Merge pull request #46 from tqchen/master

merge master into unity

src/io/io.cpp

@@ -2,6 +2,7 @@
 #define _CRT_SECURE_NO_DEPRECATE
 #include <string>
 #include "./io.h"
+#include "../utils/io.h"
 #include "../utils/utils.h"
 #include "simple_dmatrix-inl.hpp"
 // implements data loads using dmatrix simple for now
@@ -9,6 +10,19 @@
 namespace xgboost {
 namespace io {
 DataMatrix* LoadDataMatrix(const char *fname, bool silent, bool savebuffer) {
+  int magic;
+  utils::FileStream fs(utils::FopenCheck(fname, "rb"));
+  utils::Check(fs.Read(&magic, sizeof(magic)) != 0, "invalid input file format");
+  fs.Seek(0);
+
+  if (magic == DMatrixSimple::kMagic) { 
+    DMatrixSimple *dmat = new DMatrixSimple();
+    dmat->LoadBinary(fs, silent, fname);
+    fs.Close();
+    return dmat;
+  } 
+  fs.Close();
+ 
   DMatrixSimple *dmat = new DMatrixSimple();
   dmat->CacheLoad(fname, silent, savebuffer);
   return dmat;

src/io/simple_dmatrix-inl.hpp

@@ -128,6 +128,17 @@ class DMatrixSimple : public DataMatrix {
     FILE *fp = fopen64(fname, "rb");
     if (fp == NULL) return false;
     utils::FileStream fs(fp);
+    this->LoadBinary(fs, silent, fname);
+    fs.Close();
+    return true;
+  }
+  /*!
+   * \brief load from binary stream
+   * \param fs input file stream
+   * \param silent whether print information during loading
+   * \param fname file name, used to print message
+   */
+  inline void LoadBinary(utils::IStream &fs, bool silent = false, const char *fname = NULL) {
     int magic;
     utils::Check(fs.Read(&magic, sizeof(magic)) != 0, "invalid input file format");
     utils::Check(magic == kMagic, "invalid format,magic number mismatch");
@@ -135,16 +146,19 @@ class DMatrixSimple : public DataMatrix {
     info.LoadBinary(fs);
     FMatrixS::LoadBinary(fs, &row_ptr_, &row_data_);
     fmat.LoadColAccess(fs);
-    fs.Close();
 
     if (!silent) {
-      printf("%lux%lu matrix with %lu entries is loaded from %s\n",
-             info.num_row(), info.num_col(), row_data_.size(), fname);
+      printf("%lux%lu matrix with %lu entries is loaded",
+             info.num_row(), info.num_col(), row_data_.size());
+      if (fname != NULL) {
+        printf(" from %s\n", fname);
+      } else {
+        printf("\n");
+      }
       if (info.group_ptr.size() != 0) {
         printf("data contains %u groups\n", (unsigned)info.group_ptr.size()-1);
       }
     }
-    return true;
   }
   /*!
    * \brief save to binary file

src/utils/io.h

@@ -102,6 +102,9 @@ class FileStream : public IStream {
   virtual void Write(const void *ptr, size_t size) {
     fwrite(ptr, size, 1, fp);
   }
+  inline void Seek(size_t pos) {
+    fseek(fp, 0, SEEK_SET);
+  }
   inline void Close(void) {
     fclose(fp);
   }

src/utils/omp.h

@@ -10,7 +10,9 @@
 #else
 #ifndef DISABLE_OPENMP
 #ifndef _MSC_VER
-#warning "OpenMP is not available, compile to single thread code"
+#warning "OpenMP is not available, compile to single thread code."\
+		 "You may want to ungrade your compiler to enable OpenMP support,"\
+		 "to get benefit of multi-threading."
 #else
 // TODO add warning for msvc
 #endif

src/utils/random.h

@@ -89,16 +89,19 @@ struct Random{
   /*! \brief set random number seed */
   inline void Seed(unsigned sd) {
 	 this->rseed = sd;
-#ifdef _MSC_VER
+#if defined(_MSC_VER)||defined(_WIN32)
     srand(rseed);
 #endif
   }
   /*! \brief return a real number uniform in [0,1) */
   inline double RandDouble(void) {
-#ifndef _MSC_VER
-    return static_cast<double>(rand_r(&rseed)) / (static_cast<double>(RAND_MAX) + 1.0);
+	// use rand instead of rand_r in windows, for MSVC it is fine since rand is threadsafe
+	// For cygwin and mingw, this can slows down parallelism, but rand_r is only used in objective-inl.hpp, won't affect speed in general
+	// todo, replace with another PRNG
+#if defined(_MSC_VER)||defined(_WIN32)
+    return static_cast<double>(rand()) / (static_cast<double>(RAND_MAX) + 1.0);
 #else
-     return static_cast<double>(rand()) / (static_cast<double>(RAND_MAX) + 1.0);
+    return static_cast<double>(rand_r(&rseed)) / (static_cast<double>(RAND_MAX) + 1.0);
 #endif
   }
   // random number seed