-point #3 at 24.75 	Fold #5 Rep #1 pred log like = 803.246
+#> Running at Laplace(0.284268) None  Grid-point #3 at 24.75 	Fold #6 Rep #1 pred log like = 774.98
+#> Running at Laplace(0.284268) None  Grid-point #3 at 24.75 	Fold #7 Rep #1 pred log like = 771.949
+#> Running at Laplace(0.284268) None  Grid-point #3 at 24.75 	Fold #8 Rep #1 pred log like = 809.558
+#> Running at Laplace(0.284268) None  Grid-point #3 at 24.75 	Fold #9 Rep #1 pred log like = 730.488
+#> Running at Laplace(0.284268) None  Grid-point #3 at 24.75 	Fold #10 Rep #1 pred log like = 661.931
+#> AvgPred = 775.803 with stdev = 46.7163
+#> Completed at 24.75
+#> Next point at 247.5 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> 
+#> Running at Laplace(0.0898933) None  Grid-point #4 at 247.5 	Fold #1 Rep #1 pred log like = 764.126
+#> Running at Laplace(0.0898933) None  Grid-point #4 at 247.5 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(0.0898933) None  Grid-point #4 at 247.5 	Fold #3 Rep #1 pred log like = 809.91
+#> Running at Laplace(0.0898933) None  Grid-point #4 at 247.5 	Fold #4 Rep #1 pred log like = 829.658
+#> Running at Laplace(0.0898933) None  Grid-point #4 at 247.5 	Fold #5 Rep #1 pred log like = 803.25
+#> Running at Laplace(0.0898933) None  Grid-point #4 at 247.5 	Fold #6 Rep #1 pred log like = 774.979
+#> Running at Laplace(0.0898933) None  Grid-point #4 at 247.5 	Fold #7 Rep #1 pred log like = 771.949
+#> Running at Laplace(0.0898933) None  Grid-point #4 at 247.5 	Fold #8 Rep #1 pred log like = 809.557
+#> Running at Laplace(0.0898933) None  Grid-point #4 at 247.5 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(0.0898933) None  Grid-point #4 at 247.5 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7169
+#> Completed at 247.5
+#> Next point at 2475 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> 
+#> Running at Laplace(0.0284268) None  Grid-point #5 at 2475 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(0.0284268) None  Grid-point #5 at 2475 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(0.0284268) None  Grid-point #5 at 2475 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(0.0284268) None  Grid-point #5 at 2475 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(0.0284268) None  Grid-point #5 at 2475 	Fold #5 Rep #1 pred log like = 803.251
+#> Running at Laplace(0.0284268) None  Grid-point #5 at 2475 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(0.0284268) None  Grid-point #5 at 2475 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(0.0284268) None  Grid-point #5 at 2475 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(0.0284268) None  Grid-point #5 at 2475 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(0.0284268) None  Grid-point #5 at 2475 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7171
+#> Completed at 2475
+#> Next point at 24750 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> 
+#> Running at Laplace(0.00898933) None  Grid-point #6 at 24750 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(0.00898933) None  Grid-point #6 at 24750 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(0.00898933) None  Grid-point #6 at 24750 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(0.00898933) None  Grid-point #6 at 24750 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(0.00898933) None  Grid-point #6 at 24750 	Fold #5 Rep #1 pred log like = 803.251
+#> Running at Laplace(0.00898933) None  Grid-point #6 at 24750 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(0.00898933) None  Grid-point #6 at 24750 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(0.00898933) None  Grid-point #6 at 24750 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(0.00898933) None  Grid-point #6 at 24750 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(0.00898933) None  Grid-point #6 at 24750 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7171
+#> Completed at 24750
+#> Next point at 247500 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> 
+#> Running at Laplace(0.00284268) None  Grid-point #7 at 247500 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(0.00284268) None  Grid-point #7 at 247500 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(0.00284268) None  Grid-point #7 at 247500 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(0.00284268) None  Grid-point #7 at 247500 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(0.00284268) None  Grid-point #7 at 247500 	Fold #5 Rep #1 pred log like = 803.251
+#> Running at Laplace(0.00284268) None  Grid-point #7 at 247500 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(0.00284268) None  Grid-point #7 at 247500 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(0.00284268) None  Grid-point #7 at 247500 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(0.00284268) None  Grid-point #7 at 247500 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(0.00284268) None  Grid-point #7 at 247500 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7171
+#> Completed at 247500
+#> Next point at 2.475e+06 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> 
+#> Running at Laplace(0.000898933) None  Grid-point #8 at 2.475e+06 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(0.000898933) None  Grid-point #8 at 2.475e+06 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(0.000898933) None  Grid-point #8 at 2.475e+06 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(0.000898933) None  Grid-point #8 at 2.475e+06 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(0.000898933) None  Grid-point #8 at 2.475e+06 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(0.000898933) None  Grid-point #8 at 2.475e+06 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(0.000898933) None  Grid-point #8 at 2.475e+06 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(0.000898933) None  Grid-point #8 at 2.475e+06 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(0.000898933) None  Grid-point #8 at 2.475e+06 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(0.000898933) None  Grid-point #8 at 2.475e+06 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+06
+#> Next point at 2.475e+07 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(0.000284268) None  Grid-point #9 at 2.475e+07 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(0.000284268) None  Grid-point #9 at 2.475e+07 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(0.000284268) None  Grid-point #9 at 2.475e+07 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(0.000284268) None  Grid-point #9 at 2.475e+07 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(0.000284268) None  Grid-point #9 at 2.475e+07 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(0.000284268) None  Grid-point #9 at 2.475e+07 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(0.000284268) None  Grid-point #9 at 2.475e+07 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(0.000284268) None  Grid-point #9 at 2.475e+07 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(0.000284268) None  Grid-point #9 at 2.475e+07 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(0.000284268) None  Grid-point #9 at 2.475e+07 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+07
+#> Next point at 2.475e+08 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(8.98933e-05) None  Grid-point #10 at 2.475e+08 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(8.98933e-05) None  Grid-point #10 at 2.475e+08 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(8.98933e-05) None  Grid-point #10 at 2.475e+08 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(8.98933e-05) None  Grid-point #10 at 2.475e+08 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(8.98933e-05) None  Grid-point #10 at 2.475e+08 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(8.98933e-05) None  Grid-point #10 at 2.475e+08 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(8.98933e-05) None  Grid-point #10 at 2.475e+08 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(8.98933e-05) None  Grid-point #10 at 2.475e+08 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(8.98933e-05) None  Grid-point #10 at 2.475e+08 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(8.98933e-05) None  Grid-point #10 at 2.475e+08 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+08
+#> Next point at 2.475e+09 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(2.84268e-05) None  Grid-point #11 at 2.475e+09 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(2.84268e-05) None  Grid-point #11 at 2.475e+09 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(2.84268e-05) None  Grid-point #11 at 2.475e+09 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(2.84268e-05) None  Grid-point #11 at 2.475e+09 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(2.84268e-05) None  Grid-point #11 at 2.475e+09 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(2.84268e-05) None  Grid-point #11 at 2.475e+09 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(2.84268e-05) None  Grid-point #11 at 2.475e+09 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(2.84268e-05) None  Grid-point #11 at 2.475e+09 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(2.84268e-05) None  Grid-point #11 at 2.475e+09 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(2.84268e-05) None  Grid-point #11 at 2.475e+09 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+09
+#> Next point at 2.475e+10 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> search[ 2.475e+09 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(8.98933e-06) None  Grid-point #12 at 2.475e+10 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(8.98933e-06) None  Grid-point #12 at 2.475e+10 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(8.98933e-06) None  Grid-point #12 at 2.475e+10 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(8.98933e-06) None  Grid-point #12 at 2.475e+10 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(8.98933e-06) None  Grid-point #12 at 2.475e+10 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(8.98933e-06) None  Grid-point #12 at 2.475e+10 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(8.98933e-06) None  Grid-point #12 at 2.475e+10 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(8.98933e-06) None  Grid-point #12 at 2.475e+10 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(8.98933e-06) None  Grid-point #12 at 2.475e+10 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(8.98933e-06) None  Grid-point #12 at 2.475e+10 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+10
+#> Next point at 2.475e+11 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> search[ 2.475e+09 ] = 775.803(46.7172)
+#> search[ 2.475e+10 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(2.84268e-06) None  Grid-point #13 at 2.475e+11 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(2.84268e-06) None  Grid-point #13 at 2.475e+11 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(2.84268e-06) None  Grid-point #13 at 2.475e+11 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(2.84268e-06) None  Grid-point #13 at 2.475e+11 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(2.84268e-06) None  Grid-point #13 at 2.475e+11 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(2.84268e-06) None  Grid-point #13 at 2.475e+11 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(2.84268e-06) None  Grid-point #13 at 2.475e+11 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(2.84268e-06) None  Grid-point #13 at 2.475e+11 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(2.84268e-06) None  Grid-point #13 at 2.475e+11 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(2.84268e-06) None  Grid-point #13 at 2.475e+11 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+11
+#> Next point at 2.475e+12 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> search[ 2.475e+09 ] = 775.803(46.7172)
+#> search[ 2.475e+10 ] = 775.803(46.7172)
+#> search[ 2.475e+11 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(8.98933e-07) None  Grid-point #14 at 2.475e+12 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(8.98933e-07) None  Grid-point #14 at 2.475e+12 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(8.98933e-07) None  Grid-point #14 at 2.475e+12 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(8.98933e-07) None  Grid-point #14 at 2.475e+12 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(8.98933e-07) None  Grid-point #14 at 2.475e+12 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(8.98933e-07) None  Grid-point #14 at 2.475e+12 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(8.98933e-07) None  Grid-point #14 at 2.475e+12 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(8.98933e-07) None  Grid-point #14 at 2.475e+12 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(8.98933e-07) None  Grid-point #14 at 2.475e+12 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(8.98933e-07) None  Grid-point #14 at 2.475e+12 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+12
+#> Next point at 2.475e+13 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> search[ 2.475e+09 ] = 775.803(46.7172)
+#> search[ 2.475e+10 ] = 775.803(46.7172)
+#> search[ 2.475e+11 ] = 775.803(46.7172)
+#> search[ 2.475e+12 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(2.84268e-07) None  Grid-point #15 at 2.475e+13 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(2.84268e-07) None  Grid-point #15 at 2.475e+13 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(2.84268e-07) None  Grid-point #15 at 2.475e+13 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(2.84268e-07) None  Grid-point #15 at 2.475e+13 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(2.84268e-07) None  Grid-point #15 at 2.475e+13 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(2.84268e-07) None  Grid-point #15 at 2.475e+13 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(2.84268e-07) None  Grid-point #15 at 2.475e+13 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(2.84268e-07) None  Grid-point #15 at 2.475e+13 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(2.84268e-07) None  Grid-point #15 at 2.475e+13 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(2.84268e-07) None  Grid-point #15 at 2.475e+13 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+13
+#> Next point at 2.475e+14 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> search[ 2.475e+09 ] = 775.803(46.7172)
+#> search[ 2.475e+10 ] = 775.803(46.7172)
+#> search[ 2.475e+11 ] = 775.803(46.7172)
+#> search[ 2.475e+12 ] = 775.803(46.7172)
+#> search[ 2.475e+13 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(8.98933e-08) None  Grid-point #16 at 2.475e+14 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(8.98933e-08) None  Grid-point #16 at 2.475e+14 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(8.98933e-08) None  Grid-point #16 at 2.475e+14 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(8.98933e-08) None  Grid-point #16 at 2.475e+14 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(8.98933e-08) None  Grid-point #16 at 2.475e+14 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(8.98933e-08) None  Grid-point #16 at 2.475e+14 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(8.98933e-08) None  Grid-point #16 at 2.475e+14 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(8.98933e-08) None  Grid-point #16 at 2.475e+14 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(8.98933e-08) None  Grid-point #16 at 2.475e+14 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(8.98933e-08) None  Grid-point #16 at 2.475e+14 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+14
+#> Next point at 2.475e+15 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> search[ 2.475e+09 ] = 775.803(46.7172)
+#> search[ 2.475e+10 ] = 775.803(46.7172)
+#> search[ 2.475e+11 ] = 775.803(46.7172)
+#> search[ 2.475e+12 ] = 775.803(46.7172)
+#> search[ 2.475e+13 ] = 775.803(46.7172)
+#> search[ 2.475e+14 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(2.84268e-08) None  Grid-point #17 at 2.475e+15 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(2.84268e-08) None  Grid-point #17 at 2.475e+15 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(2.84268e-08) None  Grid-point #17 at 2.475e+15 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(2.84268e-08) None  Grid-point #17 at 2.475e+15 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(2.84268e-08) None  Grid-point #17 at 2.475e+15 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(2.84268e-08) None  Grid-point #17 at 2.475e+15 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(2.84268e-08) None  Grid-point #17 at 2.475e+15 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(2.84268e-08) None  Grid-point #17 at 2.475e+15 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(2.84268e-08) None  Grid-point #17 at 2.475e+15 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(2.84268e-08) None  Grid-point #17 at 2.475e+15 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+15
+#> Next point at 2.475e+16 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> search[ 2.475e+09 ] = 775.803(46.7172)
+#> search[ 2.475e+10 ] = 775.803(46.7172)
+#> search[ 2.475e+11 ] = 775.803(46.7172)
+#> search[ 2.475e+12 ] = 775.803(46.7172)
+#> search[ 2.475e+13 ] = 775.803(46.7172)
+#> search[ 2.475e+14 ] = 775.803(46.7172)
+#> search[ 2.475e+15 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(8.98933e-09) None  Grid-point #18 at 2.475e+16 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(8.98933e-09) None  Grid-point #18 at 2.475e+16 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(8.98933e-09) None  Grid-point #18 at 2.475e+16 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(8.98933e-09) None  Grid-point #18 at 2.475e+16 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(8.98933e-09) None  Grid-point #18 at 2.475e+16 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(8.98933e-09) None  Grid-point #18 at 2.475e+16 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(8.98933e-09) None  Grid-point #18 at 2.475e+16 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(8.98933e-09) None  Grid-point #18 at 2.475e+16 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(8.98933e-09) None  Grid-point #18 at 2.475e+16 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(8.98933e-09) None  Grid-point #18 at 2.475e+16 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+16
+#> Next point at 2.475e+17 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> search[ 2.475e+09 ] = 775.803(46.7172)
+#> search[ 2.475e+10 ] = 775.803(46.7172)
+#> search[ 2.475e+11 ] = 775.803(46.7172)
+#> search[ 2.475e+12 ] = 775.803(46.7172)
+#> search[ 2.475e+13 ] = 775.803(46.7172)
+#> search[ 2.475e+14 ] = 775.803(46.7172)
+#> search[ 2.475e+15 ] = 775.803(46.7172)
+#> search[ 2.475e+16 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(2.84268e-09) None  Grid-point #19 at 2.475e+17 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(2.84268e-09) None  Grid-point #19 at 2.475e+17 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(2.84268e-09) None  Grid-point #19 at 2.475e+17 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(2.84268e-09) None  Grid-point #19 at 2.475e+17 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(2.84268e-09) None  Grid-point #19 at 2.475e+17 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(2.84268e-09) None  Grid-point #19 at 2.475e+17 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(2.84268e-09) None  Grid-point #19 at 2.475e+17 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(2.84268e-09) None  Grid-point #19 at 2.475e+17 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(2.84268e-09) None  Grid-point #19 at 2.475e+17 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(2.84268e-09) None  Grid-point #19 at 2.475e+17 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+17
+#> Next point at 2.475e+18 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> search[ 2.475e+09 ] = 775.803(46.7172)
+#> search[ 2.475e+10 ] = 775.803(46.7172)
+#> search[ 2.475e+11 ] = 775.803(46.7172)
+#> search[ 2.475e+12 ] = 775.803(46.7172)
+#> search[ 2.475e+13 ] = 775.803(46.7172)
+#> search[ 2.475e+14 ] = 775.803(46.7172)
+#> search[ 2.475e+15 ] = 775.803(46.7172)
+#> search[ 2.475e+16 ] = 775.803(46.7172)
+#> search[ 2.475e+17 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(8.98933e-10) None  Grid-point #20 at 2.475e+18 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(8.98933e-10) None  Grid-point #20 at 2.475e+18 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(8.98933e-10) None  Grid-point #20 at 2.475e+18 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(8.98933e-10) None  Grid-point #20 at 2.475e+18 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(8.98933e-10) None  Grid-point #20 at 2.475e+18 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(8.98933e-10) None  Grid-point #20 at 2.475e+18 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(8.98933e-10) None  Grid-point #20 at 2.475e+18 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(8.98933e-10) None  Grid-point #20 at 2.475e+18 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(8.98933e-10) None  Grid-point #20 at 2.475e+18 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(8.98933e-10) None  Grid-point #20 at 2.475e+18 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+18
+#> Next point at 2.475e+19 with value 0 and continue = 1
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> search[ 2.475e+09 ] = 775.803(46.7172)
+#> search[ 2.475e+10 ] = 775.803(46.7172)
+#> search[ 2.475e+11 ] = 775.803(46.7172)
+#> search[ 2.475e+12 ] = 775.803(46.7172)
+#> search[ 2.475e+13 ] = 775.803(46.7172)
+#> search[ 2.475e+14 ] = 775.803(46.7172)
+#> search[ 2.475e+15 ] = 775.803(46.7172)
+#> search[ 2.475e+16 ] = 775.803(46.7172)
+#> search[ 2.475e+17 ] = 775.803(46.7172)
+#> search[ 2.475e+18 ] = 775.803(46.7172)
+#> 
+#> Running at Laplace(2.84268e-10) None  Grid-point #21 at 2.475e+19 	Fold #1 Rep #1 pred log like = 764.125
+#> Running at Laplace(2.84268e-10) None  Grid-point #21 at 2.475e+19 	Fold #2 Rep #1 pred log like = 802.186
+#> Running at Laplace(2.84268e-10) None  Grid-point #21 at 2.475e+19 	Fold #3 Rep #1 pred log like = 809.911
+#> Running at Laplace(2.84268e-10) None  Grid-point #21 at 2.475e+19 	Fold #4 Rep #1 pred log like = 829.657
+#> Running at Laplace(2.84268e-10) None  Grid-point #21 at 2.475e+19 	Fold #5 Rep #1 pred log like = 803.252
+#> Running at Laplace(2.84268e-10) None  Grid-point #21 at 2.475e+19 	Fold #6 Rep #1 pred log like = 774.978
+#> Running at Laplace(2.84268e-10) None  Grid-point #21 at 2.475e+19 	Fold #7 Rep #1 pred log like = 771.948
+#> Running at Laplace(2.84268e-10) None  Grid-point #21 at 2.475e+19 	Fold #8 Rep #1 pred log like = 809.556
+#> Running at Laplace(2.84268e-10) None  Grid-point #21 at 2.475e+19 	Fold #9 Rep #1 pred log like = 730.487
+#> Running at Laplace(2.84268e-10) None  Grid-point #21 at 2.475e+19 	Fold #10 Rep #1 pred log like = 661.93
+#> AvgPred = 775.803 with stdev = 46.7172
+#> Completed at 2.475e+19
+#> Next point at 6.1351e+11 with value 775.803 and continue = 0
+#> search[ 0.2475 ] = 775.802(46.7085)
+#> search[ 2.475 ] = 775.803(46.7144)
+#> search[ 24.75 ] = 775.803(46.7163)
+#> search[ 247.5 ] = 775.803(46.7169)
+#> search[ 2475 ] = 775.803(46.7171)
+#> search[ 24750 ] = 775.803(46.7171)
+#> search[ 247500 ] = 775.803(46.7171)
+#> search[ 2.475e+06 ] = 775.803(46.7172)
+#> search[ 2.475e+07 ] = 775.803(46.7172)
+#> search[ 2.475e+08 ] = 775.803(46.7172)
+#> search[ 2.475e+09 ] = 775.803(46.7172)
+#> search[ 2.475e+10 ] = 775.803(46.7172)
+#> search[ 2.475e+11 ] = 775.803(46.7172)
+#> search[ 2.475e+12 ] = 775.803(46.7172)
+#> search[ 2.475e+13 ] = 775.803(46.7172)
+#> search[ 2.475e+14 ] = 775.803(46.7172)
+#> search[ 2.475e+15 ] = 775.803(46.7172)
+#> search[ 2.475e+16 ] = 775.803(46.7172)
+#> search[ 2.475e+17 ] = 775.803(46.7172)
+#> search[ 2.475e+18 ] = 775.803(46.7172)
+#> search[ 2.475e+19 ] = 775.803(46.7172)
+#> 
+#> 
+#> Maximum predicted log likelihood (775.803) estimated at:
+#> 	6.1351e+11 (variance)
+#> 	1.80553e-06 (lambda)
 #> 
 #> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(0.531234) None 
+#> Using prior: Laplace(1.80553e-06) None 
 
 #Find out what the optimal hyperparameter was:
 getHyperParameter(fit)
-#> [1] 7.086931
+#> [1] 6.1351e+11
 
 #Extract the current log-likelihood, and coefficients
 logLik(fit)
-#> 'log Lik.' -2045.115 (df=3)
+#> 'log Lik.' -2193.651 (df=3)
 coef(fit)
 #> (Intercept)           1           2 
-#> -3.89896635 -0.03932575  0.03150517 
+#> -3.61883104  0.06239337  0.04106083 
 
 #We can only retrieve the confidence interval for unregularized coefficients:
 confint(fit, c(0))
 #> Using 1 thread(s)
 #>             covariate     2.5 %    97.5 % evaluations
-#> (Intercept)         0 -3.932993 -3.865291          22
+#> (Intercept)         0 -3.649159 -3.588779          22
diff --git a/docs/reference/simulateCyclopsData.html b/docs/reference/simulateCyclopsData.html index 222a5a05..59a8f165 100644 --- a/docs/reference/simulateCyclopsData.html +++ b/docs/reference/simulateCyclopsData.html @@ -109,7 +109,7 @@

Examples

#Generate some simulated data:
 sim <- simulateCyclopsData(nstrata = 1, nrows = 1000, ncovars = 2, eCovarsPerRow = 0.5, 
                            model = "poisson")
-#> Sparseness = 76.25 %
+#> Sparseness = 77.45 %
 cyclopsData <- convertToCyclopsData(sim$outcomes, sim$covariates, modelType = "pr", 
                                     addIntercept = TRUE)
 #> Sorting covariates by covariateId and rowId
@@ -122,163 +122,99 @@ 
Examples

 #Fit the model
 fit <- fitCyclopsModel(cyclopsData,prior = prior, control = control)  
 #> Using cross-validation selector type byRow
-#> Performing 10-fold cross-validation [seed = 1698757941] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
+#> Performing 10-fold cross-validation [seed = 1698789255] with data partitions of sizes 100 100 100 100 100 100 100 100 100 100
 #> Using 1 thread(s)
-#> Starting var = 0.2375 (default)
-#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #1 Rep #1 pred log like = 102.616
-#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #2 Rep #1 pred log like = 194.806
-#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #3 Rep #1 pred log like = 198.183
-#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #4 Rep #1 pred log like = 145.178
-#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #5 Rep #1 pred log like = 75.747
-#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #6 Rep #1 pred log like = 78.3006
-#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #7 Rep #1 pred log like = 123.887
-#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #8 Rep #1 pred log like = 192.631
-#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #9 Rep #1 pred log like = 153.328
-#> Running at Laplace(2.90191) None  Grid-point #1 at 0.2375 	Fold #10 Rep #1 pred log like = 101.303
-#> AvgPred = 136.598 with stdev = 45.0972
-#> Completed at 0.2375
-#> Next point at 2.375 with value 0 and continue = 1
-#> search[ 0.2375 ] = 136.598(45.0972)
-#> 
-#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #1 Rep #1 pred log like = 102.586
-#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #2 Rep #1 pred log like = 194.788
-#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #3 Rep #1 pred log like = 198.074
-#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #4 Rep #1 pred log like = 145.144
-#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #5 Rep #1 pred log like = 75.6951
-#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #6 Rep #1 pred log like = 78.2926
-#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #7 Rep #1 pred log like = 123.843
-#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #8 Rep #1 pred log like = 192.573
-#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #9 Rep #1 pred log like = 153.292
-#> Running at Laplace(0.917663) None  Grid-point #2 at 2.375 	Fold #10 Rep #1 pred log like = 101.237
-#> AvgPred = 136.553 with stdev = 45.0876
-#> Completed at 2.375
-#> Next point at 0.02375 with value 0 and continue = 1
-#> search[ 0.2375 ] = 136.598(45.0972)
-#> search[ 2.375 ] = 136.553(45.0876)
-#> 
-#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #1 Rep #1 pred log like = 102.69
-#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #2 Rep #1 pred log like = 194.857
-#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #3 Rep #1 pred log like = 198.387
-#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #4 Rep #1 pred log like = 145.273
-#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #5 Rep #1 pred log like = 75.8784
-#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #6 Rep #1 pred log like = 78.3257
-#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #7 Rep #1 pred log like = 124.02
-#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #8 Rep #1 pred log like = 192.801
-#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #9 Rep #1 pred log like = 153.42
-#> Running at Laplace(9.17663) None  Grid-point #3 at 0.02375 	Fold #10 Rep #1 pred log like = 101.43
-#> AvgPred = 136.708 with stdev = 45.1178
-#> Completed at 0.02375
-#> Next point at 0.002375 with value 0 and continue = 1
-#> search[ 0.02375 ] = 136.708(45.1178)
-#> search[ 0.2375 ] = 136.598(45.0972)
-#> search[ 2.375 ] = 136.553(45.0876)
-#> 
-#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #1 Rep #1 pred log like = 102.69
-#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #2 Rep #1 pred log like = 194.874
-#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #3 Rep #1 pred log like = 198.387
-#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #4 Rep #1 pred log like = 145.273
-#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #5 Rep #1 pred log like = 75.988
-#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #6 Rep #1 pred log like = 78.3279
-#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #7 Rep #1 pred log like = 124.209
-#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #8 Rep #1 pred log like = 192.831
-#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #9 Rep #1 pred log like = 153.42
-#> Running at Laplace(29.0191) None  Grid-point #4 at 0.002375 	Fold #10 Rep #1 pred log like = 101.43
-#> AvgPred = 136.743 with stdev = 45.1033
-#> Completed at 0.002375
-#> Next point at 0.0002375 with value 0 and continue = 1
-#> search[ 0.002375 ] = 136.743(45.1033)
-#> search[ 0.02375 ] = 136.708(45.1178)
-#> search[ 0.2375 ] = 136.598(45.0972)
-#> search[ 2.375 ] = 136.553(45.0876)
-#> 
-#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #1 Rep #1 pred log like = 102.69
-#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #2 Rep #1 pred log like = 194.874
-#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #3 Rep #1 pred log like = 198.387
-#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #4 Rep #1 pred log like = 145.273
-#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #5 Rep #1 pred log like = 75.988
-#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #6 Rep #1 pred log like = 78.3279
-#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #7 Rep #1 pred log like = 124.209
-#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #8 Rep #1 pred log like = 192.831
-#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #9 Rep #1 pred log like = 153.42
-#> Running at Laplace(91.7663) None  Grid-point #5 at 0.0002375 	Fold #10 Rep #1 pred log like = 101.43
-#> AvgPred = 136.743 with stdev = 45.1033
-#> Completed at 0.0002375
-#> Next point at 0.00014571 with value 136.751 and continue = 0
-#> search[ 0.0002375 ] = 136.743(45.1033)
-#> search[ 0.002375 ] = 136.743(45.1033)
-#> search[ 0.02375 ] = 136.708(45.1178)
-#> search[ 0.2375 ] = 136.598(45.0972)
-#> search[ 2.375 ] = 136.553(45.0876)
-#> 
-#> 
-#> Maximum predicted log likelihood (136.751) estimated at:
-#> 	0.00014571 (variance)
-#> 	117.158 (lambda)
+#> Starting var = 0.2255 (default)
+#> Running at Laplace(2.97812) None  Grid-point #1 at 0.2255 	Fold #1 Rep #1 pred log like = 273.307
+#> Running at Laplace(2.97812) None  Grid-point #1 at 0.2255 	Fold #2 Rep #1 pred log like = 399.873
+#> Running at Laplace(2.97812) None  Grid-point #1 at 0.2255 	Fold #3 Rep #1 pred log like = 404.29
+#> Running at Laplace(2.97812) None  Grid-point #1 at 0.2255 	Fold #4 Rep #1 pred log like = 453.587
+#> Running at Laplace(2.97812) None  Grid-point #1 at 0.2255 	Fold #5 Rep #1 pred log like = 409.265
+#> Running at Laplace(2.97812) None  Grid-point #1 at 0.2255 	Fold #6 Rep #1 pred log like = 383.626
+#> Running at Laplace(2.97812) None  Grid-point #1 at 0.2255 	Fold #7 Rep #1 pred log like = 322.027
+#> Running at Laplace(2.97812) None  Grid-point #1 at 0.2255 	Fold #8 Rep #1 pred log like = 388.538
+#> Running at Laplace(2.97812) None  Grid-point #1 at 0.2255 	Fold #9 Rep #1 pred log like = 307.366
+#> Running at Laplace(2.97812) None  Grid-point #1 at 0.2255 	Fold #10 Rep #1 pred log like = 439.966
+#> AvgPred = 378.185 with stdev = 55.6106
+#> Completed at 0.2255
+#> Next point at 2.255 with value 0 and continue = 1
+#> search[ 0.2255 ] = 378.185(55.6106)
+#> 
+#> Running at Laplace(0.941763) None  Grid-point #2 at 2.255 	Fold #1 Rep #1 pred log like = 273.215
+#> Running at Laplace(0.941763) None  Grid-point #2 at 2.255 	Fold #2 Rep #1 pred log like = 399.868
+#> Running at Laplace(0.941763) None  Grid-point #2 at 2.255 	Fold #3 Rep #1 pred log like = 404.281
+#> Running at Laplace(0.941763) None  Grid-point #2 at 2.255 	Fold #4 Rep #1 pred log like = 453.566
+#> Running at Laplace(0.941763) None  Grid-point #2 at 2.255 	Fold #5 Rep #1 pred log like = 409.239
+#> Running at Laplace(0.941763) None  Grid-point #2 at 2.255 	Fold #6 Rep #1 pred log like = 383.621
+#> Running at Laplace(0.941763) None  Grid-point #2 at 2.255 	Fold #7 Rep #1 pred log like = 322.048
+#> Running at Laplace(0.941763) None  Grid-point #2 at 2.255 	Fold #8 Rep #1 pred log like = 388.517
+#> Running at Laplace(0.941763) None  Grid-point #2 at 2.255 	Fold #9 Rep #1 pred log like = 307.357
+#> Running at Laplace(0.941763) None  Grid-point #2 at 2.255 	Fold #10 Rep #1 pred log like = 439.957
+#> AvgPred = 378.167 with stdev = 55.6206
+#> Completed at 2.255
+#> Next point at 0.02255 with value 0 and continue = 1
+#> search[ 0.2255 ] = 378.185(55.6106)
+#> search[ 2.255 ] = 378.167(55.6206)
+#> 
+#> Running at Laplace(9.41763) None  Grid-point #3 at 0.02255 	Fold #1 Rep #1 pred log like = 273.567
+#> Running at Laplace(9.41763) None  Grid-point #3 at 0.02255 	Fold #2 Rep #1 pred log like = 399.871
+#> Running at Laplace(9.41763) None  Grid-point #3 at 0.02255 	Fold #3 Rep #1 pred log like = 404.295
+#> Running at Laplace(9.41763) None  Grid-point #3 at 0.02255 	Fold #4 Rep #1 pred log like = 453.644
+#> Running at Laplace(9.41763) None  Grid-point #3 at 0.02255 	Fold #5 Rep #1 pred log like = 409.323
+#> Running at Laplace(9.41763) None  Grid-point #3 at 0.02255 	Fold #6 Rep #1 pred log like = 383.623
+#> Running at Laplace(9.41763) None  Grid-point #3 at 0.02255 	Fold #7 Rep #1 pred log like = 321.955
+#> Running at Laplace(9.41763) None  Grid-point #3 at 0.02255 	Fold #8 Rep #1 pred log like = 388.579
+#> Running at Laplace(9.41763) None  Grid-point #3 at 0.02255 	Fold #9 Rep #1 pred log like = 307.378
+#> Running at Laplace(9.41763) None  Grid-point #3 at 0.02255 	Fold #10 Rep #1 pred log like = 439.958
+#> AvgPred = 378.219 with stdev = 55.5785
+#> Completed at 0.02255
+#> Next point at 0.002255 with value 0 and continue = 1
+#> search[ 0.02255 ] = 378.219(55.5785)
+#> search[ 0.2255 ] = 378.185(55.6106)
+#> search[ 2.255 ] = 378.167(55.6206)
+#> 
+#> Running at Laplace(29.7812) None  Grid-point #4 at 0.002255 	Fold #1 Rep #1 pred log like = 274.347
+#> Running at Laplace(29.7812) None  Grid-point #4 at 0.002255 	Fold #2 Rep #1 pred log like = 399.829
+#> Running at Laplace(29.7812) None  Grid-point #4 at 0.002255 	Fold #3 Rep #1 pred log like = 404.168
+#> Running at Laplace(29.7812) None  Grid-point #4 at 0.002255 	Fold #4 Rep #1 pred log like = 453.483
+#> Running at Laplace(29.7812) None  Grid-point #4 at 0.002255 	Fold #5 Rep #1 pred log like = 409.31
+#> Running at Laplace(29.7812) None  Grid-point #4 at 0.002255 	Fold #6 Rep #1 pred log like = 383.395
+#> Running at Laplace(29.7812) None  Grid-point #4 at 0.002255 	Fold #7 Rep #1 pred log like = 321.694
+#> Running at Laplace(29.7812) None  Grid-point #4 at 0.002255 	Fold #8 Rep #1 pred log like = 388.495
+#> Running at Laplace(29.7812) None  Grid-point #4 at 0.002255 	Fold #9 Rep #1 pred log like = 307.173
+#> Running at Laplace(29.7812) None  Grid-point #4 at 0.002255 	Fold #10 Rep #1 pred log like = 439.822
+#> AvgPred = 378.172 with stdev = 55.4357
+#> Completed at 0.002255
+#> Next point at 0.0505023 with value 378.206 and continue = 0
+#> search[ 0.002255 ] = 378.172(55.4357)
+#> search[ 0.02255 ] = 378.219(55.5785)
+#> search[ 0.2255 ] = 378.185(55.6106)
+#> search[ 2.255 ] = 378.167(55.6206)
+#> 
+#> 
+#> Maximum predicted log likelihood (378.206) estimated at:
+#> 	0.0505023 (variance)
+#> 	6.29302 (lambda)
 #> 
 #> Fitting model at optimal hyperparameter
-#> Using prior: Laplace(117.158) None 
+#> Using prior: Laplace(6.29302) None 
 
 #Find out what the optimal hyperparameter was:
 getHyperParameter(fit)
-#> [1] 0.0001457099
+#> [1] 0.0505023
 
 #Extract the current log-likelihood, and coefficients
 logLik(fit)
-#> 'log Lik.' -1805.625 (df=3)
+#> 'log Lik.' -2012.552 (df=3)
 coef(fit)
 #> (Intercept)           1           2 
-#>   -4.287453    0.000000    0.000000 
+#> -3.94394237  0.00000000  0.06899875 
 
 #We can only retrieve the confidence interval for unregularized coefficients:
 confint(fit, c(0))
 #> Using 1 thread(s)
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
-#> 
-#> Warning: BLR gradient is ill-conditioned
-#> Enforcing convergence!
 #>             covariate     2.5 %    97.5 % evaluations
-#> (Intercept)         0 -4.321798 -4.253487          23
+#> (Intercept)         0 -3.977897 -3.909783          22