Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add new parameters to several functions avoid the need of a text dump

Browse Source
This commit is contained in:
El Potaeto
2015-01-11 03:06:41 +01:00
parent 70df227689
commit c8c5789efd
5 changed files with 48 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
R-package/R/xgb.importance.R
View File

@@ -9,6 +9,7 @@
#' @importFrom magrittr %>%
#' @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}).
#' @param model generated by the \code{xgb.train} function. Avoid the creation of a dump file.
#'
#' @return A \code{data.table} of the features used in the model with their average gain (and their weight for boosted tree model) in the model.
#'
@@ -38,20 +39,30 @@
#'
#' bst <- xgboost(data = train$data, label = train$label, max.depth = 2,
#' eta = 1, nround = 2,objective = "binary:logistic")
#' xgb.dump(bst, 'xgb.model.dump', with.stats = T)
#'
#' #agaricus.test$data@@Dimnames[[2]] represents the column names of the sparse matrix.
#' xgb.importance(agaricus.test$data@@Dimnames[[2]], 'xgb.model.dump')
#' xgb.importance(agaricus.test$data@@Dimnames[[2]], model = bst)
#'
#' @export
xgb.importance <- function(feature_names = NULL, filename_dump = NULL){
xgb.importance <- function(feature_names = NULL, filename_dump = NULL, model = 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)) {
if (!(class(filename_dump) %in% c("character", "NULL") && length(filename_dump) <= 1)) {
stop("filename_dump: Has to be a path to the model dump file.")
}
text <- readLines(filename_dump)
if (!class(model) %in% c("xgb.Booster", "NULL")) {
stop("model: Has to be an object of class xgb.Booster model generaged by the xgb.train function.")
}
if(is.null(model)){
text <- readLines(filename_dump)
} else {
text <- xgb.dump(model = model, with.stats = T)
}
if(text[2] == "bias:"){
result <- linearDump(feature_names, text)
} else {