add dump statistics

R-package/R/xgb.dump.R

@@ -10,6 +10,10 @@
 #'        See demo/ for walkthrough example in R, and
 #'        \url{https://github.com/tqchen/xgboost/blob/master/demo/data/featmap.txt} 
 #'        for example Format.
+#' @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.
 #'
 #' @examples
 #' data(agaricus.train, package='xgboost')
@@ -21,13 +25,13 @@
 #' xgb.dump(bst, 'xgb.model.dump')
 #' @export
 #' 
-xgb.dump <- function(model, fname, fmap = "") {
+xgb.dump <- function(model, fname, fmap = "", with.stats=FALSE) {
   if (class(model) != "xgb.Booster") {
     stop("xgb.dump: first argument must be type xgb.Booster")
   }
   if (typeof(fname) != "character") {
     stop("xgb.dump: second argument must be type character")
   }
-  .Call("XGBoosterDumpModel_R", model, fname, fmap, PACKAGE = "xgboost")
+  .Call("XGBoosterDumpModel_R", model, fname, fmap, as.integer(with.stats), PACKAGE = "xgboost")
   return(TRUE)
 } 

R-package/src/xgboost_R.cpp

@@ -241,10 +241,10 @@ extern "C" {
     for (int i = 0; i < len; ++i) {
       vec_sptr.push_back(vec_names[i].c_str());
     }
+    _WrapperEnd();
     return mkString(XGBoosterEvalOneIter(R_ExternalPtrAddr(handle),
                                          asInteger(iter),
                                          BeginPtr(vec_dmats), BeginPtr(vec_sptr), len));
-    _WrapperEnd();
   }
   SEXP XGBoosterPredict_R(SEXP handle, SEXP dmat, SEXP output_margin, SEXP ntree_limit) {
     _WrapperBegin();
@@ -272,11 +272,13 @@ extern "C" {
     XGBoosterSaveModel(R_ExternalPtrAddr(handle), CHAR(asChar(fname)));
     _WrapperEnd();
   }
-  void XGBoosterDumpModel_R(SEXP handle, SEXP fname, SEXP fmap) {
+  void XGBoosterDumpModel_R(SEXP handle, SEXP fname,
+                            SEXP fmap, SEXP with_stats) {
     _WrapperBegin();
     bst_ulong olen;
     const char **res = XGBoosterDumpModel(R_ExternalPtrAddr(handle),
                                           CHAR(asChar(fmap)),
+                                          asInteger(with_stats),
                                           &olen);
     FILE *fo = utils::FopenCheck(CHAR(asChar(fname)), "w");
     for (size_t i = 0; i < olen; ++i) {

R-package/src/xgboost_R.h

@@ -132,7 +132,8 @@ extern "C" {
    * \param handle handle
    * \param fname file name of model that can be dumped into
    * \param fmap  name to fmap can be empty string
+   * \param with_stats whether dump statistics of splits
    */
-  void XGBoosterDumpModel_R(SEXP handle, SEXP fname, SEXP fmap);
+  void XGBoosterDumpModel_R(SEXP handle, SEXP fname, SEXP fmap, SEXP with_stats);
 }
 #endif  // XGBOOST_WRAPPER_R_H_

wrapper/xgboost.py

@@ -368,13 +368,15 @@ class Booster:
                 None
         """
         xglib.XGBoosterLoadModel( self.handle, ctypes.c_char_p(fname.encode('utf-8')) )
-    def dump_model(self, fo, fmap=''):
+    def dump_model(self, fo, fmap='', with_stats = False):
         """dump model into text file
             Args:
                 fo: string
                     file name to be dumped
                 fmap: string, optional
                       file name of feature map names
+                with_stats: bool, optional
+                      whether output statistics of the split
             Returns:
                 None
         """
@@ -383,16 +385,18 @@ class Booster:
             need_close = True
         else:
             need_close = False
-        ret = self.get_dump(fmap)
+        ret = self.get_dump(fmap, with_stats)
         for i in range(len(ret)):
             fo.write('booster[%d]:\n' %i)
             fo.write( ret[i] )
         if need_close:
             fo.close()
-    def get_dump(self, fmap=''):
+    def get_dump(self, fmap='', with_stats=False):
         """get dump of model as list of strings """
         length = ctypes.c_ulong()
-        sarr = xglib.XGBoosterDumpModel(self.handle, ctypes.c_char_p(fmap.encode('utf-8')), ctypes.byref(length))
+        sarr = xglib.XGBoosterDumpModel(self.handle,
+                                        ctypes.c_char_p(fmap.encode('utf-8')),
+                                        int(with_stats), ctypes.byref(length))
         res = []
         for i in range(length.value):
             res.append( str(sarr[i]) )

wrapper/xgboost_wrapper.cpp

@@ -293,11 +293,11 @@ extern "C"{
   void XGBoosterSaveModel(const void *handle, const char *fname) {
     static_cast<const Booster*>(handle)->SaveModel(fname);
   }
-  const char** XGBoosterDumpModel(void *handle, const char *fmap, bst_ulong *len){
+  const char** XGBoosterDumpModel(void *handle, const char *fmap, int with_stats, bst_ulong *len){
     utils::FeatMap featmap;
     if (strlen(fmap) != 0) {
       featmap.LoadText(fmap);
     }
-    return static_cast<Booster*>(handle)->GetModelDump(featmap, false, len);
+    return static_cast<Booster*>(handle)->GetModelDump(featmap, with_stats != 0, len);
   }
 }

wrapper/xgboost_wrapper.h

@@ -200,11 +200,12 @@ extern "C" {
    * \brief dump model, return array of strings representing model dump
    * \param handle handle
    * \param fmap  name to fmap can be empty string
+   * \param with_stats whether to dump with statistics
    * \param out_len length of output array
    * \return char *data[], representing dump of each model
    */
   XGB_DLL const char **XGBoosterDumpModel(void *handle, const char *fmap,
-                                          bst_ulong *out_len);
+                                          int with_stats, bst_ulong *out_len);
 #ifdef __cplusplus
 }
 #endif