Fixed #92; Refixed #108; Updated D3

NAMESPACE

@@ -23,6 +23,7 @@ export(plot_str)
 export(profile_missing)
 export(set_missing)
 export(split_columns)
+export(update_columns)
 import(data.table)
 import(ggplot2)
 import(gridExtra)

NEWS.md

@@ -1,8 +1,6 @@
 # DataExplorer 0.7.1.9000
-## Bug Fixes
-* [#88](https://github.com/boxuancui/DataExplorer/issues/88): Added `plot_intro` to report config.
-* [#90](https://github.com/boxuancui/DataExplorer/issues/90): Added first plot in `plot_prcomp` to output and `page_0`.
-* [#94](https://github.com/boxuancui/DataExplorer/issues/94): Fixed typo for PCA.
+## New Features
+* [#92](https://github.com/boxuancui/DataExplorer/issues/92): Added `update_columns` to transform any selected columns.
 
 ## Enhancements
 * [#89](https://github.com/boxuancui/DataExplorer/issues/89): Added option to customize `geom_text` and `geom_label` arguments.
@@ -11,7 +9,13 @@
 * [#98](https://github.com/boxuancui/DataExplorer/issues/98): Added band customization to `plot_missing`.
 * [#100](https://github.com/boxuancui/DataExplorer/issues/100): Switched `geom_text` to `geom_label`.
 * [#103](https://github.com/boxuancui/DataExplorer/issues/103): Report title can now be customized in `create_report`.
-* [#108](https://github.com/boxuancui/DataExplorer/issues/108): Added option to treat binary features as discrete in `plot_bar`, `plot_histogram` and `plot_density`.
+* [#108](https://github.com/boxuancui/DataExplorer/issues/108): Added option to treat binary features as discrete in `plot_bar`, `plot_histogram`, `plot_density` and `plot_boxplot`.
+* Updated d3.min.js to v5.9.2.
+
+## Bug Fixes
+* [#88](https://github.com/boxuancui/DataExplorer/issues/88): Added `plot_intro` to report config.
+* [#90](https://github.com/boxuancui/DataExplorer/issues/90): Added first plot in `plot_prcomp` to output and `page_0`.
+* [#94](https://github.com/boxuancui/DataExplorer/issues/94): Fixed typo for PCA.
 
 # DataExplorer 0.7.1
 ## Enhancements

R/drop_columns.r

@@ -1,12 +1,12 @@
 #' Drop selected variables
 #'
-#' Quickly drop variables by either name or column position.
+#' Quickly drop variables by either column names or positions.
 #' @param data input data
 #' @param ind a vector of either names or column positions of the variables to be dropped.
 #' @keywords drop_columns
 #' @details \bold{This function updates \link{data.table} object directly.} Otherwise, output data will be returned matching input object class.
 #' @import data.table
-#' @export drop_columns
+#' @export
 #' @examples
 #' # Load packages
 #' library(data.table)

R/plot_boxplot.r

@@ -3,6 +3,7 @@
 #' This function creates boxplot for each continuous feature based on a selected feature.
 #' @param data input data
 #' @param by feature name to be broken down by. If selecting a continuous feature, boxplot will be grouped by 5 equal ranges, otherwise, all existing categories for a discrete feature.
+#' @param binary_as_factor treat binary as categorical? Default is \code{TRUE}.
 #' @param geom_boxplot_args a list of other arguments to \link{geom_boxplot}
 #' @param title plot title
 #' @param ggtheme complete ggplot2 themes. The default is \link{theme_gray}.
@@ -20,13 +21,13 @@
 #' plot_boxplot(iris, by = "Species", nrow = 2L, ncol = 2L)
 #' plot_boxplot(iris, by = "Species", geom_boxplot_args = list("outlier.color" = "red"))
 
-plot_boxplot <- function(data, by, geom_boxplot_args = list(), title = NULL, ggtheme = theme_gray(), theme_config = list(), nrow = 3L, ncol = 4L, parallel = FALSE) {
+plot_boxplot <- function(data, by, binary_as_factor = TRUE, geom_boxplot_args = list(), title = NULL, ggtheme = theme_gray(), theme_config = list(), nrow = 3L, ncol = 4L, parallel = FALSE) {
 	## Declare variable first to pass R CMD check
 	variable <- by_f <- value <- NULL
 	## Check if input is data.table
 	if (!is.data.table(data)) data <- data.table(data)
 	## Stop if no continuous features
-	split_obj <- split_columns(data)
+	split_obj <- split_columns(data, binary_as_factor = binary_as_factor)
 	if (split_obj$num_continuous == 0) stop("No Continuous Features!")
 	## Get continuous features
 	continuous <- split_obj$continuous

R/plot_density.r

@@ -2,8 +2,8 @@
 #'
 #' Plot density estimates for each continuous feature
 #' @param data input data
-#' @param geom_density_args a list of other arguments to \link{geom_density}
 #' @param binary_as_factor treat binary as categorical? Default is \code{TRUE}.
+#' @param geom_density_args a list of other arguments to \link{geom_density}
 #' @param title plot title
 #' @param ggtheme complete ggplot2 themes. The default is \link{theme_gray}.
 #' @param theme_config a list of configurations to be passed to \link{theme}.
@@ -28,7 +28,7 @@
 #' # Add color to density area
 #' plot_density(data, geom_density_args = list("fill" = "black", "alpha" = 0.6))
 
-plot_density <- function(data, geom_density_args = list(), binary_as_factor = TRUE, title = NULL, ggtheme = theme_gray(), theme_config = list(), nrow = 4L, ncol = 4L, parallel = FALSE) {
+plot_density <- function(data, binary_as_factor = TRUE, geom_density_args = list(), title = NULL, ggtheme = theme_gray(), theme_config = list(), nrow = 4L, ncol = 4L, parallel = FALSE) {
 	## Declare variable first to pass R CMD check
 	variable <- value <- NULL
 	## Check if input is data.table

R/plot_histogram.r

@@ -2,8 +2,8 @@
 #'
 #' Plot histogram for each continuous feature
 #' @param data input data
-#' @param geom_histogram_args a list of other arguments to \link{geom_histogram}
 #' @param binary_as_factor treat binary as categorical? Default is \code{TRUE}.
+#' @param geom_histogram_args a list of other arguments to \link{geom_histogram}
 #' @param title plot title
 #' @param ggtheme complete ggplot2 themes. The default is \link{theme_gray}.
 #' @param theme_config a list of configurations to be passed to \link{theme}.
@@ -25,7 +25,7 @@
 #' data <- data.frame(replicate(16L, rnorm(50)))
 #' plot_histogram(data)
 
-plot_histogram <- function(data, geom_histogram_args = list("bins" = 30L), binary_as_factor = TRUE, title = NULL, ggtheme = theme_gray(), theme_config = list(), nrow = 4L, ncol = 4L, parallel = FALSE) {
+plot_histogram <- function(data, binary_as_factor = TRUE, geom_histogram_args = list("bins" = 30L), title = NULL, ggtheme = theme_gray(), theme_config = list(), nrow = 4L, ncol = 4L, parallel = FALSE) {
 	## Declare variable first to pass R CMD check
 	variable <- value <- NULL
 	## Check if input is data.table

R/update_columns.r

@@ -0,0 +1,39 @@
+#' Update variable types or values
+#'
+#' Quickly update selected variables using column names or positions.
+#' @param data input data
+#' @param ind a vector of either names or column positions of the variables to be dropped.
+#' @param what either a function or a non-empty character string naming the function to be called. See \link{do.call}.
+#' @keywords drop_columns
+#' @details \bold{This function updates \link{data.table} object directly.} Otherwise, output data will be returned matching input object class.
+#' @import data.table
+#' @export
+#' @examples
+#' str(update_columns(iris, 1L, as.factor))
+#' str(update_columns(iris, c("Sepal.Width", "Petal.Length"), "as.integer"))
+#' 
+#' ## Apply log transformation to all columns
+#' summary(airquality)
+#' summary(update_columns(airquality, names(airquality), log))
+#' 
+#' ## Force set factor to numeric
+#' df <- data.frame("a" = as.factor(sample.int(10L)))
+#' str(df)
+#' str(update_columns(df, "a", function(x) as.numeric(levels(x))[x]))
+
+update_columns <- function(data, ind, what) {
+  ## Check if input is data.table
+  is_data_table <- is.data.table(data)
+  ## Detect input data class
+  data_class <- class(data)
+  ## Set data to data.table
+  if (!is_data_table) data <- data.table(data)
+  ## Transform columns
+  if (is.numeric(ind)) ind <- as.integer(ind)
+  for (j in ind) set(x = data, j = j, value = do.call(what, list(data[[j]])))
+  ## Set data class back to original
+  if (!is_data_table) {
+    class(data) <- data_class
+    return(data)
+  }
+}

README.Rmd

@@ -209,6 +209,10 @@ df <- data.frame("a" = rnorm(260), "b" = rep(letters, 10))
 df[sample.int(260, 50), ] <- NA
 set_missing(df, list(0L, "unknown"))
 
+## Update columns
+update_columns(airquality, c("Month", "Day"), as.factor)
+update_columns(airquality, 1L, function(x) x^2)
+
 ## Drop columns
 drop_columns(diamonds, 8:10)
 drop_columns(diamonds, "clarity")

README.md

@@ -116,6 +116,10 @@ df <- data.frame("a" = rnorm(260), "b" = rep(letters, 10))
 df[sample.int(260, 50), ] <- NA
 set_missing(df, list(0L, "unknown"))
 
+## Update columns
+update_columns(airquality, c("Month", "Day"), as.factor)
+update_columns(airquality, 1L, function(x) x^2)
+
 ## Drop columns
 drop_columns(diamonds, 8:10)
 drop_columns(diamonds, "clarity")

tests/testthat/test-update-columns.r

@@ -0,0 +1,17 @@
+context("update variables")
+
+test_that("test basic functionality", {
+  iris_dt <- data.table(iris)
+  update_columns(iris_dt, 1L, as.character)
+  update_columns(iris_dt, c("Sepal.Width", "Petal.Length"), as.factor)
+  update_columns(iris_dt, "Petal.Width", as.integer)
+  expect_is(iris_dt[[1]], "character")
+  expect_is(iris_dt$Sepal.Width, "factor")
+  expect_is(iris_dt$Petal.Length, "factor")
+  expect_is(iris_dt$Petal.Width, "integer")
+  expect_is(iris_dt, "data.table")
+})
+
+test_that("test non-data.table objects", {
+  expect_is(update_columns(iris, 1L, as.character), "data.frame")
+})