Prepare release 0.17.0 (#2300)

* rerun quickstart and working with inferencedata nbs * doc fixes add dataarray and dataset as type aliases fix css for homepage * add encoding arg for reading html_repr's css * improve psislw docstring * add docstring to smooth_data * remove show=True in tests * update changelog and bump version * make smooth data public api * extend numpydoc type ignores
arviz-devs · Dec 27, 2023 · 3713edf · 3713edf
1 parent 27b8a49
commit 3713edf
Show file tree

Hide file tree

Showing 16 changed files with 9,194 additions and 5,544 deletions.
diff --git a/.gitignore b/.gitignore
@@ -82,6 +82,9 @@ doc/source/user_guide/wrappers/*
 !doc/source/user_guide/wrappers/*.md
 
 # eight-schools files
+doc/source/getting_started/schools*
+!doc/source/user_guide/wrappers/schools.stan
+!doc/source/user_guide/wrappers/schools.json
 doc/source/getting_started/eight_school*
 doc/source/getting_started/sample_data/
 

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,21 +1,23 @@
 # Change Log
 
-## v0.x.x Unreleased
+## v0.17.0 (2023 Dec 22)
 
 ### New features
 - Add prior sensitivity diagnostic `psens` ([2093](https://github.com/arviz-devs/arviz/pull/2093))
--   Add filter_vars functionality to `InfereceData.to_dataframe`method ([2277](https://github.com/arviz-devs/arviz/pull/2277))
+- Add filter_vars functionality to `InfereceData.to_dataframe`method ([2277](https://github.com/arviz-devs/arviz/pull/2277))
 
 ### Maintenance and fixes
 
 -   Update requirements: matplotlib>=3.5, pandas>=1.4.0, numpy>=1.22.0 ([2280](https://github.com/arviz-devs/arviz/pull/2280))
 -   Fix behaviour of `plot_ppc` when dimension order isn't `chain, draw, ...` ([2283](https://github.com/arviz-devs/arviz/pull/2283))
 -   Avoid repeating the variable name in `plot_ppc`, `plot_bpv`, `plot_loo_pit`... when repeated. ([2283](https://github.com/arviz-devs/arviz/pull/2283))
 -   Add support for the latest CmdStanPy. ([2287](https://github.com/arviz-devs/arviz/pull/2287))
-
-### Deprecation
+-   Fix import error on windows due to missing encoding argument ([2300](https://github.com/arviz-devs/arviz/pull/2300))
+-   Add ``__delitem__`` method to InferenceData ([2292](https://github.com/arviz-devs/arviz/pull/2292))
 
 ### Documentation
+- Improve the docstring of `psislw` ([2300](https://github.com/arviz-devs/arviz/pull/2300))
+- Rerun the quickstart and working with InferenceData notebooks ([2300](https://github.com/arviz-devs/arviz/pull/2300))
 
 -   Several fixes in `plot_ppc` docstring ([2283](https://github.com/arviz-devs/arviz/pull/2283))
 

diff --git a/arviz/__init__.py b/arviz/__init__.py
@@ -1,6 +1,6 @@
 # pylint: disable=wildcard-import,invalid-name,wrong-import-position
 """ArviZ is a library for exploratory analysis of Bayesian models."""
-__version__ = "0.17.0.dev0"
+__version__ = "0.17.0"
 
 import logging
 import os

diff --git a/arviz/plots/bpvplot.py b/arviz/plots/bpvplot.py
@@ -165,7 +165,7 @@ def plot_bpv(
     Notes
     -----
     Discrete data is smoothed before computing either p-values or u-values using the
-    function :func:`smooth_data`
+    function :func:`~arviz.smooth_data`
 
     Examples
     --------

diff --git a/arviz/stats/__init__.py b/arviz/stats/__init__.py
@@ -28,6 +28,7 @@
     "autocorr",
     "autocov",
     "make_ufunc",
+    "smooth_data",
     "wrap_xarray_ufunc",
     "reloo",
     "_calculate_ics",

diff --git a/arviz/stats/stats.py b/arviz/stats/stats.py
@@ -880,17 +880,18 @@ def psislw(log_weights, reff=1.0):
 
     Parameters
     ----------
-    log_weights: array
+    log_weights : DataArray or (..., N) array-like
         Array of size (n_observations, n_samples)
-    reff: float
+    reff : float, default 1
         relative MCMC efficiency, ``ess / n``
 
     Returns
     -------
-    lw_out: array
-        Smoothed log weights
-    kss: array
-        Pareto tail indices
+    lw_out : DataArray or (..., N) ndarray
+        Smoothed, truncated and normalized log weights.
+    kss : DataArray or (...) ndarray
+        Estimates of the shape parameter *k* of the generalized Pareto
+        distribution.
 
     References
     ----------

diff --git a/arviz/stats/stats_utils.py b/arviz/stats/stats_utils.py
@@ -16,7 +16,7 @@
 from .density_utils import histogram as _histogram
 
 
-__all__ = ["autocorr", "autocov", "ELPDData", "make_ufunc", "wrap_xarray_ufunc"]
+__all__ = ["autocorr", "autocov", "ELPDData", "make_ufunc", "smooth_data", "wrap_xarray_ufunc"]
 
 
 def autocov(ary, axis=-1):
@@ -564,7 +564,25 @@ def _circular_standard_deviation(samples, high=2 * np.pi, low=0, skipna=False, a
 
 
 def smooth_data(obs_vals, pp_vals):
-    """Smooth data, helper function for discrete data in plot_pbv, loo_pit and plot_loo_pit."""
+    """Smooth data using a cubic spline.
+
+    Helper function for discrete data in plot_pbv, loo_pit and plot_loo_pit.
+
+    Parameters
+    ----------
+    obs_vals : (N) array-like
+        Observed data
+    pp_vals : (S, N) array-like
+        Posterior predictive samples. ``N`` is the number of observations,
+        and ``S`` is the number of samples (generally n_chains*n_draws).
+
+    Returns
+    -------
+    obs_vals : (N) ndarray
+        Smoothed observed data
+    pp_vals : (S, N) ndarray
+        Smoothed posterior predictive samples
+    """
     x = np.linspace(0, 1, len(obs_vals))
     csi = CubicSpline(x, obs_vals)
     obs_vals = csi(np.linspace(0.01, 0.99, len(obs_vals)))

diff --git a/arviz/tests/base_tests/test_plots_matplotlib.py b/arviz/tests/base_tests/test_plots_matplotlib.py
@@ -1921,7 +1921,7 @@ def test_plot_ts(kwargs):
         dims={"y": ["obs_dim"], "z": ["pred_dim"]},
     )
 
-    ax = plot_ts(idata=idata, y="y", show=True, **kwargs)
+    ax = plot_ts(idata=idata, y="y", **kwargs)
     assert np.all(ax)
 
 

diff --git a/arviz/utils.py b/arviz/utils.py
@@ -668,7 +668,8 @@ def _load_static_files():
     Clone from xarray.core.formatted_html_template.
     """
     return [
-        importlib.resources.files("arviz").joinpath(fname).read_text() for fname in STATIC_FILES
+        importlib.resources.files("arviz").joinpath(fname).read_text(encoding="utf-8")
+        for fname in STATIC_FILES
     ]
 
 

diff --git a/doc/source/_static/custom.css b/doc/source/_static/custom.css
@@ -80,7 +80,7 @@ html[data-theme="dark"] {
 }
 .primary-button {
   background-color: var(--pst-color-primary);
-  color: var(--pst-color-background);
+  color: var(--pst-color-background) !important;
 }
 .secondary-button {
   background-color: var(--pst-color-background);

diff --git a/doc/source/api/stats_utils.rst b/doc/source/api/stats_utils.rst
@@ -11,4 +11,5 @@ Stats utils
     autocov
     autocorr
     make_ufunc
+    smooth_data
     wrap_xarray_ufunc
diff --git a/doc/source/conf.py b/doc/source/conf.py
@@ -99,15 +99,16 @@
 autodoc_typehints = "none"
 numpydoc_xref_param_type = True
 numpydoc_xref_ignore = {
-    "of", "or", "optional", "default", "1D", "2D", "3D", "n-dimensional", "M", "N", "K",
+    "of", "or", "optional", "default", "1D", "2D", "3D", "n-dimensional", "K", "M", "N", "S",
 }
 numpydoc_xref_aliases = {
+    "DataArray": ":class:`~xarray.DataArray`",
+    "Dataset": ":class:`~xarray.Dataset`",
     "Labeller": ":ref:`Labeller <labeller_api>`",
     "ndarray": ":class:`~numpy.ndarray`",
     "InferenceData": ":class:`~arviz.InferenceData`",
     "matplotlib_axes": ":class:`matplotlib Axes <matplotlib.axes.Axes>`",
     "bokeh_figure": ":class:`Bokeh Figure <bokeh.plotting.figure>`",
-
 }
 
 # The base toctree document.

diff --git a/doc/source/getting_started/Introduction.ipynb b/doc/source/getting_started/Introduction.ipynb
diff --git a/doc/source/getting_started/WorkingWithInferenceData.ipynb b/doc/source/getting_started/WorkingWithInferenceData.ipynb
diff --git a/doc/source/getting_started/schools.json b/doc/source/getting_started/schools.json
@@ -0,0 +1,5 @@
+{
+  "J": 8,
+  "y": [28, 8, -3, 7, -1, 1, 18, 12],
+  "sigma": [15, 10, 16, 11, 9, 11, 10, 18]
+}
diff --git a/doc/source/getting_started/schools.stan b/doc/source/getting_started/schools.stan
@@ -0,0 +1,26 @@
+data {
+  int<lower=0> J;
+  array[J] real y;
+  array[J] real<lower=0> sigma;
+}
+
+parameters {
+  real mu;
+  real<lower=0> tau;
+  array[J] real theta;
+}
+
+model {
+  mu ~ normal(0, 5);
+  tau ~ cauchy(0, 5);
+  theta ~ normal(mu, tau);
+  y ~ normal(theta, sigma);
+}
+generated quantities {
+    array[J] real log_lik;
+    array[J] real y_hat;
+    for (j in 1:J) {
+        log_lik[j] = normal_lpdf(y[j] | theta[j], sigma[j]);
+        y_hat[j] = normal_rng(theta[j], sigma[j]);
+    }
+}