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

Polishing API + wording in function description #Rstat

Browse Source
This commit is contained in:
pommedeterresautee
2015-11-30 10:22:14 +01:00
parent 5e9f4dc973
commit 84ab71dd7e
8 changed files with 41 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
R-package/R/xgb.model.dt.tree.R
View File

@@ -14,7 +14,6 @@
#' @importFrom stringr str_split
#' @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.
@@ -54,20 +53,13 @@
#' xgb.model.dt.tree(agaricus.train$data@@Dimnames[[2]], model = bst)
#'
#' @export
xgb.model.dt.tree <- function(feature_names = NULL, filename_dump = NULL, model = NULL, text = NULL, n_first_tree = NULL){
xgb.model.dt.tree <- function(feature_names = 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") && 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(model) && is.null(text)){
stop("filename_dump & model & text: no path to dump model, no model, no text dump, have been provided.")
}
if (!class(model) %in% c("xgb.Booster", "NULL")) {
if (class(model) != "xgb.Booster") {
stop("model: Has to be an object of class xgb.Booster model generaged by the xgb.train function.")
}
@@ -79,12 +71,8 @@ xgb.model.dt.tree <- function(feature_names = NULL, filename_dump = NULL, model
stop("n_first_tree: Has to be a numeric vector of size 1.")
}
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")
}
text <- xgb.dump(model = model, with.stats = T)
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