merge from dmlc/xgboost

Makefile

@@ -1,5 +1,5 @@
-export CC  = $(if $(shell which gcc-5),gcc-5,gcc)
-export CXX = $(if $(shell which g++-5),g++-5,g++)
+export CC  = $(if $(shell which gcc-5 2>/dev/null),gcc-5,gcc)
+export CXX = $(if $(shell which g++-5 2>/dev/null),g++-5,g++)
 
 export MPICXX = mpicxx
 export LDFLAGS= -pthread -lm

doc/model.md

@@ -188,7 +188,7 @@ By defining it formally, we can get a better idea of what we are learning, and y
 Here is the magical part of the derivation. After reformalizing the tree model, we can write the objective value with the ``$ t$``-th tree as:
 
 ```math
-Obj^{(t)} &\approx \sum_{i=1}^n [g_i w_q(x_i) + \frac{1}{2} h_i w_{q(x_i)}^2] + \gamma T + \frac{1}{2}\lambda \sum_{j=1}^T w_j^2\\
+Obj^{(t)} &\approx \sum_{i=1}^n [g_i w_{q(x_i)} + \frac{1}{2} h_i w_{q(x_i)}^2] + \gamma T + \frac{1}{2}\lambda \sum_{j=1}^T w_j^2\\
 &= \sum^T_{j=1} [(\sum_{i\in I_j} g_i) w_j + \frac{1}{2} (\sum_{i\in I_j} h_i + \lambda) w_j^2 ] + \gamma T
 ```
 

java/create_wrap.sh

@@ -1,11 +1,18 @@
+#!/usr/bin/env sh
 echo "build java wrapper"
-dylib="so"
+
+# cd to script's directory
+pushd `dirname $0` > /dev/null
+
+#settings according to os
+dl="so"
 omp="0"
 if [ $(uname) == "Darwin" ]; then
   export JAVA_HOME=$(/usr/libexec/java_home)
-  dylib="dylib"
+  dl="dylib"
   omp="1"
 fi
+
 cd ..
 make java no_omp=${omp}
 cd java
@@ -16,7 +23,8 @@ if [ ! -d "$libPath" ]; then
   mkdir -p "$libPath"
 fi
 
-rm -f xgboost4j/src/main/resources/lib/libxgboost4j.${dylib}
-mv libxgboost4j.so xgboost4j/src/main/resources/lib/libxgboost4j.${dylib}
+rm -f xgboost4j/src/main/resources/lib/libxgboost4j.${dl}
+mv libxgboost4j.so xgboost4j/src/main/resources/lib/libxgboost4j.${dl}
 
+popd > /dev/null
 echo "complete"

python-package/xgboost/training.py

@@ -117,7 +117,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
             evals_result.update(dict([(key, {}) for key in evals_name]))
 
     if not early_stopping_rounds:
-        for i in range(num_boost_round):
+        for i in range(nboost, nboost + num_boost_round):
             bst.update(dtrain, i, obj)
             nboost += 1
             if len(evals) != 0:
@@ -189,7 +189,7 @@ def train(params, dtrain, num_boost_round=10, evals=(), obj=None, feval=None,
         if isinstance(learning_rates, list) and len(learning_rates) != num_boost_round:
             raise ValueError("Length of list 'learning_rates' has to equal 'num_boost_round'.")
 
-        for i in range(num_boost_round):
+        for i in range(nboost, nboost + num_boost_round):
             if learning_rates is not None:
                 if isinstance(learning_rates, list):
                     bst.set_param({'eta': learning_rates[i]})
@@ -337,7 +337,8 @@ def aggcv(rlist, show_stdv=True, show_progress=None, as_pandas=True, trial=0):
         if show_progress is None:
             show_progress = True
 
-    if (isinstance(show_progress, int) and trial % show_progress == 0) or (isinstance(show_progress, bool) and show_progress):
+    if (isinstance(show_progress, int) and show_progress > 0 and trial % show_progress == 0) or \
+            (isinstance(show_progress, bool) and show_progress):
         sys.stderr.write(msg + '\n')
         sys.stderr.flush()
 
@@ -432,10 +433,10 @@ def cv(params, dtrain, num_boost_round=10, nfold=3, metrics=(),
                 best_score = score
                 best_score_i = i
             elif i - best_score_i >= early_stopping_rounds:
-                sys.stderr.write("Stopping. Best iteration: {}\n".format(best_score_i))
                 results = results[:best_score_i+1]
+                sys.stderr.write("Stopping. Best iteration: {} (mean: {}, std: {})\n".
+                                 format(best_score_i, results[-1][0], results[-1][1]))
                 break
-
     if as_pandas:
         try:
             import pandas as pd

src/io/dmlc_simple.cpp

@@ -153,7 +153,7 @@ class StdFile : public dmlc::Stream {
     return std::fread(ptr, 1, size, fp);
   }
   virtual void Write(const void *ptr, size_t size) {
-    std::fwrite(ptr, size, 1, fp);
+    Check(std::fwrite(ptr, size, 1, fp) == 1, "StdFile::Write: fwrite error!");
   }
   virtual void Seek(size_t pos) {
     std::fseek(fp, static_cast<long>(pos), SEEK_SET);  // NOLINT(*)

src/utils/io.h

@@ -33,7 +33,7 @@ class FileStream : public ISeekStream {
     return std::fread(ptr, size, 1, fp);
   }
   virtual void Write(const void *ptr, size_t size) {
-    std::fwrite(ptr, size, 1, fp);
+    Check(std::fwrite(ptr, size, 1, fp) == 1, "FileStream::Write: fwrite error!");
   }
   virtual void Seek(size_t pos) {
     std::fseek(fp, static_cast<long>(pos), SEEK_SET); // NOLINT(*)

subtree/rabit/windows/rabit/rabit.vcxproj

@@ -24,7 +24,7 @@
   </PropertyGroup>
   <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
-    <ConfigurationType>Application</ConfigurationType>
+    <ConfigurationType>StaticLibrary</ConfigurationType>
     <UseDebugLibraries>true</UseDebugLibraries>
     <CharacterSet>MultiByte</CharacterSet>
   </PropertyGroup>

windows/xgboost/xgboost.vcxproj

@@ -25,6 +25,11 @@
     <ClCompile Include="..\..\src\tree\updater.cpp" />
     <ClCompile Include="..\..\src\xgboost_main.cpp" />
   </ItemGroup>
+  <ItemGroup>
+    <ProjectReference Include="..\..\subtree\rabit\windows\rabit\rabit.vcxproj">
+      <Project>{d7b77d06-4f5f-4bd7-b81e-7cc8ebbe684f}</Project>
+    </ProjectReference>
+  </ItemGroup>
   <PropertyGroup Label="Globals">
     <ProjectGuid>{19766C3F-7508-49D0-BAAC-0988FCC9970C}</ProjectGuid>
     <RootNamespace>xgboost</RootNamespace>