Merge remote-tracking branch 'upstream/master'

.gitignore

@@ -54,3 +54,4 @@ train*
 rabit
 .Rbuildignore
 R-package.Rproj
+

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

@@ -8,7 +8,7 @@ setClass("xgb.Booster")
 #' @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.
+#'     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,

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
@@ -25,7 +25,7 @@
 #'   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.
+#'     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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgboost.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgboost.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/getinfo.xgb.DMatrix.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/predict.xgb.Booster.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/setinfo.xgb.DMatrix.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/slice.xgb.DMatrix.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgb.DMatrix.save.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgb.cv.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgb.dump.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgb.importance.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgb.load.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgb.model.dt.tree.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgb.plot.tree.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgb.save.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgb.train.R
 \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
+% Generated by roxygen2 (4.0.1): do not edit by hand
-% Please edit documentation in R/xgboost.R
 \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{label}{the response variable. User should not set this field,
-
+if data is local data file or  \code{xgb.DMatrix}.}
-\item{missing}{Missing is only used when input is dense matrix, pick a float}
 
 \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];
+    bst_ulong nrow = static_cast<bst_ulong>(INTEGER(dim)[0]);
-    int ncol = INTEGER(dim)[1];    
+    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 (bst_omp_uint i = 0; i < nrow; ++i) {
-      for (int j = 0; j < ncol; ++j) {
+      for (bst_ulong j = 0; j < ncol; ++j) {
         data[i * ncol +j] = din[i + nrow * j];
       }
     }

README.md

@@ -1,7 +1,7 @@
 xgboost: eXtreme Gradient Boosting 
 ======
 An optimized general purpose gradient boosting library. The library is parallelized, and also provides an optimized distributed version.
-It implements machine learning algorithm under gradient boosting framework, including generalized linear model and gradient boosted regression tree. 
+It implements machine learning algorithm under gradient boosting framework, including generalized linear model and gradient boosted regression tree (GBDT). XGBoost can also also distributed and scale to even larger data.
 
 Contributors: https://github.com/tqchen/xgboost/graphs/contributors
 

demo/.gitignore

@@ -0,0 +1 @@
+*.libsvm

demo/yearpredMSD/README.md

@@ -0,0 +1,9 @@
+Demonstrating how to use XGBoost on [Year Prediction task of Million Song Dataset](https://archive.ics.uci.edu/ml/datasets/YearPredictionMSD)
+
+1. Run runexp.sh
+```bash
+./runexp.sh
+```
+
+You can also use the script to prepare LIBSVM format, and run the [Distributed Version](../../multi-node).
+Note that though that normally you only need to use single machine for dataset at this scale, and use distributed version for larger scale dataset.

demo/yearpredMSD/csv2libsvm.py

@@ -0,0 +1,14 @@
+#!/usr/bin/python
+import sys
+
+if len(sys.argv) < 3:
+    print 'Usage: <csv> <libsvm>'
+    print 'convert a all numerical csv to libsvm'
+
+fo = open(sys.argv[2], 'w')
+for l in open(sys.argv[1]):
+    arr = l.split(',')
+    fo.write('%s' % arr[0])
+    for i in xrange(len(arr) - 1):
+        fo.write(' %d:%s' % (i, arr[i+1]))
+fo.close()

demo/yearpredMSD/runexp.sh

@@ -0,0 +1,17 @@
+#!/bin/bash
+
+if [ -f YearPredictionMSD.txt ]
+then
+    echo "use existing data to run experiment"
+else
+    echo "getting data from uci, make sure you are connected to internet"
+    wget https://archive.ics.uci.edu/ml/machine-learning-databases/00203/YearPredictionMSD.txt.zip
+    unzip YearPredictionMSD.txt.zip
+fi
+echo "start making data.."
+# map feature using indicator encoding, also produce featmap.txt
+python csv2libsvm.py YearPredictionMSD.txt yearpredMSD.libsvm
+head -n 463715 yearpredMSD.libsvm > yearpredMSD.libsvm.train
+tail -n 51630 yearpredMSD.libsvm > yearpredMSD.libsvm.test
+echo "finish making the data"
+../../xgboost yearpredMSD.conf

multi-node/README.md

@@ -1,6 +1,6 @@
 Distributed XGBoost
 ======
-This folder contains information of Distributed XGBoost.
+This folder contains information of Distributed XGBoost (Distributed GBDT).
 
 * The distributed version is built on Rabit:[Reliable Allreduce and Broadcast Library](https://github.com/tqchen/rabit)
   - Rabit is a portable library that provides fault-tolerance for Allreduce calls for distributed machine learning  

src/learner/learner-inl.hpp

@@ -227,14 +227,19 @@ class BoostLearner : public rabit::ISerializable {
    */
   inline void SaveModel(const char *fname) const {
     FILE *fp;
+    bool use_stdout = false;;
+#ifndef XGBOOST_STRICT_CXX98_
     if (!strcmp(fname, "stdout")) {
       fp = stdout;
-    } else {
+      use_stdout = true;
+    } else
+#endif
+    {
       fp = utils::FopenCheck(fname, "wb");      
     }
     utils::FileStream fo(fp);
     std::string header;
-    if (save_base64 != 0|| fp == stdout) {
+    if (save_base64 != 0|| use_stdout) {
       fo.Write("bs64\t", 5);
       utils::Base64OutStream bout(fp);
       this->SaveModel(bout);
@@ -243,7 +248,9 @@ class BoostLearner : public rabit::ISerializable {
       fo.Write("binf", 4);
       this->SaveModel(fo);      
     }
-    if (fp != stdout) fclose(fp);
+    if (!use_stdout) {
+      fclose(fp);
+    }
   }
   /*!
    * \brief check if data matrix is ready to be used by training,

src/learner/objective-inl.hpp

@@ -206,7 +206,8 @@ class SoftmaxMultiClassObj : public IObjFunction {
         Softmax(&rec);
         const unsigned j = i % nstep;
         int label = static_cast<int>(info.labels[j]);
-        utils::Check(label < nclass, "SoftmaxMultiClassObj: label exceed num_class");
+        utils::Check(label >= 0 && label < nclass,
+                     "SoftmaxMultiClassObj: label must be in [0, num_class)");
         const float wt = info.GetWeight(j);
         for (int k = 0; k < nclass; ++k) {
           float p = rec[k];

src/utils/matrix_csr.h

@@ -208,7 +208,6 @@ struct SparseCSRFileBuilder {
         fo->Write(BeginPtr(buffer_data), (rptr[end] - rptr[begin]) * sizeof(IndexType));
       }
     }
-    printf("CSV::begin_dat=%lu\n", begin_data);
   }
  protected:
   inline void WriteBuffer(void) {