Add JSON IO for various components.

CMakeLists.txt

@@ -14,11 +14,8 @@ if (CMAKE_COMPILER_IS_GNUCC AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 5.0)
 endif()
 
 message(STATUS "xgboost VERSION: ${xgboost_VERSION}")
-set(XGBOOST_DEFINITIONS
-  ${XGBOOST_DEFINITIONS}
-  -DXGBOOST_VER_MAJOR=${xgboost_VERSION_MAJOR}
-  -DXGBOOST_VER_MINOR=${xgboost_VERSION_MINOR}
-  -DXGBOOST_VER_PATCH=${xgboost_VERSION_PATCH})
+include (${xgboost_SOURCE_DIR}/cmake/Version.cmake)
+write_version()
 set_default_configuration_release()
 
 #-- Options

amalgamation/xgboost-all0.cc

@@ -25,7 +25,9 @@
 // gbms
 #include "../src/gbm/gbm.cc"
 #include "../src/gbm/gbtree.cc"
+#include "../src/gbm/gbtree_model.cc"
 #include "../src/gbm/gblinear.cc"
+#include "../src/gbm/gblinear_model.cc"
 
 // data
 #include "../src/data/data.cc"

cmake/Version.cmake

@@ -0,0 +1,5 @@
+function (write_version)
+  configure_file(
+    ${xgboost_SOURCE_DIR}/cmake/build_config.h.in
+    ${xgboost_SOURCE_DIR}/include/xgboost/build_config.h @ONLY)
+endfunction (write_version)

cmake/build_config.h.in

@@ -0,0 +1,28 @@
+/*!
+ * Copyright 2019 by Contributors
+ * \file build_config.h
+ *
+ * Generated from `cmake/build_config.h.in` by cmake.
+ */
+#ifndef XGBOOST_BUILD_CONFIG_H_
+#define XGBOOST_BUILD_CONFIG_H_
+
+// These check are for Makefile.
+#if !defined(XGBOOST_MM_PREFETCH_PRESENT) && !defined(XGBOOST_BUILTIN_PREFETCH_PRESENT)
+/* default logic for software pre-fetching */
+#if (defined(_MSC_VER) && (defined(_M_IX86) || defined(_M_AMD64))) || defined(__INTEL_COMPILER)
+// Enable _mm_prefetch for Intel compiler and MSVC+x86
+  #define XGBOOST_MM_PREFETCH_PRESENT
+  #define XGBOOST_BUILTIN_PREFETCH_PRESENT
+#elif defined(__GNUC__)
+// Enable __builtin_prefetch for GCC
+#define XGBOOST_BUILTIN_PREFETCH_PRESENT
+#endif  // GUARDS
+
+#endif  // !defined(XGBOOST_MM_PREFETCH_PRESENT) && !defined()
+
+#define XGBOOST_VER_MAJOR @xgboost_VERSION_MAJOR@
+#define XGBOOST_VER_MINOR @xgboost_VERSION_MINOR@
+#define XGBOOST_VER_PATCH @xgboost_VERSION_PATCH@
+
+#endif  // XGBOOST_BUILD_CONFIG_H_

include/xgboost/base.h

@@ -197,6 +197,21 @@ inline XGBOOST_DEVICE void GradientPairInternal<int64_t>::SetHess(float h) {
 
 }  // namespace detail
 
+class Json;
+
+struct Serializable {
+  /*!
+   * \brief load the model from a json object
+   * \param in json object where to load the model from
+   */
+  virtual void Load(Json const& in) = 0;
+  /*!
+   * \breif saves the model to a json object
+   * \param out json container where to save the model to
+   */
+  virtual void Save(Json* out) const = 0;
+};
+
 /*! \brief gradient statistics pair usually needed in gradient boosting */
 using GradientPair = detail::GradientPairInternal<float>;
 

include/xgboost/build_config.h

@@ -1,6 +1,8 @@
 /*!
  * Copyright 2019 by Contributors
  * \file build_config.h
+ *
+ * Generated from `cmake/build_config.h.in` by cmake.
  */
 #ifndef XGBOOST_BUILD_CONFIG_H_
 #define XGBOOST_BUILD_CONFIG_H_
@@ -19,4 +21,8 @@
 
 #endif  // !defined(XGBOOST_MM_PREFETCH_PRESENT) && !defined()
 
+#define XGBOOST_VER_MAJOR 1
+#define XGBOOST_VER_MINOR 0
+#define XGBOOST_VER_PATCH 0
+
 #endif  // XGBOOST_BUILD_CONFIG_H_

include/xgboost/gbm.h

@@ -10,6 +10,7 @@
 
 #include <dmlc/registry.h>
 #include <xgboost/base.h>
+#include <xgboost/json.h>
 #include <xgboost/data.h>
 #include <xgboost/objective.h>
 #include <xgboost/feature_map.h>
@@ -27,7 +28,7 @@ namespace xgboost {
 /*!
  * \brief interface of gradient boosting model.
  */
-class GradientBooster {
+class GradientBooster : public Serializable {
  protected:
   GenericParameter const* learner_param_;
 
@@ -46,11 +47,21 @@ class GradientBooster {
    * \param fi input stream.
    */
   virtual void Load(dmlc::Stream* fi) = 0;
+  /*!
+   * \brief load model from json
+   * \param in input json model.
+   */
+  void Load(Json const& in) override = 0;
   /*!
    * \brief save model to stream.
    * \param fo output stream
    */
   virtual void Save(dmlc::Stream* fo) const = 0;
+  /*!
+   * \brief Save model to Json
+   * \param out output json document.
+   */
+  void Save(Json* out) const override = 0;
   /*!
    * \brief whether the model allow lazy checkpoint
    * return true if model is only updated in DoBoost

include/xgboost/learner.h

@@ -9,13 +9,13 @@
 #define XGBOOST_LEARNER_H_
 
 #include <rabit/rabit.h>
-
 #include <xgboost/base.h>
 #include <xgboost/gbm.h>
 #include <xgboost/metric.h>
 #include <xgboost/objective.h>
 #include <xgboost/feature_map.h>
 #include <xgboost/generic_parameters.h>
+#include <xgboost/json.h>
 
 #include <utility>
 #include <map>
@@ -41,19 +41,31 @@ namespace xgboost {
  *
  *  \endcode
  */
-class Learner : public rabit::Serializable {
+class Learner : public Serializable, public rabit::Serializable {
  public:
   /*! \brief virtual destructor */
   ~Learner() override = default;
   /*!
    * \brief Configure Learner based on set parameters.
    */
   virtual void Configure() = 0;
+
+  /*!
+   * \brief load model from json object
+   * \param in input json object
+   */
+  void Load(Json const& in) override = 0;
   /*!
    * \brief load model from stream
    * \param fi input stream.
    */
   void Load(dmlc::Stream* fi) override = 0;
+
+  /*!
+   * \brief save model to json object
+   * \param out output json object
+   */
+  void Save(Json* out) const override = 0;
   /*!
    * \brief save model to stream.
    * \param fo output stream

include/xgboost/objective.h

@@ -21,8 +21,10 @@
 
 namespace xgboost {
 
+class Json;
+
 /*! \brief interface of objective function */
-class ObjFunction {
+class ObjFunction : public Serializable {
  protected:
   GenericParameter const* tparam_;
 
@@ -72,6 +74,9 @@ class ObjFunction {
   virtual bst_float ProbToMargin(bst_float base_score) const {
     return base_score;
   }
+
+  virtual void Save(Json* out) const = 0;
+  virtual void Load(Json const& in) = 0;
   /*!
    * \brief Create an objective function according to name.
    * \param tparam Generic parameters.

include/xgboost/tree_model.h

@@ -9,6 +9,7 @@
 
 #include <dmlc/io.h>
 #include <dmlc/parameter.h>
+
 #include <limits>
 #include <vector>
 #include <string>
@@ -24,6 +25,8 @@ namespace xgboost {
 
 struct PathElement;  // forward declaration
 
+class Json;
+
 /*! \brief meta parameters of the tree */
 struct TreeParam : public dmlc::Parameter<TreeParam> {
   /*! \brief number of start root */
@@ -57,6 +60,7 @@ struct TreeParam : public dmlc::Parameter<TreeParam> {
     // other arguments are set by the algorithm.
     DMLC_DECLARE_FIELD(num_roots).set_lower_bound(1).set_default(1)
         .describe("Number of start root of trees.");
+    DMLC_DECLARE_FIELD(num_nodes).set_lower_bound(1).set_default(1);
     DMLC_DECLARE_FIELD(num_feature)
         .describe("Number of features used in tree construction.");
     DMLC_DECLARE_FIELD(size_leaf_vector).set_lower_bound(0).set_default(0)
@@ -80,7 +84,7 @@ struct RTreeNodeStat {
   /*! \brief weight of current node */
   bst_float base_weight;
   /*! \brief number of child that is leaf node known up to now */
-  int leaf_child_cnt;
+  int leaf_child_cnt {0};
   bool operator==(const RTreeNodeStat& b) const {
     return loss_chg == b.loss_chg && sum_hess == b.sum_hess &&
            base_weight == b.base_weight && leaf_child_cnt == b.leaf_child_cnt;
@@ -91,7 +95,7 @@ struct RTreeNodeStat {
  * \brief define regression tree to be the most common tree model.
  *  This is the data structure used in xgboost's major tree models.
  */
-class RegTree {
+class RegTree : public Serializable {
  public:
   /*! \brief auxiliary statistics of node to help tree building */
   using SplitCondT = bst_float;
@@ -103,6 +107,12 @@ class RegTree {
       static_assert(sizeof(Node) == 4 * sizeof(int) + sizeof(Info),
                     "Node: 64 bit align");
     }
+    Node(int32_t cleft, int32_t cright, int32_t parent,
+         uint32_t split_ind, float split_cond, bool default_left) :
+        parent_{parent}, cleft_{cleft}, cright_{cright} {
+      this->SetSplit(split_ind, split_cond, default_left);
+    }
+
     /*! \brief index of left child */
     XGBOOST_DEVICE int LeftChild() const {
       return this->cleft_;
@@ -216,9 +226,9 @@ class RegTree {
     };
     // pointer to parent, highest bit is used to
     // indicate whether it's a left child or not
-    int parent_;
+    int parent_{-1};
     // pointer to left, right
-    int cleft_, cright_;
+    int cleft_{-1}, cright_{-1};
     // split feature index, left split or right split depends on the highest bit
     unsigned sindex_{0};
     // extra info
@@ -307,6 +317,8 @@ class RegTree {
     }
     CHECK_EQ(static_cast<int>(deleted_nodes_.size()), param.num_deleted);
   }
+
+  void Load(Json const& in) override;
   /*!
    * \brief save model to stream
    * \param fo output stream
@@ -320,6 +332,8 @@ class RegTree {
     fo->Write(dmlc::BeginPtr(stats_), sizeof(RTreeNodeStat) * nodes_.size());
   }
 
+  void Save(Json* out) const override;
+
   bool operator==(const RegTree& b) const {
     return nodes_ == b.nodes_ && stats_ == b.stats_ &&
            deleted_nodes_ == b.deleted_nodes_ && param == b.param;

include/xgboost/tree_updater.h

@@ -22,6 +22,9 @@
 #include "../../src/common/host_device_vector.h"
 
 namespace xgboost {
+
+class Json;
+
 /*!
  * \brief interface of tree update module, that performs update of a tree.
  */
@@ -67,6 +70,8 @@ class TreeUpdater {
 
   virtual char const* Name() const = 0;
 
+  virtual void Save(Json* out) const {}
+
   /*!
    * \brief Create a tree updater given name
    * \param name Name of the tree updater.

plugin/example/custom_obj.cc

@@ -1,12 +1,13 @@
 /*!
- * Copyright 2015 by Contributors
+ * Copyright 2015-2019 by Contributors
  * \file custom_metric.cc
  * \brief This is an example to define plugin of xgboost.
  *  This plugin defines the additional metric function.
  */
 #include <xgboost/base.h>
 #include <dmlc/parameter.h>
 #include <xgboost/objective.h>
+#include <xgboost/json.h>
 
 namespace xgboost {
 namespace obj {
@@ -69,6 +70,16 @@ class MyLogistic : public ObjFunction {
     return -std::log(1.0f / base_score - 1.0f);
   }
 
+  void Save(Json* p_out) const override {
+    auto& out = *p_out;
+    out["name"] = String("MyLogistic");
+    out["MyLogisticParam"] = toJson(param_);
+  }
+
+  void Load(Json const& in) override {
+    param_.InitAllowUnknown(fromJson(get<Object>(in["MyLogisticParam"])));
+  }
+
  private:
   MyLogisticParam param_;
 };

python-package/xgboost/compat.py

@@ -12,14 +12,18 @@
     # pylint: disable=invalid-name, redefined-builtin
     STRING_TYPES = (str,)
 
-
     def py_str(x):
         """convert c string back to python string"""
-        return x.decode('utf-8')
+        try:
+            s = x.decode('utf-8')
+        except UnicodeDecodeError as e:
+            print('Failed to decode error message, please file a bug report.')
+            print(e)
+            s = x
+        return s
 else:
     STRING_TYPES = (basestring,)  # pylint: disable=undefined-variable
 
-
     def py_str(x):
         """convert c string back to python string"""
         return x