refactoring of importance function

R-package/R/xgb.importance.R

@@ -6,7 +6,6 @@
 #' @importFrom data.table data.table
 #' @importFrom magrittr %>%
 #' @importFrom data.table :=
-#' @importFrom stringr str_extract
 #' @param feature_names names of each feature as a character vector. Can be extracted from a sparse matrix (see example). If model dump already contains feature names, this argument should be \code{NULL}.
 #' @param filename_dump the path to the text file storing the model. Model dump must include the gain per feature and per tree (\code{with.stats = T} in function \code{xgb.dump}).
 #'
@@ -21,7 +20,8 @@
 #' There are 3 columns :
 #' \itemize{
 #'   \item \code{Features} name of the features as provided in \code{feature_names} or already present in the model dump.
-#'   \item \code{Gain} contribution of each feature to the model. For boosted tree model, each gain of each feature of each tree is taken into account, then average per feature to give a vision of the entire model. Highest percentage means most important feature regarding the \code{label} used for the training.
+#'   \item \code{Gain} contribution of each feature to the model. For boosted tree model, each gain of each feature of each tree is taken into account, then average per feature to give a vision of the entire model. Highest percentage means important feature to predict the \code{label} used for the training ;
+#'   \item \code{Cover} metric of the number of observation related to this feature (only available for tree models) ;
 #'   \item \code{Weight} percentage representing the relative number of times a feature have been taken into trees. \code{Gain} should be prefered to search the most important feature. For boosted linear model, this column has no meaning.
 #' }
 #' 
@@ -60,20 +60,9 @@ xgb.importance <- function(feature_names = NULL, filename_dump = NULL){
 }
 
 treeDump <- function(feature_names, text){  
-  featureVec <- c()
-  gainVec <- c()
-  for(line in text){
-    p <- str_extract(line, "\\[f.*<")
-    if (!is.na(p)) {
-      featureVec <- substr(p, 3, nchar(p)-1) %>% c(featureVec)
-      gainVec <- str_extract(line, "gain.*,") %>%  substr(x = ., 6, nchar(.)-1) %>% as.numeric %>% c(gainVec)
-    }
-  }
-  if(!is.null(feature_names)) {
-    featureVec %<>% as.numeric %>% {c =.+1; feature_names[c]} #+1 because in R indexing start with 1 instead of 0.
-  }
-  #1. Reduce, 2. %, 3. reorder - bigger top, 4. remove temp col
-  data.table(Feature = featureVec, Weight = gainVec)[,list(sum(Weight), .N), by = Feature][, Gain:= V1/sum(V1)][,Weight:= N/sum(N)][order(-rank(Gain))][,-c(2,3), with = F]
+  result <- xgb.model.dt.tree(feature_names = feature_names, text = text)[Feature!="Leaf",][,.(sum(Quality), sum(Cover), .N),by = Feature][,V1:=V1/sum(V1)][,V2:=V2/sum(V2)][,N:=N/sum(N)][order(-rank(V1))]
+  setnames(result, c("Feature", "Gain", "Cover", "Frequence"))
+  result  
 }
 
 linearDump <- function(feature_names, text){

R-package/R/xgb.model.dt.tree.R

@@ -51,19 +51,29 @@
 #' xgb.model.dt.tree(agaricus.train$data@@Dimnames[[2]], 'xgb.model.dump')
 #' 
 #' @export
-xgb.model.dt.tree <- function(feature_names = NULL, filename_dump = NULL, n_first_tree = NULL){
+xgb.model.dt.tree <- function(feature_names = NULL, filename_dump = NULL, text = NULL, n_first_tree = NULL){
   
   if (!class(feature_names) %in% c("character", "NULL")) {     
     stop("feature_names: Has to be a vector of character or NULL if the model dump already contains feature name. Look at this function documentation to see where to get feature names.")
   }
-  if (class(filename_dump) != "character" || !file.exists(filename_dump)) {
-    stop("filename_dump: Has to be a path to the model dump file.")
+  if (!class(filename_dump) %in% c("character", "NULL")) {
+    stop("filename_dump: Has to be a character vector representing the path to the model dump file.")
+  } else if (class(filename_dump) == "character" && !file.exists(filename_dump)) {
+    stop("filename_dump: path to the model doesn't exist.")
+  } else if(is.null(filename_dump) & is.null(text)){
+    stop("filename_dump: no path and no string version of the model dump have been provided.")
+  }
+  if (!class(text) %in% c("character", "NULL")) {     
+    stop("text: Has to be a vector of character or NULL if a path to the model dump has already been provided.")
   }
   if (!class(n_first_tree) %in% c("numeric", "NULL") | length(n_first_tree) > 1) {
     stop("n_first_tree: Has to be a numeric vector of size 1.")
   }
   
+  if(is.null(text)){
     text <- readLines(filename_dump) %>% str_trim(side = "both")  
+  }
+  
   position <- str_match(text, "booster") %>% is.na %>% not %>% which %>% c(length(text)+1)
   
   extract <- function(x, pattern)  str_extract(x, pattern) %>% str_split("=") %>% lapply(function(x) x[2] %>% as.numeric) %>% unlist

R-package/man/xgb.importance.Rd

@@ -27,7 +27,8 @@ Results are returned for both linear and tree models.
 There are 3 columns :
 \itemize{
   \item \code{Features} name of the features as provided in \code{feature_names} or already present in the model dump.
-  \item \code{Gain} contribution of each feature to the model. For boosted tree model, each gain of each feature of each tree is taken into account, then average per feature to give a vision of the entire model. Highest percentage means most important feature regarding the \code{label} used for the training.
+  \item \code{Gain} contribution of each feature to the model. For boosted tree model, each gain of each feature of each tree is taken into account, then average per feature to give a vision of the entire model. Highest percentage means most important feature regarding the \code{label} used for the training ;
+  \item \code{Cover} metric of the number of observation related to this feature (only available for tree models) ;
   \item \code{Weight} percentage representing the relative number of times a feature have been taken into trees. \code{Gain} should be prefered to search the most important feature. For boosted linear model, this column has no meaning.
 }
 }

R-package/man/xgb.model.dt.tree.Rd

@@ -4,7 +4,7 @@
 \alias{xgb.model.dt.tree}
 \title{Convert tree model dump to data.table}
 \usage{
-xgb.model.dt.tree(feature_names = NULL, filename_dump = NULL,
+xgb.model.dt.tree(feature_names = NULL, filename_dump = NULL, text = NULL,
   n_first_tree = NULL)
 }
 \arguments{