Merge pull request #15 from Yue-Jiang/master

prep for new cran release

Author: Yue-Jiang

.Rbuildignore

@@ -5,3 +5,5 @@ materials*
 ^_pkgdown\.yml$
 ^\.travis\.yml$
 ^cran-comments\.md$
+^doc$
+^Meta$

.gitignore

@@ -1,3 +1,5 @@
 .Rproj.user
 .Rhistory
 .RData
+doc
+Meta

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: randomForestExplainer
 Title: Explaining and Visualizing Random Forests in Terms of Variable Importance
-Version: 0.9
+Version: 0.10.0
 Authors@R: c(
   person("Aleksandra", "Paluszynska", email = "ola.paluszynska@gmail.com", role = c("aut")),
   person("Przemyslaw", "Biecek", email = "przemyslaw.biecek@gmail.com", role = c("aut","ths")),
@@ -18,13 +18,13 @@ Imports:
   GGally (>= 1.3.0),
   ggplot2 (>= 2.2.1),
   ggrepel (>= 0.6.5),
-  MASS (>= 7.3.47),
   randomForest (>= 4.6.12),
   ranger(>= 0.9.0),
   reshape2 (>= 1.4.2),
   rmarkdown (>= 1.5)
 Suggests:
     knitr,
+    MASS (>= 7.3.47),
     testthat
 VignetteBuilder: knitr
 RoxygenNote: 6.1.1

NEWS.md

@@ -0,0 +1,9 @@
+# randomForestExplainer 0.10.0
+## New features
+* Added support for ranger forests.
+* Added support for unsupervised randomForest.
+* Added tests for most functions.
+
+## Bug fixes
+* Fixed bug for explain_forest not finding templates.
+* Added more intuitive error message for explain_forest when local importance is absent.

R/measure_importance.R

@@ -148,6 +148,7 @@ measure_importance.randomForest <- function(forest, mean_sample = "top_trees", m
     }
     forest_table <-
       lapply(1:forest$ntree, function(i) randomForest::getTree(forest, k = i, labelVar = T) %>%
+               mutate_if(is.factor, as.character) %>%
                calculate_tree_depth() %>% cbind(tree = i)) %>% rbindlist()
     min_depth_frame <- dplyr::group_by(forest_table, tree, `split var`) %>%
       dplyr::summarize(min(depth))
@@ -245,7 +246,7 @@ measure_importance.ranger <- function(forest, mean_sample = "top_trees", measure
 #' @param importance_frame A result of using the function measure_importance() to a random forest or a randomForest object
 #' @param measures A character vector specifying the measures of importance to be used
 #' @param k The number of variables to extract
-#' @param ties_action One of three: c("none", "all", "draw"); specifies which variables to pick when ties occur. When set to "none" we may get less than k variables, when "all" whe may get more and "draw" makes us get exactly k.
+#' @param ties_action One of three: c("none", "all", "draw"); specifies which variables to pick when ties occur. When set to "none" we may get less than k variables, when "all" we may get more and "draw" makes us get exactly k.
 #'
 #' @return A character vector with names of k variables with highest sum of rankings
 #'

R/min_depth_distribution.R

@@ -39,8 +39,8 @@ calculate_tree_depth_ranger <- function(frame){
 #' @return A data frame with the value of minimal depth for every variable in every tree
 #'
 #' @examples
-#' min_depth_distribution(randomForest::randomForest(Species ~ ., data = iris))
-#' min_depth_distribution(ranger::ranger(Species ~ ., data = iris))
+#' min_depth_distribution(randomForest::randomForest(Species ~ ., data = iris, ntree = 100))
+#' min_depth_distribution(ranger::ranger(Species ~ ., data = iris, num.trees = 100))
 #'
 #' @export
 min_depth_distribution <- function(forest){
@@ -54,6 +54,7 @@ min_depth_distribution.randomForest <- function(forest){
   tree <- NULL; `split var` <- NULL; depth <- NULL
   forest_table <-
     lapply(1:forest$ntree, function(i) randomForest::getTree(forest, k = i, labelVar = T) %>%
+             mutate_if(is.factor, as.character) %>%
              calculate_tree_depth() %>% cbind(tree = i)) %>% rbindlist()
   min_depth_frame <- dplyr::group_by(forest_table, tree, `split var`) %>%
     dplyr::summarize(min(depth))

R/min_depth_interactions.R

@@ -60,6 +60,7 @@ min_depth_interactions_values <- function(forest, vars){
   `.` <- NULL; .SD <- NULL; tree <- NULL; `split var` <- NULL
   interactions_frame <-
     lapply(1:forest$ntree, function(i) randomForest::getTree(forest, k = i, labelVar = T) %>%
+             mutate_if(is.factor, as.character) %>%
              calculate_tree_depth() %>% cbind(., tree = i, number = 1:nrow(.))) %>%
     data.table::rbindlist() %>% as.data.frame()
   interactions_frame[vars] <- as.numeric(NA)
@@ -109,11 +110,11 @@ min_depth_interactions_values_ranger <- function(forest, vars){
 #' Calculate mean conditional minimal depth with respect to a vector of variables
 #'
 #' @param forest A randomForest object
-#' @param vars A character vector with variables with respect to which conditional minimal depth will be calculated; by defalt it is extracted by the important_variables function but this may be time consuming
+#' @param vars A character vector with variables with respect to which conditional minimal depth will be calculated; by default it is extracted by the important_variables function but this may be time consuming
 #' @param mean_sample The sample of trees on which conditional mean minimal depth is calculated, possible values are "all_trees", "top_trees", "relevant_trees"
 #' @param uncond_mean_sample The sample of trees on which unconditional mean minimal depth is calculated, possible values are "all_trees", "top_trees", "relevant_trees"
 #'
-#' @return A data frame with each observarion giving the means of conditional minimal depth and the size of sample for a given interaction
+#' @return A data frame with each observation giving the means of conditional minimal depth and the size of sample for a given interaction
 #'
 #' @examples
 #' forest <- randomForest::randomForest(Species ~ ., data = iris, ntree = 100)
@@ -164,6 +165,7 @@ min_depth_interactions.randomForest <- function(forest, vars = important_variabl
   interactions_frame$interaction <- paste(interactions_frame$root_variable, interactions_frame$variable, sep = ":")
   forest_table <-
     lapply(1:forest$ntree, function(i) randomForest::getTree(forest, k = i, labelVar = T) %>%
+             mutate_if(is.factor, as.character) %>%
              calculate_tree_depth() %>% cbind(tree = i)) %>% rbindlist()
   min_depth_frame <- dplyr::group_by(forest_table, tree, `split var`) %>%
     dplyr::summarize(min(depth))

README.md

@@ -5,9 +5,9 @@
 [![codecov](https://codecov.io/gh/ModelOriented/randomForestExplainer/branch/master/graph/badge.svg)](https://codecov.io/gh/ModelOriented/randomForestExplainer)
 [![DOI](https://zenodo.org/badge/97007621.svg)](https://zenodo.org/badge/latestdoi/97007621)
 
-A set of tools to understand what is happening inside a Random Forest. A detailed discussion of the package and importance measures it implements can be found here: [Master thesis on randomForestExplainer](https://rawgit.com/geneticsMiNIng/BlackBoxOpener/master/randomForestExplainer_Master_thesis.pdf).
+A set of tools to understand what is happening inside a Random Forest. A detailed discussion of the package and importance measures it implements can be found here: [Master thesis on randomForestExplainer](https://cdn.staticaly.com/gh/geneticsMiNIng/BlackBoxOpener/master/randomForestExplainer_Master_thesis.pdf).
 
-## Instalation
+## Installation
 
 randomForestExplainer can be installed from [CRAN](https://cran.r-project.org/package=randomForestExplainer) as follows:
 
@@ -26,12 +26,12 @@ library(randomForestExplainer)
 
 ## Vignette
 
-* [Understanding random forests with randomForestExplainer](https://rawgit.com/ModelOriented/randomForestExplainer/master/inst/doc/randomForestExplainer.html)
+* [Understanding random forests with randomForestExplainer](https://modeloriented.github.io/randomForestExplainer/articles/randomForestExplainer.html)
 
 ## Cheatsheets
 
 * [A one-page summary](https://github.com/ModelOriented/randomForestExplainer/blob/master/materials/cheatsheet.pdf)
 
 ## Examples
 
-* [Initial vignette for glioblastoma data](https://rawgit.com/geneticsMiNIng/BlackBoxOpener/master/randomForestExplainer/inst/doc/randomForestExplainer.html)
+* [Initial vignette for glioblastoma data](https://cdn.staticaly.com/gh/geneticsMiNIng/BlackBoxOpener/master/randomForestExplainer/inst/doc/randomForestExplainer.html)

cran-comments.md

@@ -0,0 +1,22 @@
+## Test environments
+* local OS X install, R 3.6.1
+* ubuntu 16.04 (on travis-ci, devel and release)
+* win-builder (devel and release)
+
+## R CMD check results
+There were no ERRORs or WARNINGs.
+
+There was one NOTE:
+```
+* checking CRAN incoming feasibility ... NOTE
+Maintainer: 'Yue Jiang <rivehill@gmail.com>'
+
+New maintainer:
+  Yue Jiang <rivehill@gmail.com>
+Old maintainer(s):
+  Aleksandra Paluszynska <ola.paluszynska@gmail.com>
+```    
+The maintainer role has been passed along to Yue Jiang and this is correct.
+
+## Downstream dependencies
+There are no downstream dependencies at this time.