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

Merge branch 'master' of https://github.com/pommedeterresautee/xgboost

Browse Source
This commit is contained in:
pommedeterresautee
2015-06-16 21:40:09 +02:00
parent ad2e93f6c5 ab219d3331
commit 37714eb331
42 changed files with 1072 additions and 298 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
R-package/DESCRIPTION
View File

@@ -1,8 +1,8 @@
Package: xgboost
Type: Package
Title: eXtreme Gradient Boosting
Version: 0.3-4
Date: 2014-12-28
Version: 0.4-0
Date: 2015-05-11
Author: Tianqi Chen <tianqi.tchen@gmail.com>, Tong He <hetong007@gmail.com>, Michael Benesty <michael@benesty.fr>
Maintainer: Tong He <hetong007@gmail.com>
Description: Xgboost is short for eXtreme Gradient Boosting, which is an

78
R-package/R/xgb.cv.R
View File

@@ -54,6 +54,13 @@
#' @param folds \code{list} provides a possibility of using a list of pre-defined CV folds (each element must be a vector of fold's indices).
#' If folds are supplied, the nfold and stratified parameters would be ignored.
#' @param verbose \code{boolean}, print the statistics during the process
#' @param print.every.n Print every N progress messages when \code{verbose>0}. Default is 1 which means all messages are printed.
#' @param early.stop.round If \code{NULL}, the early stopping function is not triggered.
#' If set to an integer \code{k}, training with a validation set will stop if the performance
#' keeps getting worse consecutively for \code{k} rounds.
#' @param maximize If \code{feval} and \code{early.stop.round} are set, then \code{maximize} must be set as well.
#' \code{maximize=TRUE} means the larger the evaluation score the better.
#'
#' @param ... other parameters to pass to \code{params}.
#'
#' @return
@@ -86,7 +93,8 @@
#'
xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing = NULL,
prediction = FALSE, showsd = TRUE, metrics=list(),
obj = NULL, feval = NULL, stratified = TRUE, folds = NULL, verbose = T,...) {
obj = NULL, feval = NULL, stratified = TRUE, folds = NULL, verbose = T, print.every.n=1L,
early.stop.round = NULL, maximize = NULL, ...) {
if (typeof(params) != "list") {
stop("xgb.cv: first argument params must be list")
}
@@ -109,7 +117,50 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
for (mc in metrics) {
params <- append(params, list("eval_metric"=mc))
}
# customized objective and evaluation metric interface
if (!is.null(params$objective) && !is.null(obj))
stop("xgb.cv: cannot assign two different objectives")
if (!is.null(params$objective))
if (class(params$objective)=='function') {
obj = params$objective
params$objective = NULL
}
if (!is.null(params$eval_metric) && !is.null(feval))
stop("xgb.cv: cannot assign two different evaluation metrics")
if (!is.null(params$eval_metric))
if (class(params$eval_metric)=='function') {
feval = params$eval_metric
params$eval_metric = NULL
}
# Early Stopping
if (!is.null(early.stop.round)){
if (!is.null(feval) && is.null(maximize))
stop('Please set maximize to note whether the model is maximizing the evaluation or not.')
if (is.null(maximize) && is.null(params$eval_metric))
stop('Please set maximize to note whether the model is maximizing the evaluation or not.')
if (is.null(maximize))
{
if (params$eval_metric %in% c('rmse','logloss','error','merror','mlogloss')) {
maximize = FALSE
} else {
maximize = TRUE
}
}
if (maximize) {
bestScore = 0
} else {
bestScore = Inf
}
bestInd = 0
earlyStopflag = FALSE
if (length(metrics)>1)
warning('Only the first metric is used for early stopping process.')
}
xgb_folds <- xgb.cv.mknfold(dtrain, nfold, params, stratified, folds)
obj_type = params[['objective']]
mat_pred = FALSE
@@ -124,6 +175,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
else
predictValues <- rep(0,xgb.numrow(dtrain))
history <- c()
print.every.n = max(as.integer(print.every.n), 1L)
for (i in 1:nrounds) {
msg <- list()
for (k in 1:nfold) {
@@ -148,7 +200,27 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
}
ret <- xgb.cv.aggcv(msg, showsd)
history <- c(history, ret)
if(verbose) paste(ret, "\n", sep="") %>% cat
if(verbose)
if (0==(i-1L)%%print.every.n)
cat(ret, "\n", sep="")
# early_Stopping
if (!is.null(early.stop.round)){
score = strsplit(ret,'\\s+')[[1]][1+length(metrics)+2]
score = strsplit(score,'\\+|:')[[1]][[2]]
score = as.numeric(score)
if ((maximize && score>bestScore) || (!maximize && score<bestScore)) {
bestScore = score
bestInd = i
} else {
if (i-bestInd>=early.stop.round) {
earlyStopflag = TRUE
cat('Stopping. Best iteration:',bestInd)
break
}
}
}
}
colnames <- str_split(string = history[1], pattern = "\t")[[1]] %>% .[2:length(.)] %>% str_extract(".*:") %>% str_replace(":","") %>% str_replace("-", ".")

88
R-package/R/xgb.train.R
View File

@@ -36,7 +36,7 @@
#' 3. Task Parameters
#'
#' \itemize{
#' \item \code{objective} specify the learning task and the corresponding learning objective, and the objective options are below:
#' \item \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it. The default objective options are below:
#' \itemize{
#' \item \code{reg:linear} linear regression (Default).
#' \item \code{reg:logistic} logistic regression.
@@ -48,7 +48,7 @@
#' \item \code{rank:pairwise} set xgboost to do ranking task by minimizing the pairwise loss.
#' }
#' \item \code{base_score} the initial prediction score of all instances, global bias. Default: 0.5
#' \item \code{eval_metric} evaluation metrics for validation data. Default: metric will be assigned according to objective(rmse for regression, and error for classification, mean average precision for ranking). List is provided in detail section.
#' \item \code{eval_metric} evaluation metrics for validation data. Users can pass a self-defined function to it. Default: metric will be assigned according to objective(rmse for regression, and error for classification, mean average precision for ranking). List is provided in detail section.
#' }
#'
#' @param data takes an \code{xgb.DMatrix} as the input.
@@ -66,7 +66,12 @@
#' prediction and dtrain,
#' @param verbose If 0, xgboost will stay silent. If 1, xgboost will print
#' information of performance. If 2, xgboost will print information of both
#'
#' @param print.every.n Print every N progress messages when \code{verbose>0}. Default is 1 which means all messages are printed.
#' @param early.stop.round If \code{NULL}, the early stopping function is not triggered.
#' If set to an integer \code{k}, training with a validation set will stop if the performance
#' keeps getting worse consecutively for \code{k} rounds.
#' @param maximize If \code{feval} and \code{early.stop.round} are set, then \code{maximize} must be set as well.
#' \code{maximize=TRUE} means the larger the evaluation score the better.
#' @param ... other parameters to pass to \code{params}.
#'
#' @details
@@ -98,7 +103,6 @@
#' dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
#' dtest <- dtrain
#' watchlist <- list(eval = dtest, train = dtrain)
#' param <- list(max.depth = 2, eta = 1, silent = 1)
#' logregobj <- function(preds, dtrain) {
#' labels <- getinfo(dtrain, "label")
#' preds <- 1/(1 + exp(-preds))
@@ -111,11 +115,13 @@
#' err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
#' return(list(metric = "error", value = err))
#' }
#' bst <- xgb.train(param, dtrain, nthread = 2, nround = 2, watchlist, logregobj, evalerror)
#' param <- list(max.depth = 2, eta = 1, silent = 1, objective=logregobj,eval_metric=evalerror)
#' bst <- xgb.train(param, dtrain, nthread = 2, nround = 2, watchlist)
#' @export
#'
xgb.train <- function(params=list(), data, nrounds, watchlist = list(),
obj = NULL, feval = NULL, verbose = 1, ...) {
obj = NULL, feval = NULL, verbose = 1, print.every.n=1L,
early.stop.round = NULL, maximize = NULL, ...) {
dtrain <- data
if (typeof(params) != "list") {
stop("xgb.train: first argument params must be list")
@@ -130,19 +136,85 @@ xgb.train <- function(params=list(), data, nrounds, watchlist = list(),
}
if (length(watchlist) != 0 && verbose == 0) {
warning('watchlist is provided but verbose=0, no evaluation information will be printed')
watchlist <- list()
}
params = append(params, list(...))
# customized objective and evaluation metric interface
if (!is.null(params$objective) && !is.null(obj))
stop("xgb.train: cannot assign two different objectives")
if (!is.null(params$objective))
if (class(params$objective)=='function') {
obj = params$objective
params$objective = NULL
}
if (!is.null(params$eval_metric) && !is.null(feval))
stop("xgb.train: cannot assign two different evaluation metrics")
if (!is.null(params$eval_metric))
if (class(params$eval_metric)=='function') {
feval = params$eval_metric
params$eval_metric = NULL
}
# Early stopping
if (!is.null(early.stop.round)){
if (!is.null(feval) && is.null(maximize))
stop('Please set maximize to note whether the model is maximizing the evaluation or not.')
if (length(watchlist) == 0)
stop('For early stopping you need at least one set in watchlist.')
if (is.null(maximize) && is.null(params$eval_metric))
stop('Please set maximize to note whether the model is maximizing the evaluation or not.')
if (is.null(maximize))
{
if (params$eval_metric %in% c('rmse','logloss','error','merror','mlogloss')) {
maximize = FALSE
} else {
maximize = TRUE
}
}
if (maximize) {
bestScore = 0
} else {
bestScore = Inf
}
bestInd = 0
earlyStopflag = FALSE
if (length(watchlist)>1)
warning('Only the first data set in watchlist is used for early stopping process.')
}
handle <- xgb.Booster(params, append(watchlist, dtrain))
bst <- xgb.handleToBooster(handle)
print.every.n=max( as.integer(print.every.n), 1L)
for (i in 1:nrounds) {
succ <- xgb.iter.update(bst$handle, dtrain, i - 1, obj)
if (length(watchlist) != 0) {
msg <- xgb.iter.eval(bst$handle, watchlist, i - 1, feval)
cat(paste(msg, "\n", sep=""))
if (0== ( (i-1) %% print.every.n))
cat(paste(msg, "\n", sep=""))
if (!is.null(early.stop.round))
{
score = strsplit(msg,':|\\s+')[[1]][3]
score = as.numeric(score)
if ((maximize && score>bestScore) || (!maximize && score<bestScore)) {
bestScore = score
bestInd = i
} else {
if (i-bestInd>=early.stop.round) {
earlyStopflag = TRUE
cat('Stopping. Best iteration:',bestInd)
break
}
}
}
}
}
bst <- xgb.Booster.check(bst)
if (!is.null(early.stop.round)) {
bst$bestScore = bestScore
bst$bestInd = bestInd
}
return(bst)
}

12
R-package/R/xgboost.R
View File

@@ -28,8 +28,14 @@
#' @param verbose If 0, xgboost will stay silent. If 1, xgboost will print
#' information of performance. If 2, xgboost will print information of both
#' performance and construction progress information
#' @param print.every.n Print every N progress messages when \code{verbose>0}. Default is 1 which means all messages are printed.
#' @param missing Missing is only used when input is dense matrix, pick a float
#' value that represents missing value. Sometimes a data use 0 or other extreme value to represents missing values.
#' @param early.stop.round If \code{NULL}, the early stopping function is not triggered.
#' If set to an integer \code{k}, training with a validation set will stop if the performance
#' keeps getting worse consecutively for \code{k} rounds.
#' @param maximize If \code{feval} and \code{early.stop.round} are set, then \code{maximize} must be set as well.
#' \code{maximize=TRUE} means the larger the evaluation score the better.
#' @param ... other parameters to pass to \code{params}.
#'
#' @details
@@ -51,7 +57,8 @@
#' @export
#'
xgboost <- function(data = NULL, label = NULL, missing = NULL, params = list(), nrounds,
verbose = 1, ...) {
verbose = 1, print.every.n = 1L, early.stop.round = NULL,
maximize = NULL, ...) {
if (is.null(missing)) {
dtrain <- xgb.get.DMatrix(data, label)
} else {
@@ -66,7 +73,8 @@ xgboost <- function(data = NULL, label = NULL, missing = NULL, params = list(),
watchlist <- list()
}
bst <- xgb.train(params, dtrain, nrounds, watchlist, verbose=verbose)
bst <- xgb.train(params, dtrain, nrounds, watchlist, verbose = verbose, print.every.n=print.every.n,
early.stop.round = early.stop.round)
return(bst)
}

5
R-package/README.md
View File

@@ -8,11 +8,6 @@ For up-to-date version (which is recommended), please install from github. Windo
devtools::install_github('dmlc/xgboost',subdir='R-package')
```
For stable version on CRAN, please run
```r
install.packages('xgboost')
```
## Examples

2
R-package/demo/00Index
View File

@@ -6,3 +6,5 @@ generalized_linear_model Generalized Linear Model
cross_validation Cross validation
create_sparse_matrix Create Sparse Matrix
predict_leaf_indices Predicting the corresponding leaves
early_stopping Early Stop in training
poisson_regression Poisson Regression on count data

6
R-package/demo/cross_validation.R
View File

@@ -40,10 +40,10 @@ evalerror <- function(preds, dtrain) {
return(list(metric = "error", value = err))
}
param <- list(max.depth=2,eta=1,silent=1)
param <- list(max.depth=2,eta=1,silent=1,
objective = logregobj, eval_metric = evalerror)
# train with customized objective
xgb.cv(param, dtrain, nround, nfold = 5,
obj = logregobj, feval=evalerror)
xgb.cv(param, dtrain, nround, nfold = 5)
# do cross validation with prediction values for each fold
res <- xgb.cv(param, dtrain, nround, nfold=5, prediction = TRUE)

9
R-package/demo/custom_objective.R
View File

@@ -8,7 +8,6 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
# note: for customized objective function, we leave objective as default
# note: what we are getting is margin value in prediction
# you must know what you are doing
param <- list(max.depth=2,eta=1,nthread = 2, silent=1)
watchlist <- list(eval = dtest, train = dtrain)
num_round <- 2
@@ -33,10 +32,13 @@ evalerror <- function(preds, dtrain) {
err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
return(list(metric = "error", value = err))
}
param <- list(max.depth=2,eta=1,nthread = 2, silent=1,
objective=logregobj, eval_metric=evalerror)
print ('start training with user customized objective')
# training with customized objective, we can also do step by step training
# simply look at xgboost.py's implementation of train
bst <- xgb.train(param, dtrain, num_round, watchlist, logregobj, evalerror)
bst <- xgb.train(param, dtrain, num_round, watchlist)
#
# there can be cases where you want additional information
@@ -59,4 +61,5 @@ logregobjattr <- function(preds, dtrain) {
print ('start training with user customized objective, with additional attributes in DMatrix')
# training with customized objective, we can also do step by step training
# simply look at xgboost.py's implementation of train
bst <- xgb.train(param, dtrain, num_round, watchlist, logregobjattr, evalerror)
bst <- xgb.train(param, dtrain, num_round, watchlist,
objective=logregobj, eval_metric=evalerror)

40
R-package/demo/early_stopping.R Normal file
View File

@@ -0,0 +1,40 @@
require(xgboost)
# load in the agaricus dataset
data(agaricus.train, package='xgboost')
data(agaricus.test, package='xgboost')
dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
# note: for customized objective function, we leave objective as default
# note: what we are getting is margin value in prediction
# you must know what you are doing
param <- list(max.depth=2,eta=1,nthread = 2, silent=1)
watchlist <- list(eval = dtest)
num_round <- 20
# user define objective function, given prediction, return gradient and second order gradient
# this is loglikelihood loss
logregobj <- function(preds, dtrain) {
labels <- getinfo(dtrain, "label")
preds <- 1/(1 + exp(-preds))
grad <- preds - labels
hess <- preds * (1 - preds)
return(list(grad = grad, hess = hess))
}
# user defined evaluation function, return a pair metric_name, result
# NOTE: when you do customized loss function, the default prediction value is margin
# this may make buildin evalution metric not function properly
# for example, we are doing logistic loss, the prediction is score before logistic transformation
# the buildin evaluation error assumes input is after logistic transformation
# Take this in mind when you use the customization, and maybe you need write customized evaluation function
evalerror <- function(preds, dtrain) {
labels <- getinfo(dtrain, "label")
err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
return(list(metric = "error", value = err))
}
print ('start training with early Stopping setting')
bst <- xgb.train(param, dtrain, num_round, watchlist,
objective = logregobj, eval_metric = evalerror, maximize = FALSE,
early.stop.round = 3)
bst <- xgb.cv(param, dtrain, num_round, nfold = 5,
objective = logregobj, eval_metric = evalerror,
maximize = FALSE, early.stop.round = 3)

7
R-package/demo/poisson_regression.R Normal file
View File

@@ -0,0 +1,7 @@
data(mtcars)
head(mtcars)
bst = xgboost(data=as.matrix(mtcars[,-11]),label=mtcars[,11],
objective='count:poisson',nrounds=5)
pred = predict(bst,as.matrix(mtcars[,-11]))
sqrt(mean((pred-mtcars[,11])^2))

2
R-package/demo/runall.R
View File

@@ -7,3 +7,5 @@ demo(generalized_linear_model)
demo(cross_validation)
demo(create_sparse_matrix)
demo(predict_leaf_indices)
demo(early_stopping)
demo(poisson_regression)

12
R-package/man/xgb.cv.Rd
View File

@@ -7,7 +7,8 @@
xgb.cv(params = list(), data, nrounds, nfold, label = NULL,
missing = NULL, prediction = FALSE, showsd = TRUE, metrics = list(),
obj = NULL, feval = NULL, stratified = TRUE, folds = NULL,
verbose = T, ...)
verbose = T, print.every.n = 1L, early.stop.round = NULL,
maximize = NULL, ...)
}
\arguments{
\item{params}{the list of parameters. Commonly used ones are:
@@ -65,6 +66,15 @@ If folds are supplied, the nfold and stratified parameters would be ignored.}
\item{verbose}{\code{boolean}, print the statistics during the process}
\item{print.every.n}{Print every N progress messages when \code{verbose>0}. Default is 1 which means all messages are printed.}
\item{early.stop.round}{If \code{NULL}, the early stopping function is not triggered.
If set to an integer \code{k}, training with a validation set will stop if the performance
keeps getting worse consecutively for \code{k} rounds.}
\item{maximize}{If \code{feval} and \code{early.stop.round} are set, then \code{maximize} must be set as well.
\code{maximize=TRUE} means the larger the evaluation score the better.}
\item{...}{other parameters to pass to \code{params}.}
}
\value{

22
R-package/man/xgb.train.Rd
View File

@@ -5,7 +5,8 @@
\title{eXtreme Gradient Boosting Training}
\usage{
xgb.train(params = list(), data, nrounds, watchlist = list(), obj = NULL,
feval = NULL, verbose = 1, ...)
feval = NULL, verbose = 1, print.every.n = 1L,
early.stop.round = NULL, maximize = NULL, ...)
}
\arguments{
\item{params}{the list of parameters.
@@ -42,7 +43,7 @@ xgb.train(params = list(), data, nrounds, watchlist = list(), obj = NULL,
3. Task Parameters
\itemize{
\item \code{objective} specify the learning task and the corresponding learning objective, and the objective options are below:
\item \code{objective} specify the learning task and the corresponding learning objective, users can pass a self-defined function to it. The default objective options are below:
\itemize{
\item \code{reg:linear} linear regression (Default).
\item \code{reg:logistic} logistic regression.
@@ -54,7 +55,7 @@ xgb.train(params = list(), data, nrounds, watchlist = list(), obj = NULL,
\item \code{rank:pairwise} set xgboost to do ranking task by minimizing the pairwise loss.
}
\item \code{base_score} the initial prediction score of all instances, global bias. Default: 0.5
\item \code{eval_metric} evaluation metrics for validation data. Default: metric will be assigned according to objective(rmse for regression, and error for classification, mean average precision for ranking). List is provided in detail section.
\item \code{eval_metric} evaluation metrics for validation data. Users can pass a self-defined function to it. Default: metric will be assigned according to objective(rmse for regression, and error for classification, mean average precision for ranking). List is provided in detail section.
}}
\item{data}{takes an \code{xgb.DMatrix} as the input.}
@@ -75,7 +76,16 @@ gradient with given prediction and dtrain,}
prediction and dtrain,}
\item{verbose}{If 0, xgboost will stay silent. If 1, xgboost will print
information of performance. If 2, xgboost will print information of both}
information of performance. If 2, xgboost will print information of both}
\item{print.every.n}{Print every N progress messages when \code{verbose>0}. Default is 1 which means all messages are printed.}
\item{early.stop.round}{If \code{NULL}, the early stopping function is not triggered.
If set to an integer \code{k}, training with a validation set will stop if the performance
keeps getting worse consecutively for \code{k} rounds.}
\item{maximize}{If \code{feval} and \code{early.stop.round} are set, then \code{maximize} must be set as well.
\code{maximize=TRUE} means the larger the evaluation score the better.}
\item{...}{other parameters to pass to \code{params}.}
}
@@ -110,7 +120,6 @@ data(agaricus.train, package='xgboost')
dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
dtest <- dtrain
watchlist <- list(eval = dtest, train = dtrain)
param <- list(max.depth = 2, eta = 1, silent = 1)
logregobj <- function(preds, dtrain) {
labels <- getinfo(dtrain, "label")
preds <- 1/(1 + exp(-preds))
@@ -123,6 +132,7 @@ evalerror <- function(preds, dtrain) {
err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
return(list(metric = "error", value = err))
}
bst <- xgb.train(param, dtrain, nthread = 2, nround = 2, watchlist, logregobj, evalerror)
param <- list(max.depth = 2, eta = 1, silent = 1, objective=logregobj,eval_metric=evalerror)
bst <- xgb.train(param, dtrain, nthread = 2, nround = 2, watchlist)
}

12
R-package/man/xgboost.Rd
View File

@@ -5,7 +5,8 @@
\title{eXtreme Gradient Boosting (Tree) library}
\usage{
xgboost(data = NULL, label = NULL, missing = NULL, params = list(),
nrounds, verbose = 1, ...)
nrounds, verbose = 1, print.every.n = 1L, early.stop.round = NULL,
maximize = NULL, ...)
}
\arguments{
\item{data}{takes \code{matrix}, \code{dgCMatrix}, local data file or
@@ -41,6 +42,15 @@ Commonly used ones are:
information of performance. If 2, xgboost will print information of both
performance and construction progress information}
\item{print.every.n}{Print every N progress messages when \code{verbose>0}. Default is 1 which means all messages are printed.}
\item{early.stop.round}{If \code{NULL}, the early stopping function is not triggered.
If set to an integer \code{k}, training with a validation set will stop if the performance
keeps getting worse consecutively for \code{k} rounds.}
\item{maximize}{If \code{feval} and \code{early.stop.round} are set, then \code{maximize} must be set as well.
\code{maximize=TRUE} means the larger the evaluation score the better.}
\item{...}{other parameters to pass to \code{params}.}
}
\description{

38
R-package/src/xgboost_R.cpp
View File

@@ -70,10 +70,10 @@ extern "C" {
SEXP XGDMatrixCreateFromFile_R(SEXP fname, SEXP silent) {
_WrapperBegin();
void *handle = XGDMatrixCreateFromFile(CHAR(asChar(fname)), asInteger(silent));
_WrapperEnd();
SEXP ret = PROTECT(R_MakeExternalPtr(handle, R_NilValue, R_NilValue));
R_RegisterCFinalizerEx(ret, _DMatrixFinalizer, TRUE);
UNPROTECT(1);
_WrapperEnd();
return ret;
}
SEXP XGDMatrixCreateFromMat_R(SEXP mat,
@@ -91,10 +91,10 @@ extern "C" {
}
}
void *handle = XGDMatrixCreateFromMat(BeginPtr(data), nrow, ncol, asReal(missing));
_WrapperEnd();
SEXP ret = PROTECT(R_MakeExternalPtr(handle, R_NilValue, R_NilValue));
R_RegisterCFinalizerEx(ret, _DMatrixFinalizer, TRUE);
UNPROTECT(1);
_WrapperEnd();
return ret;
}
SEXP XGDMatrixCreateFromCSC_R(SEXP indptr,
@@ -120,10 +120,10 @@ extern "C" {
}
void *handle = XGDMatrixCreateFromCSC(BeginPtr(col_ptr_), BeginPtr(indices_),
BeginPtr(data_), nindptr, ndata);
_WrapperEnd();
SEXP ret = PROTECT(R_MakeExternalPtr(handle, R_NilValue, R_NilValue));
R_RegisterCFinalizerEx(ret, _DMatrixFinalizer, TRUE);
UNPROTECT(1);
_WrapperEnd();
return ret;
}
SEXP XGDMatrixSliceDMatrix_R(SEXP handle, SEXP idxset) {
@@ -134,10 +134,10 @@ extern "C" {
idxvec[i] = INTEGER(idxset)[i] - 1;
}
void *res = XGDMatrixSliceDMatrix(R_ExternalPtrAddr(handle), BeginPtr(idxvec), len);
_WrapperEnd();
SEXP ret = PROTECT(R_MakeExternalPtr(res, R_NilValue, R_NilValue));
R_RegisterCFinalizerEx(ret, _DMatrixFinalizer, TRUE);
UNPROTECT(1);
_WrapperEnd();
return ret;
}
void XGDMatrixSaveBinary_R(SEXP handle, SEXP fname, SEXP silent) {
@@ -157,10 +157,7 @@ extern "C" {
vec[i] = static_cast<unsigned>(INTEGER(array)[i]);
}
XGDMatrixSetGroup(R_ExternalPtrAddr(handle), BeginPtr(vec), len);
_WrapperEnd();
return;
}
{
} else {
std::vector<float> vec(len);
#pragma omp parallel for schedule(static)
for (int i = 0; i < len; ++i) {
@@ -177,12 +174,12 @@ extern "C" {
bst_ulong olen;
const float *res = XGDMatrixGetFloatInfo(R_ExternalPtrAddr(handle),
CHAR(asChar(field)), &olen);
_WrapperEnd();
SEXP ret = PROTECT(allocVector(REALSXP, olen));
for (size_t i = 0; i < olen; ++i) {
REAL(ret)[i] = res[i];
}
UNPROTECT(1);
_WrapperEnd();
return ret;
}
SEXP XGDMatrixNumRow_R(SEXP handle) {
@@ -203,10 +200,10 @@ extern "C" {
dvec.push_back(R_ExternalPtrAddr(VECTOR_ELT(dmats, i)));
}
void *handle = XGBoosterCreate(BeginPtr(dvec), dvec.size());
_WrapperEnd();
SEXP ret = PROTECT(R_MakeExternalPtr(handle, R_NilValue, R_NilValue));
R_RegisterCFinalizerEx(ret, _BoosterFinalizer, TRUE);
UNPROTECT(1);
_WrapperEnd();
return ret;
}
void XGBoosterSetParam_R(SEXP handle, SEXP name, SEXP val) {
@@ -252,10 +249,12 @@ extern "C" {
for (int i = 0; i < len; ++i) {
vec_sptr.push_back(vec_names[i].c_str());
}
const char *ret =
XGBoosterEvalOneIter(R_ExternalPtrAddr(handle),
asInteger(iter),
BeginPtr(vec_dmats), BeginPtr(vec_sptr), len);
_WrapperEnd();
return mkString(XGBoosterEvalOneIter(R_ExternalPtrAddr(handle),
asInteger(iter),
BeginPtr(vec_dmats), BeginPtr(vec_sptr), len));
return mkString(ret);
}
SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP option_mask, SEXP ntree_limit) {
_WrapperBegin();
@@ -265,12 +264,12 @@ extern "C" {
asInteger(option_mask),
asInteger(ntree_limit),
&olen);
_WrapperEnd();
SEXP ret = PROTECT(allocVector(REALSXP, olen));
for (size_t i = 0; i < olen; ++i) {
REAL(ret)[i] = res[i];
}
UNPROTECT(1);
_WrapperEnd();
return ret;
}
void XGBoosterLoadModel_R(SEXP handle, SEXP fname) {
@@ -305,17 +304,18 @@ extern "C" {
SEXP XGBoosterDumpModel_R(SEXP handle, SEXP fmap, SEXP with_stats) {
_WrapperBegin();
bst_ulong olen;
const char **res = XGBoosterDumpModel(R_ExternalPtrAddr(handle),
CHAR(asChar(fmap)),
asInteger(with_stats),
&olen);
const char **res =
XGBoosterDumpModel(R_ExternalPtrAddr(handle),
CHAR(asChar(fmap)),
asInteger(with_stats),
&olen);
_WrapperEnd();
SEXP out = PROTECT(allocVector(STRSXP, olen));
for (size_t i = 0; i < olen; ++i) {
stringstream stream;
stream << "booster["<<i<<"]\n" << res[i];
SET_STRING_ELT(out, i, mkChar(stream.str().c_str()));
}
_WrapperEnd();
UNPROTECT(1);
return out;
}

6
R-package/vignettes/xgboostPresentation.Rmd
View File

@@ -57,11 +57,9 @@ devtools::install_github('dmlc/xgboost', subdir='R-package')
Cran version
------------
For stable version on *CRAN*, run:
As of 2015-03-13, ‘xgboost’ was removed from the CRAN repository.
```{r installCran, eval=FALSE}
install.packages('xgboost')
```
Formerly available versions can be obtained from the CRAN [archive](http://cran.r-project.org/src/contrib/Archive/xgboost)
Learning
========