Merge remote-tracking branch 'upstream/master'

R-package/NAMESPACE

@@ -1,4 +1,4 @@
-# Generated by roxygen2 (4.1.0): do not edit by hand
+# Generated by roxygen2 (4.0.1): do not edit by hand
 
 export(getinfo)
 export(setinfo)

R-package/R/predict.xgb.Booster.R

@@ -7,8 +7,8 @@ setClass("xgb.Booster")
 #' @param object Object of class "xgb.Boost"
 #' @param newdata takes \code{matrix}, \code{dgCMatrix}, local data file or 
 #'   \code{xgb.DMatrix}. 
-#' @param missing Missing is only used when input is dense matrix, pick a float
-#     value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.
+#' @param missing Missing is only used when input is dense matrix, pick a float 
+#'     value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.
 #' @param outputmargin whether the prediction should be shown in the original
 #'   value of sum of functions, when outputmargin=TRUE, the prediction is 
 #'   untransformed margin value. In logistic regression, outputmargin=T will

R-package/R/slice.xgb.DMatrix.R

@@ -28,6 +28,18 @@ setMethod("slice", signature = "xgb.DMatrix",
               if (class(object) != "xgb.DMatrix") {
                   stop("slice: first argument dtrain must be xgb.DMatrix")
               }
-              ret <- .Call("XGDMatrixSliceDMatrix_R", object, idxset, PACKAGE = "xgboost")
+              ret <- .Call("XGDMatrixSliceDMatrix_R", object, idxset, 
+                           PACKAGE = "xgboost")
+              
+              attr_list <- attributes(object)
+              nr <- xgb.numrow(object)
+              len <- sapply(attr_list,length)
+              ind <- which(len==nr)
+              if (length(ind)>0) {
+                  nms <- names(attr_list)[ind]
+                  for (i in 1:length(ind)) {
+                    attr(ret,nms[i]) <- attr(object,nms[i])[idxset]
+                  }
+              }
               return(structure(ret, class = "xgb.DMatrix"))
           })

R-package/R/xgb.DMatrix.R

@@ -6,7 +6,7 @@
 #'   indicating the data file.
 #' @param info a list of information of the xgb.DMatrix object
 #' @param missing Missing is only used when input is dense matrix, pick a float
-#     value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.
+#'     value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.
 #
 #' @param ... other information to pass to \code{info}.
 #' 

R-package/R/xgb.cv.R

@@ -32,7 +32,7 @@
 #' @param nfold number of folds used
 #' @param label option field, when data is Matrix
 #' @param missing Missing is only used when input is dense matrix, pick a float
-#     value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.
+#'     value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.
 #' @param prediction A logical value indicating whether to return the prediction vector.
 #' @param showsd \code{boolean}, whether show standard deviation of cross validation
 #' @param metrics, list of evaluation metrics to be used in corss validation,
@@ -134,4 +134,4 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
 # 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(".")
+globalVariables(".")

R-package/R/xgboost.R

@@ -5,7 +5,7 @@
 #' @param data takes \code{matrix}, \code{dgCMatrix}, local data file or 
 #'   \code{xgb.DMatrix}. 
 #' @param label the response variable. User should not set this field,
-#    if data is local data file or  \code{xgb.DMatrix}. 
+#'    if data is local data file or  \code{xgb.DMatrix}. 
 #' @param params the list of parameters. Commonly used ones are:
 #' \itemize{
 #'   \item \code{objective} objective function, common ones are
@@ -24,8 +24,8 @@
 #' @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 missing Missing is only used when input is dense matrix, pick a float
-#     value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.
+#' @param missing Missing is only used when input is dense matrix, pick a float 
+#'     value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.
 #' @param ... other parameters to pass to \code{params}.
 #' 
 #' @details 

R-package/man/agaricus.test.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgboost.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \docType{data}
 \name{agaricus.test}
 \alias{agaricus.test}

R-package/man/agaricus.train.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgboost.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \docType{data}
 \name{agaricus.train}
 \alias{agaricus.train}

R-package/man/getinfo.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/getinfo.xgb.DMatrix.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \docType{methods}
 \name{getinfo}
 \alias{getinfo}
@@ -13,9 +12,9 @@ getinfo(object, ...)
 \arguments{
 \item{object}{Object of class "xgb.DMatrix"}
 
-\item{...}{other parameters}
-
 \item{name}{the name of the field to get}
+
+\item{...}{other parameters}
 }
 \description{
 Get information of an xgb.DMatrix object

R-package/man/predict-xgb.Booster-method.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/predict.xgb.Booster.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \docType{methods}
 \name{predict,xgb.Booster-method}
 \alias{predict,xgb.Booster-method}
@@ -14,7 +13,8 @@
 \item{newdata}{takes \code{matrix}, \code{dgCMatrix}, local data file or
 \code{xgb.DMatrix}.}
 
-\item{missing}{Missing is only used when input is dense matrix, pick a float}
+\item{missing}{Missing is only used when input is dense matrix, pick a float
+value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.}
 
 \item{outputmargin}{whether the prediction should be shown in the original
 value of sum of functions, when outputmargin=TRUE, the prediction is

R-package/man/setinfo.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/setinfo.xgb.DMatrix.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \docType{methods}
 \name{setinfo}
 \alias{setinfo}
@@ -13,11 +12,11 @@ setinfo(object, ...)
 \arguments{
 \item{object}{Object of class "xgb.DMatrix"}
 
-\item{...}{other parameters}
-
 \item{name}{the name of the field to get}
 
 \item{info}{the specific field of information to set}
+
+\item{...}{other parameters}
 }
 \description{
 Set information of an xgb.DMatrix object

R-package/man/slice.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/slice.xgb.DMatrix.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \docType{methods}
 \name{slice}
 \alias{slice}
@@ -14,9 +13,9 @@ slice(object, ...)
 \arguments{
 \item{object}{Object of class "xgb.DMatrix"}
 
-\item{...}{other parameters}
-
 \item{idxset}{a integer vector of indices of rows needed}
+
+\item{...}{other parameters}
 }
 \description{
 Get a new DMatrix containing the specified rows of

R-package/man/xgb.DMatrix.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \name{xgb.DMatrix}
 \alias{xgb.DMatrix}
 \title{Contruct xgb.DMatrix object}
@@ -12,7 +11,8 @@ indicating the data file.}
 
 \item{info}{a list of information of the xgb.DMatrix object}
 
-\item{missing}{Missing is only used when input is dense matrix, pick a float}
+\item{missing}{Missing is only used when input is dense matrix, pick a float
+value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.}
 
 \item{...}{other information to pass to \code{info}.}
 }

R-package/man/xgb.DMatrix.save.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.save.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \name{xgb.DMatrix.save}
 \alias{xgb.DMatrix.save}
 \title{Save xgb.DMatrix object to binary file}

R-package/man/xgb.cv.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgb.cv.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \name{xgb.cv}
 \alias{xgb.cv}
 \title{Cross Validation}
@@ -32,7 +31,8 @@ xgb.cv(params = list(), data, nrounds, nfold, label = NULL,
 
 \item{label}{option field, when data is Matrix}
 
-\item{missing}{Missing is only used when input is dense matrix, pick a float}
+\item{missing}{Missing is only used when input is dense matrix, pick a float
+value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.}
 
 \item{prediction}{A logical value indicating whether to return the prediction vector.}
 

R-package/man/xgb.dump.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgb.dump.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \name{xgb.dump}
 \alias{xgb.dump}
 \title{Save xgboost model to text file}

R-package/man/xgb.importance.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgb.importance.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \name{xgb.importance}
 \alias{xgb.importance}
 \title{Show importance of features in a model}

R-package/man/xgb.load.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgb.load.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \name{xgb.load}
 \alias{xgb.load}
 \title{Load xgboost model from binary file}

R-package/man/xgb.model.dt.tree.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgb.model.dt.tree.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \name{xgb.model.dt.tree}
 \alias{xgb.model.dt.tree}
 \title{Convert tree model dump to data.table}

R-package/man/xgb.plot.tree.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgb.plot.tree.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \name{xgb.plot.tree}
 \alias{xgb.plot.tree}
 \title{Plot a boosted tree model}

R-package/man/xgb.save.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgb.save.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \name{xgb.save}
 \alias{xgb.save}
 \title{Save xgboost model to binary file}

R-package/man/xgb.train.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgb.train.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \name{xgb.train}
 \alias{xgb.train}
 \title{eXtreme Gradient Boosting Training}

R-package/man/xgboost.Rd

@@ -1,5 +1,4 @@
-% Generated by roxygen2 (4.1.0): do not edit by hand
-% Please edit documentation in R/xgboost.R
+% Generated by roxygen2 (4.0.1): do not edit by hand
 \name{xgboost}
 \alias{xgboost}
 \title{eXtreme Gradient Boosting (Tree) library}
@@ -11,9 +10,8 @@ xgboost(data = NULL, label = NULL, missing = NULL, params = list(),
 \item{data}{takes \code{matrix}, \code{dgCMatrix}, local data file or
 \code{xgb.DMatrix}.}
 
-\item{label}{the response variable. User should not set this field,}
-
-\item{missing}{Missing is only used when input is dense matrix, pick a float}
+\item{label}{the response variable. User should not set this field,
+if data is local data file or  \code{xgb.DMatrix}.}
 
 \item{params}{the list of parameters. Commonly used ones are:
 \itemize{
@@ -36,6 +34,9 @@ xgboost(data = NULL, label = NULL, missing = NULL, params = list(),
 information of performance. If 2, xgboost will print information of both
 performance and construction progress information}
 
+\item{missing}{Missing is only used when input is dense matrix, pick a float
+value that represents missing value. Sometime a data use 0 or other extreme value to represents missing values.}
+
 \item{...}{other parameters to pass to \code{params}.}
 }
 \description{

R-package/src/xgboost_R.cpp

@@ -71,13 +71,13 @@ extern "C" {
                                 SEXP missing) {
     _WrapperBegin();
     SEXP dim = getAttrib(mat, R_DimSymbol);
-    int nrow = INTEGER(dim)[0];
-    int ncol = INTEGER(dim)[1];    
+    bst_ulong nrow = static_cast<bst_ulong>(INTEGER(dim)[0]);
+    bst_ulong ncol = static_cast<bst_ulong>(INTEGER(dim)[1]);
     double *din = REAL(mat);
     std::vector<float> data(nrow * ncol);
     #pragma omp parallel for schedule(static)
-    for (int i = 0; i < nrow; ++i) {
-      for (int j = 0; j < ncol; ++j) {
+    for (bst_omp_uint i = 0; i < nrow; ++i) {
+      for (bst_ulong j = 0; j < ncol; ++j) {
         data[i * ncol +j] = din[i + nrow * j];
       }
     }