[R] various R code maintenance (#1964)

* [R] xgb.save must work when handle in nil but raw exists

* [R] print.xgb.Booster should still print other info when handle is nil

* [R] rename internal function xgb.Booster to xgb.Booster.handle to make its intent clear

* [R] rename xgb.Booster.check to xgb.Booster.complete and make it visible; more docs

* [R] storing evaluation_log should depend only on watchlist, not on verbose

* [R] reduce the excessive chattiness of unit tests

* [R] only disable some tests in windows when it's not 64-bit

* [R] clean-up xgb.DMatrix

* [R] test xgb.DMatrix loading from libsvm text file

* [R] store feature_names in xgb.Booster, use them from utility functions

* [R] remove non-functional co-occurence computation from xgb.importance

* [R] verbose=0 is enough without a callback

* [R] added forgotten xgb.Booster.complete.Rd; cran check fixes

* [R] update installation instructions
This commit is contained in:
Vadim Khotilovich
2017-01-21 13:22:46 -06:00
committed by Tianqi Chen
parent a073a2c3d4
commit 2b5b96d760
27 changed files with 561 additions and 327 deletions

View File

@@ -3,14 +3,16 @@
#' Parse a boosted tree model text dump into a \code{data.table} structure.
#'
#' @param feature_names character vector of feature names. If the model already
#' contains feature names, this argument should be \code{NULL} (default value)
#' contains feature names, those would be used when \code{feature_names=NULL} (default value).
#' Non-null \code{feature_names} could be provided to override those in the model.
#' @param model object of class \code{xgb.Booster}
#' @param text \code{character} vector previously generated by the \code{xgb.dump}
#' function (where parameter \code{with_stats = TRUE} should have been set).
#' \code{text} takes precedence over \code{model}.
#' @param trees an integer vector of tree indices that should be parsed.
#' If set to \code{NULL}, all trees of the model are parsed.
#' It could be useful, e.g., in multiclass classification to get only
#' the trees of one certain class. IMPORTANT: the tree index in xgboost model
#' the trees of one certain class. IMPORTANT: the tree index in xgboost models
#' is zero-based (e.g., use \code{trees = 0:4} for first 5 trees).
#' @param ... currently not used.
#'
@@ -43,7 +45,9 @@
#' eta = 1, nthread = 2, nrounds = 2,objective = "binary:logistic")
#'
#' (dt <- xgb.model.dt.tree(colnames(agaricus.train$data), bst))
#'
#' # This bst has feature_names stored in it, so those would be used when
#' # the feature_names parameter is not provided:
#' (dt <- xgb.model.dt.tree(model = bst))
#'
#' # How to match feature names of splits that are following a current 'Yes' branch:
#'
@@ -53,11 +57,6 @@
xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
trees = NULL, ...){
check.deprecation(...)
if (!class(feature_names) %in% c("character", "NULL")) {
stop("feature_names: Has to be a vector of character\n",
" or NULL if the model dump already contains feature names.\n",
" Look at this function documentation to see where to get feature names.")
}
if (class(model) != "xgb.Booster" & class(text) != "character") {
stop("Either 'model' has to be an object of class xgb.Booster\n",
@@ -65,12 +64,19 @@ xgb.model.dt.tree <- function(feature_names = NULL, model = NULL, text = NULL,
" (or NULL if the model was provided).")
}
if (is.null(feature_names) && !is.null(model) && !is.null(model$feature_names))
feature_names <- model$feature_names
if (!class(feature_names) %in% c("character", "NULL")) {
stop("feature_names: Has to be a character vector")
}
if (!class(trees) %in% c("integer", "numeric", "NULL")) {
stop("trees: Has to be a vector of integers.")
}
if (is.null(text)){
text <- xgb.dump(model = model, with_stats = T)
text <- xgb.dump(model = model, with_stats = TRUE)
}
if (length(text) < 2 ||