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

[R] simplified the code; parameter style consistency

Browse Source
This commit is contained in:
Vadim Khotilovich
2016-06-27 01:57:57 -05:00
parent 8473b18c3d
commit 56bd442b31
4 changed files with 51 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
R-package/R/xgb.dump.R
View File

@@ -2,11 +2,6 @@
#'
#' Save a xgboost model to text file. Could be parsed later.
#'
#' @importFrom magrittr %>%
#' @importFrom stringr str_replace
#' @importFrom data.table fread
#' @importFrom data.table :=
#' @importFrom data.table setnames
#' @param model the model object.
#' @param fname the name of the text file where to save the model text dump. If not provided or set to \code{NULL} the function will return the model as a \code{character} vector.
#' @param fmap feature map file representing the type of feature.
@@ -15,10 +10,11 @@
#' See demo/ for walkthrough example in R, and
#' \url{https://github.com/dmlc/xgboost/blob/master/demo/data/featmap.txt}
#' for example Format.
#' @param with.stats whether dump statistics of splits
#' @param with_stats whether dump statistics of splits
#' When this option is on, the model dump comes with two additional statistics:
#' gain is the approximate loss function gain we get in each split;
#' cover is the sum of second order gradient in each node.
#' @param ... currently not used
#'
#' @return
#' if fname is not provided or set to \code{NULL} the function will return the model as a \code{character} vector. Otherwise it will return \code{TRUE}.
@@ -28,43 +24,36 @@
#' data(agaricus.test, package='xgboost')
#' train <- agaricus.train
#' test <- agaricus.test
#' bst <- xgboost(data = train$data, label = train$label, max.depth = 2,
#' eta = 1, nthread = 2, nround = 2,objective = "binary:logistic")
#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
#' eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
#' # save the model in file 'xgb.model.dump'
#' xgb.dump(bst, 'xgb.model.dump', with.stats = TRUE)
#' xgb.dump(bst, 'xgb.model.dump', with_stats = TRUE)
#'
#' # print the model without saving it to a file
#' print(xgb.dump(bst))
#' @export
xgb.dump <- function(model = NULL, fname = NULL, fmap = "", with.stats=FALSE) {
if (class(model) != "xgb.Booster") {
stop("model: argument must be type xgb.Booster")
xgb.dump <- function(model = NULL, fname = NULL, fmap = "", with_stats=FALSE, ...) {
check.deprecation(...)
if (class(model) != "xgb.Booster")
stop("model: argument must be of type xgb.Booster")
if (!(class(fname) %in% c("character", "NULL") && length(fname) <= 1))
stop("fname: argument must be of type character (when provided)")
if (!(class(fmap) %in% c("character", "NULL") && length(fmap) <= 1))
stop("fmap: argument must be of type character (when provided)")
model <- xgb.Booster.check(model)
model_dump <- .Call("XGBoosterDumpModel_R", model$handle, fmap, as.integer(with_stats), PACKAGE = "xgboost")
if (is.null(fname))
model_dump <- str_replace_all(model_dump, '\t', '')
model_dump <- unlist(str_split(model_dump, '\n'))
model_dump <- grep('(^$|^0$)', model_dump, invert = TRUE, value = TRUE)
if (is.null(fname)) {
return(model_dump)
} else {
model <- xgb.Booster.check(model)
}
if (!(class(fname) %in% c("character", "NULL") && length(fname) <= 1)) {
stop("fname: argument must be type character (when provided)")
}
if (!(class(fmap) %in% c("character", "NULL") && length(fname) <= 1)) {
stop("fmap: argument must be type character (when provided)")
}
longString <- .Call("XGBoosterDumpModel_R", model$handle, fmap, as.integer(with.stats), PACKAGE = "xgboost")
dt <- fread(paste(longString, collapse = ""), sep = "\n", header = F)
setnames(dt, "Lines")
if(is.null(fname)) {
result <- dt[Lines != "0"][, Lines := str_replace(Lines, "^\t+", "")][Lines != ""][, paste(Lines)]
return(result)
} else {
result <- dt[Lines != "0"][Lines != ""][, paste(Lines)] %>% writeLines(fname)
writeLines(model_dump, fname)
return(TRUE)
}
}
# Avoid error messages during CRAN check.
# The reason is that these variables are never declared
# They are mainly column names inferred by Data.table...
globalVariables(c("Lines", "."))