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

add new parameters model to avoid the use of dump file for functions plot, dt.tree, importance

Browse Source 
add new size parameter for plot function
This commit is contained in:
El Potaeto
2015-01-11 09:40:55 +01:00
parent c8c5789efd
commit 31a3b38ef8
5 changed files with 40 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
R-package/R/xgb.model.dt.tree.R
View File

@@ -16,6 +16,8 @@
#' @importFrom stringr str_trim
#' @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 (parameter \code{with.stats = T} in function \code{xgb.dump}).
#' @param model dump generated by the \code{xgb.train} function. Avoid the creation of a dump file.
#' @param text dump generated by the \code{xgb.dump} function. Avoid the creation of a dump file. Model dump must include the gain per feature and per tree (parameter \code{with.stats = T} in function \code{xgb.dump}).
#' @param n_first_tree limit the plot to the n first trees. If \code{NULL}, all trees of the model are plotted. Performance can be low for huge models.
#'
#' @return A \code{data.table} of the features used in the model with their gain, cover and few other thing.
@@ -49,29 +51,37 @@
#' xgb.dump(bst, 'xgb.model.dump', with.stats = T)
#'
#' #agaricus.test$data@@Dimnames[[2]] represents the column names of the sparse matrix.
#' xgb.model.dt.tree(agaricus.train$data@@Dimnames[[2]], 'xgb.model.dump')
#' xgb.model.dt.tree(agaricus.train$data@@Dimnames[[2]], filename_dump = 'xgb.model.dump')
#'
#' @export
xgb.model.dt.tree <- function(feature_names = NULL, filename_dump = NULL, text = NULL, n_first_tree = NULL){
xgb.model.dt.tree <- function(feature_names = NULL, filename_dump = NULL, model = 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) %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)) {
if (!(class(filename_dump) %in% c("character", "NULL") && length(filename_dump) <= 1)) {
stop("filename_dump: Has to be a character vector of size 1 representing the path to the model dump file.")
} else if (!is.null(filename_dump) && !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.")
} else if(is.null(filename_dump) && is.null(model) && is.null(text)){
stop("filename_dump & model & text: no path to dump model, no model, no text dump, have been provided.")
}
if (!class(text) %in% c("character", "NULL")) {
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 (!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)){
if(!is.null(model)){
text = xgb.dump(model = model, with.stats = T)
} else if(!is.null(filename_dump)){
text <- readLines(filename_dump) %>% str_trim(side = "both")
}