[LIBXGBOOST] pass demo running.

include/xgboost/base.h

@@ -16,6 +16,15 @@
 #define XGBOOST_STRICT_R_MODE 0
 #endif
 
+/*!
+ * \brief Whether always log console message with time.
+ *  It will display like, with timestamp appended to head of the message.
+ *  "[21:47:50] 6513x126 matrix with 143286 entries loaded from ../data/agaricus.txt.train"
+ */
+#ifndef XGBOOST_LOG_WITH_TIME
+#define XGBOOST_LOG_WITH_TIME 0
+#endif
+
 /*! \brief namespace of xgboo st*/
 namespace xgboost {
 /*!
@@ -23,6 +32,8 @@ namespace xgboost {
  *  used for feature index and row index.
  */
 typedef uint32_t bst_uint;
+/*! \brief long integers */
+typedef unsigned long bst_ulong;  // NOLINT(*)
 /*! \brief float type, used for storing statistics */
 typedef float bst_float;
 

include/xgboost/c_api.h

@@ -36,13 +36,6 @@ typedef void *BoosterHandle;
  */
 XGB_DLL const char *XGBGetLastError();
 
-/*!
- * \brief Entry point of CLI program.
- * \param argc The number of arguments.
- * \param argv The command line arguments.
- */
-XGB_DLL int XGBoostCLIMain(int argc, char* argv[])
-
 /*!
  * \brief load a data matrix
  * \param fname the name of the file

include/xgboost/data.h

@@ -59,7 +59,7 @@ struct MetaInfo {
   /*! \brief version flag, used to check version of this info */
   static const int kVersion = 1;
   /*! \brief default constructor */
-  MetaInfo() : num_row(0), num_col(0) {}
+  MetaInfo() : num_row(0), num_col(0), num_nonzero(0) {}
   /*!
    * \brief Get weight of each instances.
    * \param i Instance index.
@@ -96,14 +96,6 @@ struct MetaInfo {
    * \param num Number of elements in the source array.
    */
   void SetInfo(const char* key, const void* dptr, DataType dtype, size_t num);
-  /*!
-   * \brief Get information from meta info.
-   * \param key The key of the information.
-   * \param dptr The output data pointer of the source array.
-   * \param dtype The output data type of the information array.
-   * \param num Number of elements in the array.
-   */
-  void GetInfo(const char* key, const void** dptr, DataType* dtype, size_t* num) const;
 };
 
 /*! \brief read-only sparse instance batch in CSR format */
@@ -259,11 +251,14 @@ class DMatrix {
    * \param uri The URI of input.
    * \param silent Whether print information during loading.
    * \param load_row_split Flag to read in part of rows, divided among the workers in distributed mode.
+   * \param file_format The format type of the file, used for dmlc::Parser::Create.
+   *   By default "auto" will be able to load in both local binary file.
    * \return The created DMatrix.
    */
   static DMatrix* Load(const std::string& uri,
                        bool silent,
-                       bool load_row_split);
+                       bool load_row_split,
+                       const std::string& file_format = "auto");
   /*!
    * \brief create a new DMatrix, by wrapping a row_iterator, and meta info.
    * \param source The source iterator of the data, the create function takes ownership of the source.
@@ -273,7 +268,7 @@ class DMatrix {
    * \return a Created DMatrix.
    */
   static DMatrix* Create(std::unique_ptr<DataSource>&& source,
-                         const char* cache_prefix = nullptr);
+                         const std::string& cache_prefix = "");
   /*!
    * \brief Create a DMatrix by loaidng data from parser.
    *  Parser can later be deleted after the DMatrix i created.
@@ -287,7 +282,7 @@ class DMatrix {
    * \return A created DMatrix.
    */
   static DMatrix* Create(dmlc::Parser<uint32_t>* parser,
-                         const char* cache_prefix = nullptr);
+                         const std::string& cache_prefix = "");
 
  private:
   // allow learner class to access this field.

include/xgboost/gbm.h

@@ -163,7 +163,7 @@ struct GradientBoosterReg
  */
 #define XGBOOST_REGISTER_GBM(UniqueId, Name)                            \
   static ::xgboost::GradientBoosterReg & __make_ ## GradientBoosterReg ## _ ## UniqueId ## __ = \
-      ::dmlc::Registry< ::xgboost::GradientBoosterReg>::Get()->__REGISTER__(#Name)
+      ::dmlc::Registry< ::xgboost::GradientBoosterReg>::Get()->__REGISTER__(Name)
 
 }  // namespace xgboost
 #endif  // XGBOOST_GBM_H_

include/xgboost/learner.h

@@ -36,6 +36,8 @@ namespace xgboost {
  */
 class Learner : public rabit::Serializable {
  public:
+  /*! \brief virtual destructor */
+  virtual ~Learner() {}
   /*!
    * \brief set configuration from pair iterators.
    * \param begin The beginning iterator.
@@ -51,6 +53,11 @@ class Learner : public rabit::Serializable {
    * \param cfg configurations on both training and model parameters.
    */
   virtual void Configure(const std::vector<std::pair<std::string, std::string> >& cfg) = 0;
+  /*!
+   * \brief Initialize the model using the specified configurations via Configure.
+   *  An model have to be either Loaded or initialized before Update/Predict/Save can be called.
+   */
+  virtual void InitModel() = 0;
   /*!
    * \brief load model from stream
    * \param fi input stream.

include/xgboost/logging.h

@@ -0,0 +1,50 @@
+/*!
+ * Copyright (c) 2015 by Contributors
+ * \file logging.h
+ * \brief defines console logging options for xgboost.
+ *  Use to enforce unified print behavior.
+ *  For debug loggers, use LOG(INFO) and LOG(ERROR).
+ */
+#ifndef XGBOOST_LOGGING_H_
+#define XGBOOST_LOGGING_H_
+
+#include <dmlc/logging.h>
+#include <sstream>
+#include "./base.h"
+
+namespace xgboost {
+
+class BaseLogger {
+ public:
+  BaseLogger() {
+#if XGBOOST_LOG_WITH_TIME
+    log_stream_ << "[" << dmlc::DateLogger().HumanDate() << "] ";
+#endif
+  }
+  std::ostream& stream() { return log_stream_; }
+
+ protected:
+  std::ostringstream log_stream_;
+};
+
+class ConsoleLogger : public BaseLogger {
+ public:
+  ~ConsoleLogger();
+};
+
+class TrackerLogger : public BaseLogger {
+ public:
+  ~TrackerLogger();
+};
+
+// redefines the logging macro if not existed
+#ifndef LOG
+#define LOG(severity) LOG_##severity.stream()
+#endif
+
+// Enable LOG(CONSOLE) for print messages to console.
+#define LOG_CONSOLE ::xgboost::ConsoleLogger()
+// Enable LOG(TRACKER) for print messages to tracker
+#define LOG_TRACKER ::xgboost::TrackerLogger()
+}  // namespace xgboost.
+#endif  // XGBOOST_LOGGING_H_

include/xgboost/metric.h

@@ -70,7 +70,7 @@ struct MetricReg
  * \endcode
  */
 #define XGBOOST_REGISTER_METRIC(UniqueId, Name)                         \
-  static ::xgboost::MetricReg & __make_ ## MetricReg ## _ ## UniqueId ## __ = \
-      ::dmlc::Registry< ::xgboost::MetricReg>::Get()->__REGISTER__(#Name)
+  ::xgboost::MetricReg&  __make_ ## MetricReg ## _ ## UniqueId ## __ =  \
+      ::dmlc::Registry< ::xgboost::MetricReg>::Get()->__REGISTER__(Name)
 }  // namespace xgboost
 #endif  // XGBOOST_METRIC_H_

include/xgboost/objective.h

@@ -106,6 +106,6 @@ struct ObjFunctionReg
  */
 #define XGBOOST_REGISTER_OBJECTIVE(UniqueId, Name)                      \
   static ::xgboost::ObjFunctionReg & __make_ ## ObjFunctionReg ## _ ## UniqueId ## __ = \
-      ::dmlc::Registry< ::xgboost::ObjFunctionReg>::Get()->__REGISTER__(#Name)
+      ::dmlc::Registry< ::xgboost::ObjFunctionReg>::Get()->__REGISTER__(Name)
 }  // namespace xgboost
 #endif  // XGBOOST_OBJECTIVE_H_

include/xgboost/tree_model.h

@@ -8,7 +8,6 @@
 #define XGBOOST_TREE_MODEL_H_
 
 #include <dmlc/io.h>
-#include <dmlc/logging.h>
 #include <dmlc/parameter.h>
 #include <limits>
 #include <vector>
@@ -17,6 +16,7 @@
 #include <algorithm>
 #include "./base.h"
 #include "./data.h"
+#include "./logging.h"
 #include "./feature_map.h"
 
 namespace xgboost {

include/xgboost/tree_updater.h

@@ -79,7 +79,7 @@ struct TreeUpdaterReg
  */
 #define XGBOOST_REGISTER_TREE_UPDATER(UniqueId, Name)                   \
   static ::xgboost::TreeUpdaterReg& __make_ ## TreeUpdaterReg ## _ ## UniqueId ## __ = \
-      ::dmlc::Registry< ::xgboost::TreeUpdaterReg>::Get()->__REGISTER__(#Name)
+      ::dmlc::Registry< ::xgboost::TreeUpdaterReg>::Get()->__REGISTER__(Name)
 
 }  // namespace xgboost
 #endif  // XGBOOST_TREE_UPDATER_H_