Release patch release 1.1.1 with faster CPU performance (#5732 )

* Fix release degradation (#5720) * fix release degradation, related to 5666 * less resizes Co-authored-by: SHVETS, KIRILL <kirill.shvets@intel.com> * Make 1.1.1 patch release * Disable too-many-function-args pylint warning for predict() * Fix Windows CI * Remove cpplint Co-authored-by: ShvetsKS <33296480+ShvetsKS@users.noreply.github.com> Co-authored-by: SHVETS, KIRILL <kirill.shvets@intel.com>
Add pkgconfig to cmake (#5744 ) (#5748 )
2020-06-04 10:56:07 -07:00 · 2020-06-02 12:04:27 -07:00 · 2020-06-01 04:32:24 +08:00 · 2020-05-31 21:35:00 +08:00 · 2020-05-27 03:09:46 -07:00 · 2020-05-24 23:38:42 -07:00
26 changed files with 242 additions and 108 deletions
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.13)
-project(xgboost LANGUAGES CXX C VERSION 1.1.0)
+project(xgboost LANGUAGES CXX C VERSION 1.1.1)
 include(cmake/Utils.cmake)
 list(APPEND CMAKE_MODULE_PATH "${xgboost_SOURCE_DIR}/cmake/modules")
 cmake_policy(SET CMP0022 NEW)
@@ -57,6 +57,7 @@ address, leak, undefined and thread.")
 ## Plugins
 option(PLUGIN_LZ4 "Build lz4 plugin" OFF)
 option(PLUGIN_DENSE_PARSER "Build dense parser plugin" OFF)
+option(ADD_PKGCONFIG "Add xgboost.pc into system." ON)

 #-- Checks for building XGBoost
 if (USE_DEBUG_OUTPUT AND (NOT (CMAKE_BUILD_TYPE MATCHES Debug)))
@@ -274,3 +275,12 @@ endif (GOOGLE_TEST)
 # replace /MD with /MT. See https://github.com/dmlc/xgboost/issues/4462
 # for issues caused by mixing of /MD and /MT flags
 msvc_use_static_runtime()
+
+# Add xgboost.pc
+if (ADD_PKGCONFIG)
+  configure_file(${xgboost_SOURCE_DIR}/cmake/xgboost.pc.in ${xgboost_BINARY_DIR}/xgboost.pc @ONLY)
+
+  install(
+    FILES ${xgboost_BINARY_DIR}/xgboost.pc
+    DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
+endif (ADD_PKGCONFIG)
--- a/12
+++ b/12
@@ -48,7 +48,6 @@ pipeline {
        script {
          parallel ([
            'clang-tidy': { ClangTidy() },
-            'lint': { Lint() },
            'sphinx-doc': { SphinxDoc() },
            'doxygen': { Doxygen() }
          ])
@@ -64,7 +63,6 @@ pipeline {
            'build-cpu': { BuildCPU() },
            'build-cpu-rabit-mock': { BuildCPUMock() },
            'build-cpu-non-omp': { BuildCPUNonOmp() },
-            'build-gpu-cuda9.0': { BuildCUDA(cuda_version: '9.0') },
            'build-gpu-cuda10.0': { BuildCUDA(cuda_version: '10.0') },
            'build-gpu-cuda10.1': { BuildCUDA(cuda_version: '10.1') },
            'build-jvm-packages': { BuildJVMPackages(spark_version: '2.4.3') },
@@ -251,10 +249,10 @@ def BuildCUDA(args) {
    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} bash -c "cd python-package && rm -rf dist/* && python setup.py bdist_wheel --universal"
    ${dockerRun} ${container_type} ${docker_binary} ${docker_args} python3 tests/ci_build/rename_whl.py python-package/dist/*.whl ${commit_id} manylinux2010_x86_64
    """
-    // Stash wheel for CUDA 9.0 target
-    if (args.cuda_version == '9.0') {
+    // Stash wheel for CUDA 10.0 target
+    if (args.cuda_version == '10.0') {
      echo 'Stashing Python wheel...'
-      stash name: 'xgboost_whl_cuda9', includes: 'python-package/dist/*.whl'
+      stash name: 'xgboost_whl_cuda10', includes: 'python-package/dist/*.whl'
      path = ("${BRANCH_NAME}" == 'master') ? '' : "${BRANCH_NAME}/"
      s3Upload bucket: 'xgboost-nightly-builds', path: path, acl: 'PublicRead', workingDir: 'python-package/dist', includePathPattern:'**/*.whl'
      echo 'Stashing C++ test executable (testxgboost)...'
@@ -298,7 +296,7 @@ def BuildJVMDoc() {

 def TestPythonCPU() {
  node('linux && cpu') {
-    unstash name: 'xgboost_whl_cuda9'
+    unstash name: 'xgboost_whl_cuda10'
    unstash name: 'srcs'
    unstash name: 'xgboost_cli'
    echo "Test Python CPU"
@@ -315,7 +313,7 @@ def TestPythonCPU() {
 def TestPythonGPU(args) {
  nodeReq = (args.multi_gpu) ? 'linux && mgpu' : 'linux && gpu'
  node(nodeReq) {
-    unstash name: 'xgboost_whl_cuda9'
+    unstash name: 'xgboost_whl_cuda10'
    unstash name: 'srcs'
    echo "Test Python GPU: CUDA ${args.cuda_version}"
    def container_type = "gpu"
--- a/5
+++ b/5
@@ -28,7 +28,7 @@ pipeline {
      steps {
        script {
          parallel ([
-            'build-win64-cuda9.0': { BuildWin64() }
+            'build-win64-cuda10.0': { BuildWin64() }
          ])
        }
        milestone ordinal: 2
@@ -40,7 +40,6 @@ pipeline {
        script {
          parallel ([
            'test-win64-cpu': { TestWin64CPU() },
-            'test-win64-gpu-cuda9.0': { TestWin64GPU(cuda_target: 'cuda9') },
            'test-win64-gpu-cuda10.0': { TestWin64GPU(cuda_target: 'cuda10_0') },
            'test-win64-gpu-cuda10.1': { TestWin64GPU(cuda_target: 'cuda10_1') }
          ])
@@ -67,7 +66,7 @@ def checkoutSrcs() {
 }

 def BuildWin64() {
-  node('win64 && build') {
+  node('win64 && build && cuda10') {
    unstash name: 'srcs'
    echo "Building XGBoost for Windows AMD64 target..."
    bat "nvcc --version"
--- a/R-package/DESCRIPTION
+++ b/R-package/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: xgboost
 Type: Package
 Title: Extreme Gradient Boosting
-Version: 1.1.0.1
+Version: 1.1.1.1
 Date: 2020-02-21
 Authors@R: c(
  person("Tianqi", "Chen", role = c("aut"),
--- a/R-package/configure
+++ b/R-package/configure
@@ -2698,7 +2698,7 @@ fi
 if test `uname -s` = "Darwin"
 then
  OPENMP_CXXFLAGS='-Xclang -fopenmp'
-  OPENMP_LIB='/usr/local/lib/libomp.dylib'
+  OPENMP_LIB='-lomp'
  ac_pkg_openmp=no
  { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether OpenMP will work in a package" >&5
 $as_echo_n "checking whether OpenMP will work in a package... " >&6; }
--- a/R-package/configure.ac
+++ b/R-package/configure.ac
@@ -29,7 +29,7 @@ fi
 if test `uname -s` = "Darwin"
 then
  OPENMP_CXXFLAGS='-Xclang -fopenmp'
-  OPENMP_LIB='/usr/local/lib/libomp.dylib'
+  OPENMP_LIB='-lomp'
  ac_pkg_openmp=no
  AC_MSG_CHECKING([whether OpenMP will work in a package])
  AC_LANG_CONFTEST([AC_LANG_PROGRAM([[#include <omp.h>]], [[ return (omp_get_max_threads() <= 1); ]])])
--- a/cmake/Python_version.in
+++ b/cmake/Python_version.in
@@ -1 +1 @@
-@xgboost_VERSION_MAJOR@.@xgboost_VERSION_MINOR@.@xgboost_VERSION_PATCH@rc2
+@xgboost_VERSION_MAJOR@.@xgboost_VERSION_MINOR@.@xgboost_VERSION_PATCH@
--- a/cmake/xgboost.pc.in
+++ b/cmake/xgboost.pc.in
@@ -0,0 +1,12 @@
+prefix=@CMAKE_INSTALL_PREFIX@
+version=@xgboost_VERSION@
+exec_prefix=${prefix}/bin
+libdir=${prefix}/lib
+includedir=${prefix}/include
+
+Name: xgboost
+Description: XGBoost - Scalable and Flexible Gradient Boosting.
+Version: ${version}
+
+Cflags: -I${includedir}
+Libs: -L${libdir} -lxgboost
--- a/doc/dump.schema
+++ b/doc/dump.schema
@@ -0,0 +1,55 @@
+{
+    "$schema": "http://json-schema.org/draft-07/schema#",
+    "definitions": {
+        "split_node": {
+            "type": "object",
+            "properties": {
+                "nodeid": {
+                    "type": "number",
+                    "minimum": 0
+                },
+                "depth": {
+                    "type": "number",
+                    "minimum": 0
+                },
+                "yes": {
+                    "type": "number",
+                    "minimum": 0
+                },
+                "no": {
+                    "type": "number",
+                    "minimum": 0
+                },
+                "split": {
+                    "type": "string"
+                },
+                "children": {
+                    "type": "array",
+                    "items": {
+                        "oneOf": [
+                            {"$ref": "#/definitions/split_node"},
+                            {"$ref": "#/definitions/leaf_node"}
+                        ]
+                    },
+                    "maxItems": 2
+                }
+            },
+            "required": ["nodeid", "depth", "yes", "no", "split", "children"]
+        },
+        "leaf_node": {
+            "type": "object",
+            "properties": {
+                "nodeid": {
+                    "type": "number",
+                    "minimum": 0
+                },
+                "leaf": {
+                    "type": "number"
+                }
+            },
+            "required": ["nodeid", "leaf"]
+        }
+    },
+    "type": "object",
+    "$ref": "#/definitions/split_node"
+}
--- a/doc/tutorials/aft_survival_analysis.rst
+++ b/doc/tutorials/aft_survival_analysis.rst
@@ -35,7 +35,7 @@ There are four kinds of censoring:

 * **Uncensored**: the label is not censored and given as a single number.
 * **Right-censored**: the label is of form :math:`[a, +\infty)`, where :math:`a` is the lower bound.
-* **Left-censored**: the label is of form :math:`(-\infty, b]`, where :math:`b` is the upper bound.
+* **Left-censored**: the label is of form :math:`[0, b]`, where :math:`b` is the upper bound.
 * **Interval-censored**: the label is of form :math:`[a, b]`, where :math:`a` and :math:`b` are the lower and upper bounds, respectively.

 Right-censoring is the most commonly used.
@@ -83,7 +83,7 @@ Censoring type    Interval form        Lower bound finite? Upper bound finite?
 ================= ==================== =================== ===================
 Uncensored        :math:`[a, a]`       |tick|              |tick|
 Right-censored    :math:`[a, +\infty)` |tick|              |cross|
-Left-censored     :math:`(-\infty, b]` |cross|             |tick|
+Left-censored     :math:`[0, b]`       |tick|              |tick|
 Interval-censored :math:`[a, b]`       |tick|              |tick|
 ================= ==================== =================== ===================

@@ -102,7 +102,7 @@ Collect the lower bound numbers in one array (let's call it ``y_lower_bound``) a
  # Associate ranged labels with the data matrix.
  # This example shows each kind of censored labels.
  #                         uncensored    right     left  interval
-  y_lower_bound = np.array([      2.0,     3.0, -np.inf,     4.0])
+  y_lower_bound = np.array([      2.0,     3.0,     0.0,     4.0])
  y_upper_bound = np.array([      2.0, +np.inf,     4.0,     5.0])
  dtrain.set_float_info('label_lower_bound', y_lower_bound)
  dtrain.set_float_info('label_upper_bound', y_upper_bound)
@@ -120,7 +120,7 @@ Collect the lower bound numbers in one array (let's call it ``y_lower_bound``) a
  # Associate ranged labels with the data matrix.
  # This example shows each kind of censored labels.
  #                   uncensored  right  left  interval
-  y_lower_bound <- c(        2.,    3., -Inf,       4.)
+  y_lower_bound <- c(        2.,    3.,   0.,       4.)
  y_upper_bound <- c(        2.,  +Inf,   4.,       5.)
  setinfo(dtrain, 'label_lower_bound', y_lower_bound)
  setinfo(dtrain, 'label_upper_bound', y_upper_bound)
@@ -136,7 +136,7 @@ Now we are ready to invoke the training API:
            'aft_loss_distribution_scale': 1.20,
            'tree_method': 'hist', 'learning_rate': 0.05, 'max_depth': 2}
  bst = xgb.train(params, dtrain, num_boost_round=5,
-                  evals=[(dtrain, 'train'), (dvalid, 'valid')])
+                  evals=[(dtrain, 'train')])

 .. code-block:: r
  :caption: R
@@ -165,4 +165,4 @@ Currently, you can choose from three probability distributions for ``aft_loss_di
 ``extreme``               :math:`e^z e^{-\exp{z}}`
 ========================= ===========================================

-Note that it is not yet possible to set the ranged label using the scikit-learn interface (e.g. :class:`xgboost.XGBRegressor`). For now, you should use :class:`xgboost.train` with :class:`xgboost.DMatrix`.
+Note that it is not yet possible to set the ranged label using the scikit-learn interface (e.g. :class:`xgboost.XGBRegressor`). For now, you should use :class:`xgboost.train` with :class:`xgboost.DMatrix`.
--- a/jvm-packages/pom.xml
+++ b/jvm-packages/pom.xml
@@ -6,7 +6,7 @@

    <groupId>ml.dmlc</groupId>
    <artifactId>xgboost-jvm_2.12</artifactId>
-    <version>1.1.0-RC2</version>
+    <version>1.1.1</version>
    <packaging>pom</packaging>
    <name>XGBoost JVM Package</name>
    <description>JVM Package for XGBoost</description>
--- a/jvm-packages/xgboost4j-example/pom.xml
+++ b/jvm-packages/xgboost4j-example/pom.xml
@@ -6,10 +6,10 @@
    <parent>
        <groupId>ml.dmlc</groupId>
        <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.1.0-RC2</version>
+        <version>1.1.1</version>
    </parent>
    <artifactId>xgboost4j-example_2.12</artifactId>
-    <version>1.1.0-RC2</version>
+    <version>1.1.1</version>
    <packaging>jar</packaging>
    <build>
        <plugins>
@@ -26,7 +26,7 @@
        <dependency>
            <groupId>ml.dmlc</groupId>
            <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>
-            <version>1.1.0-RC2</version>
+            <version>1.1.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
@@ -37,7 +37,7 @@
        <dependency>
            <groupId>ml.dmlc</groupId>
            <artifactId>xgboost4j-flink_${scala.binary.version}</artifactId>
-            <version>1.1.0-RC2</version>
+            <version>1.1.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.commons</groupId>
--- a/jvm-packages/xgboost4j-flink/pom.xml
+++ b/jvm-packages/xgboost4j-flink/pom.xml
@@ -6,10 +6,10 @@
    <parent>
        <groupId>ml.dmlc</groupId>
        <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.1.0-RC2</version>
+        <version>1.1.1</version>
    </parent>
    <artifactId>xgboost4j-flink_2.12</artifactId>
-    <version>1.1.0-RC2</version>
+    <version>1.1.1</version>
    <build>
        <plugins>
            <plugin>
@@ -26,7 +26,7 @@
        <dependency>
            <groupId>ml.dmlc</groupId>
            <artifactId>xgboost4j_${scala.binary.version}</artifactId>
-            <version>1.1.0-RC2</version>
+            <version>1.1.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.commons</groupId>
--- a/jvm-packages/xgboost4j-spark/pom.xml
+++ b/jvm-packages/xgboost4j-spark/pom.xml
@@ -6,7 +6,7 @@
    <parent>
        <groupId>ml.dmlc</groupId>
        <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.1.0-RC2</version>
+        <version>1.1.1</version>
    </parent>
    <artifactId>xgboost4j-spark_2.12</artifactId>
    <build>
@@ -24,7 +24,7 @@
        <dependency>
            <groupId>ml.dmlc</groupId>
            <artifactId>xgboost4j_${scala.binary.version}</artifactId>
-            <version>1.1.0-RC2</version>
+            <version>1.1.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
--- a/jvm-packages/xgboost4j/pom.xml
+++ b/jvm-packages/xgboost4j/pom.xml
@@ -6,10 +6,10 @@
    <parent>
        <groupId>ml.dmlc</groupId>
        <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.1.0-RC2</version>
+        <version>1.1.1</version>
    </parent>
    <artifactId>xgboost4j_2.12</artifactId>
-    <version>1.1.0-RC2</version>
+    <version>1.1.1</version>
    <packaging>jar</packaging>

    <dependencies>
--- a/python-package/xgboost/VERSION
+++ b/python-package/xgboost/VERSION
@@ -1 +1 @@
-1.1.0rc2
+1.1.1
--- a/python-package/xgboost/core.py
+++ b/python-package/xgboost/core.py
@@ -1467,6 +1467,7 @@ class Booster(object):
        self._validate_features(data)
        return self.eval_set([(data, name)], iteration)

+    # pylint: disable=too-many-function-args
    def predict(self,
                data,
                output_margin=False,
@@ -1588,7 +1589,7 @@ class Booster(object):
                ngroup = int(chunk_size / ((data.num_col() + 1) *
                                           (data.num_col() + 1)))
                if ngroup == 1:
-                    preds = preds.reshape(nrow,
+                    preds = preds.reshape(nrow,  # pylint: disable=too-many-function-args
                                          data.num_col() + 1,
                                          data.num_col() + 1)
                else:
--- a/src/common/column_matrix.h
+++ b/src/common/column_matrix.h
@@ -82,14 +82,16 @@ template <typename BinIdxType>
 class DenseColumn: public Column<BinIdxType> {
 public:
  DenseColumn(ColumnType type, common::Span<const BinIdxType> index,
-              uint32_t index_base,
-              const std::vector<bool>::const_iterator missing_flags)
+              uint32_t index_base, const std::vector<bool>& missing_flags,
+              size_t feature_offset)
      : Column<BinIdxType>(type, index, index_base),
-        missing_flags_(missing_flags) {}
-  bool IsMissing(size_t idx) const { return missing_flags_[idx]; }
+        missing_flags_(missing_flags),
+        feature_offset_(feature_offset) {}
+  bool IsMissing(size_t idx) const { return missing_flags_[feature_offset_ + idx]; }
 private:
  /* flags for missing values in dense columns */
-  std::vector<bool>::const_iterator missing_flags_;
+  const std::vector<bool>& missing_flags_;
+  size_t feature_offset_;
 };

 /*! \brief a collection of columns, with support for construction from
@@ -208,10 +210,8 @@ class ColumnMatrix {
                                                 column_size };
    std::unique_ptr<const Column<BinIdxType> > res;
    if (type_[fid] == ColumnType::kDenseColumn) {
-      std::vector<bool>::const_iterator column_iterator = missing_flags_.begin();
-      advance(column_iterator, feature_offset);  // increment iterator to right position
      res.reset(new DenseColumn<BinIdxType>(type_[fid], bin_index, index_base_[fid],
-                                            column_iterator));
+                                             missing_flags_, feature_offset));
    } else {
      res.reset(new SparseColumn<BinIdxType>(type_[fid], bin_index, index_base_[fid],
                                       {&row_ind_[feature_offset], column_size}));
--- a/src/learner.cc
+++ b/src/learner.cc
@@ -689,15 +689,23 @@ class LearnerIO : public LearnerConfiguration {
      warn_old_model = false;
    }

-    if (mparam_.major_version >= 1) {
-      learner_model_param_ = LearnerModelParam(mparam_,
-                                               obj_->ProbToMargin(mparam_.base_score));
-    } else {
+    if (mparam_.major_version < 1) {
      // Before 1.0.0, base_score is saved as a transformed value, and there's no version
-      // attribute in the saved model.
-      learner_model_param_ = LearnerModelParam(mparam_, mparam_.base_score);
+      // attribute (saved a 0) in the saved model.
+      std::string multi{"multi:"};
+      if (!std::equal(multi.cbegin(), multi.cend(), tparam_.objective.cbegin())) {
+        HostDeviceVector<float> t;
+        t.HostVector().resize(1);
+        t.HostVector().at(0) = mparam_.base_score;
+        this->obj_->PredTransform(&t);
+        auto base_score = t.HostVector().at(0);
+        mparam_.base_score = base_score;
+      }
      warn_old_model = true;
    }
+
+    learner_model_param_ =
+        LearnerModelParam(mparam_, obj_->ProbToMargin(mparam_.base_score));
    if (attributes_.find("objective") != attributes_.cend()) {
      auto obj_str = attributes_.at("objective");
      auto j_obj = Json::Load({obj_str.c_str(), obj_str.size()});
--- a/src/objective/regression_obj.cu
+++ b/src/objective/regression_obj.cu
@@ -41,10 +41,11 @@ struct RegLossParam : public XGBoostParameter<RegLossParam> {
 template<typename Loss>
 class RegLossObj : public ObjFunction {
 protected:
-  HostDeviceVector<int> label_correct_;
+  HostDeviceVector<float> additional_input_;

 public:
-  RegLossObj() = default;
+  // 0 - label_correct flag, 1 - scale_pos_weight, 2 - is_null_weight
+  RegLossObj(): additional_input_(3) {}

  void Configure(const std::vector<std::pair<std::string, std::string> >& args) override {
    param_.UpdateAllowUnknown(args);
@@ -64,8 +65,7 @@ class RegLossObj : public ObjFunction {
    size_t const ndata = preds.Size();
    out_gpair->Resize(ndata);
    auto device = tparam_->gpu_id;
-    label_correct_.Resize(1);
-    label_correct_.Fill(1);
+    additional_input_.HostVector().begin()[0] = 1;  // Fill the label_correct flag

    bool is_null_weight = info.weights_.Size() == 0;
    if (!is_null_weight) {
@@ -73,35 +73,37 @@ class RegLossObj : public ObjFunction {
          << "Number of weights should be equal to number of data points.";
    }
    auto scale_pos_weight = param_.scale_pos_weight;
-    common::Transform<>::Init(
-        [=] XGBOOST_DEVICE(size_t _idx,
-                           common::Span<int> _label_correct,
+    additional_input_.HostVector().begin()[1] = scale_pos_weight;
+    additional_input_.HostVector().begin()[2] = is_null_weight;
+
+    common::Transform<>::Init([] XGBOOST_DEVICE(size_t _idx,
+                           common::Span<float> _additional_input,
                           common::Span<GradientPair> _out_gpair,
                           common::Span<const bst_float> _preds,
                           common::Span<const bst_float> _labels,
                           common::Span<const bst_float> _weights) {
+          const float _scale_pos_weight = _additional_input[1];
+          const bool _is_null_weight = _additional_input[2];
+
          bst_float p = Loss::PredTransform(_preds[_idx]);
-          bst_float w = is_null_weight ? 1.0f : _weights[_idx];
+          bst_float w = _is_null_weight ? 1.0f : _weights[_idx];
          bst_float label = _labels[_idx];
          if (label == 1.0f) {
-            w *= scale_pos_weight;
+            w *= _scale_pos_weight;
          }
          if (!Loss::CheckLabel(label)) {
            // If there is an incorrect label, the host code will know.
-            _label_correct[0] = 0;
+            _additional_input[0] = 0;
          }
          _out_gpair[_idx] = GradientPair(Loss::FirstOrderGradient(p, label) * w,
                                          Loss::SecondOrderGradient(p, label) * w);
        },
        common::Range{0, static_cast<int64_t>(ndata)}, device).Eval(
-            &label_correct_, out_gpair, &preds, &info.labels_, &info.weights_);
+            &additional_input_, out_gpair, &preds, &info.labels_, &info.weights_);

-    // copy "label correct" flags back to host
-    std::vector<int>& label_correct_h = label_correct_.HostVector();
-    for (auto const flag : label_correct_h) {
-      if (flag == 0) {
-        LOG(FATAL) << Loss::LabelErrorMsg();
-      }
+    auto const flag = additional_input_.HostVector().begin()[0];
+    if (flag == 0) {
+      LOG(FATAL) << Loss::LabelErrorMsg();
    }
  }

--- a/src/tree/tree_model.cc
+++ b/src/tree/tree_model.cc
@@ -68,20 +68,20 @@ class TreeGenerator {
    return result;
  }

-  virtual std::string Indicator(RegTree const& tree, int32_t nid, uint32_t depth) {
+  virtual std::string Indicator(RegTree const& tree, int32_t nid, uint32_t depth) const {
    return "";
  }
-  virtual std::string Integer(RegTree const& tree, int32_t nid, uint32_t depth) {
+  virtual std::string Integer(RegTree const& tree, int32_t nid, uint32_t depth) const {
    return "";
  }
-  virtual std::string Quantitive(RegTree const& tree, int32_t nid, uint32_t depth) {
+  virtual std::string Quantitive(RegTree const& tree, int32_t nid, uint32_t depth) const {
    return "";
  }
-  virtual std::string NodeStat(RegTree const& tree, int32_t nid) {
+  virtual std::string NodeStat(RegTree const& tree, int32_t nid) const {
    return "";
  }

-  virtual std::string PlainNode(RegTree const& tree, int32_t nid, uint32_t depth) = 0;
+  virtual std::string PlainNode(RegTree const& tree, int32_t nid, uint32_t depth) const = 0;

  virtual std::string SplitNode(RegTree const& tree, int32_t nid, uint32_t depth) {
    auto const split_index = tree[nid].SplitIndex();
@@ -110,7 +110,7 @@ class TreeGenerator {
    return result;
  }

-  virtual std::string LeafNode(RegTree const& tree, int32_t nid, uint32_t depth) = 0;
+  virtual std::string LeafNode(RegTree const& tree, int32_t nid, uint32_t depth) const = 0;
  virtual std::string BuildTree(RegTree const& tree, int32_t nid, uint32_t depth) = 0;

 public:
@@ -181,7 +181,7 @@ class TextGenerator : public TreeGenerator {
  TextGenerator(FeatureMap const& fmap, std::string const& attrs, bool with_stats) :
      TreeGenerator(fmap, with_stats) {}

-  std::string LeafNode(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string LeafNode(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    static std::string kLeafTemplate = "{tabs}{nid}:leaf={leaf}{stats}";
    static std::string kStatTemplate = ",cover={cover}";
    std::string result = SuperT::Match(
@@ -195,7 +195,7 @@ class TextGenerator : public TreeGenerator {
    return result;
  }

-  std::string Indicator(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string Indicator(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    static std::string const kIndicatorTemplate = "{nid}:[{fname}] yes={yes},no={no}";
    int32_t nyes = tree[nid].DefaultLeft() ?
                   tree[nid].RightChild() : tree[nid].LeftChild();
@@ -211,7 +211,7 @@ class TextGenerator : public TreeGenerator {

  std::string SplitNodeImpl(
      RegTree const& tree, int32_t nid, std::string const& template_str,
-      std::string cond, uint32_t depth) {
+      std::string cond, uint32_t depth) const {
    auto split_index = tree[nid].SplitIndex();
    std::string const result = SuperT::Match(
        template_str,
@@ -226,7 +226,7 @@ class TextGenerator : public TreeGenerator {
    return result;
  }

-  std::string Integer(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string Integer(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    static std::string const kIntegerTemplate =
        "{tabs}{nid}:[{fname}<{cond}] yes={left},no={right},missing={missing}";
    auto cond = tree[nid].SplitCond();
@@ -238,21 +238,21 @@ class TextGenerator : public TreeGenerator {
                         std::to_string(integer_threshold), depth);
  }

-  std::string Quantitive(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string Quantitive(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    static std::string const kQuantitiveTemplate =
        "{tabs}{nid}:[{fname}<{cond}] yes={left},no={right},missing={missing}";
    auto cond = tree[nid].SplitCond();
    return SplitNodeImpl(tree, nid, kQuantitiveTemplate, SuperT::ToStr(cond), depth);
  }

-  std::string PlainNode(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string PlainNode(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    auto cond = tree[nid].SplitCond();
    static std::string const kNodeTemplate =
        "{tabs}{nid}:[f{fname}<{cond}] yes={left},no={right},missing={missing}";
    return SplitNodeImpl(tree, nid, kNodeTemplate, SuperT::ToStr(cond), depth);
  }

-  std::string NodeStat(RegTree const& tree, int32_t nid) override {
+  std::string NodeStat(RegTree const& tree, int32_t nid) const override {
    static std::string const kStatTemplate = ",gain={loss_chg},cover={sum_hess}";
    std::string const result = SuperT::Match(
        kStatTemplate,
@@ -297,7 +297,7 @@ class JsonGenerator : public TreeGenerator {
  JsonGenerator(FeatureMap const& fmap, std::string attrs, bool with_stats) :
      TreeGenerator(fmap, with_stats) {}

-  std::string Indent(uint32_t depth) {
+  std::string Indent(uint32_t depth) const {
    std::string result;
    for (uint32_t i = 0; i < depth + 1; ++i) {
      result += "  ";
@@ -305,7 +305,7 @@ class JsonGenerator : public TreeGenerator {
    return result;
  }

-  std::string LeafNode(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string LeafNode(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    static std::string const kLeafTemplate =
        R"L({ "nodeid": {nid}, "leaf": {leaf} {stat}})L";
    static std::string const kStatTemplate =
@@ -321,11 +321,11 @@ class JsonGenerator : public TreeGenerator {
    return result;
  }

-  std::string Indicator(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string Indicator(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    int32_t nyes = tree[nid].DefaultLeft() ?
                   tree[nid].RightChild() : tree[nid].LeftChild();
    static std::string const kIndicatorTemplate =
-        R"ID( "nodeid": {nid}, "depth": {depth}, "split": "{fname}", "yes": {yes}, "no": {no}})ID";
+        R"ID( "nodeid": {nid}, "depth": {depth}, "split": "{fname}", "yes": {yes}, "no": {no})ID";
    auto split_index = tree[nid].SplitIndex();
    auto result = SuperT::Match(
        kIndicatorTemplate,
@@ -337,8 +337,9 @@ class JsonGenerator : public TreeGenerator {
    return result;
  }

-  std::string SplitNodeImpl(RegTree const& tree, int32_t nid,
-                            std::string const& template_str, std::string cond, uint32_t depth) {
+  std::string SplitNodeImpl(RegTree const &tree, int32_t nid,
+                            std::string const &template_str, std::string cond,
+                            uint32_t depth) const {
    auto split_index = tree[nid].SplitIndex();
    std::string const result = SuperT::Match(
        template_str,
@@ -353,7 +354,7 @@ class JsonGenerator : public TreeGenerator {
    return result;
  }

-  std::string Integer(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string Integer(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    auto cond = tree[nid].SplitCond();
    const bst_float floored = std::floor(cond);
    const int32_t integer_threshold
@@ -367,7 +368,7 @@ class JsonGenerator : public TreeGenerator {
                         std::to_string(integer_threshold), depth);
  }

-  std::string Quantitive(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string Quantitive(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    static std::string const kQuantitiveTemplate =
        R"I( "nodeid": {nid}, "depth": {depth}, "split": "{fname}", )I"
        R"I("split_condition": {cond}, "yes": {left}, "no": {right}, )I"
@@ -376,7 +377,7 @@ class JsonGenerator : public TreeGenerator {
    return SplitNodeImpl(tree, nid, kQuantitiveTemplate, SuperT::ToStr(cond), depth);
  }

-  std::string PlainNode(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string PlainNode(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    auto cond = tree[nid].SplitCond();
    static std::string const kNodeTemplate =
        R"I( "nodeid": {nid}, "depth": {depth}, "split": {fname}, )I"
@@ -385,7 +386,7 @@ class JsonGenerator : public TreeGenerator {
    return SplitNodeImpl(tree, nid, kNodeTemplate, SuperT::ToStr(cond), depth);
  }

-  std::string NodeStat(RegTree const& tree, int32_t nid) override {
+  std::string NodeStat(RegTree const& tree, int32_t nid) const override {
    static std::string kStatTemplate =
        R"S(, "gain": {loss_chg}, "cover": {sum_hess})S";
    auto result = SuperT::Match(
@@ -529,7 +530,7 @@ class GraphvizGenerator : public TreeGenerator {
 protected:
  // Only indicator is different, so we combine all different node types into this
  // function.
-  std::string PlainNode(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string PlainNode(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    auto split = tree[nid].SplitIndex();
    auto cond = tree[nid].SplitCond();
    static std::string const kNodeTemplate =
@@ -563,7 +564,7 @@ class GraphvizGenerator : public TreeGenerator {
    return result;
  };

-  std::string LeafNode(RegTree const& tree, int32_t nid, uint32_t depth) override {
+  std::string LeafNode(RegTree const& tree, int32_t nid, uint32_t depth) const override {
    static std::string const kLeafTemplate =
        "    {nid} [ label=\"leaf={leaf-value}\" {params}]\n";
    auto result = SuperT::Match(kLeafTemplate, {
--- a/tests/cpp/tree/test_tree_model.cc
+++ b/tests/cpp/tree/test_tree_model.cc
@@ -151,6 +151,10 @@ TEST(Tree, DumpJson) {

  str = tree.DumpModel(fmap, false, "json");
  ASSERT_EQ(str.find("cover"), std::string::npos);
+
+
+  auto j_tree = Json::Load({str.c_str(), str.size()});
+  ASSERT_EQ(get<Array>(j_tree["children"]).size(), 2);
 }

 TEST(Tree, DumpText) {
--- a/tests/pytest.ini
+++ b/tests/pytest.ini
@@ -1,3 +1,4 @@
 [pytest]
 markers =
-    mgpu: Mark a test that requires multiple GPUs to run.
+    mgpu: Mark a test that requires multiple GPUs to run.
+    ci: Mark a test that runs only on CI.
--- a/tests/python-gpu/test_gpu_basic_models.py
+++ b/tests/python-gpu/test_gpu_basic_models.py
@@ -12,25 +12,15 @@ rng = np.random.RandomState(1994)
 class TestGPUBasicModels(unittest.TestCase):
    cputest = test_bm.TestModels()

-    def test_eta_decay_gpu_hist(self):
-        self.cputest.run_eta_decay('gpu_hist')
-
-    def test_deterministic_gpu_hist(self):
-        kRows = 1000
-        kCols = 64
-        kClasses = 4
-        # Create large values to force rounding.
-        X = np.random.randn(kRows, kCols) * 1e4
-        y = np.random.randint(0, kClasses, size=kRows)
-
+    def run_cls(self, X, y, deterministic):
        cls = xgb.XGBClassifier(tree_method='gpu_hist',
-                                deterministic_histogram=True,
+                                deterministic_histogram=deterministic,
                                single_precision_histogram=True)
        cls.fit(X, y)
        cls.get_booster().save_model('test_deterministic_gpu_hist-0.json')

        cls = xgb.XGBClassifier(tree_method='gpu_hist',
-                                deterministic_histogram=True,
+                                deterministic_histogram=deterministic,
                                single_precision_histogram=True)
        cls.fit(X, y)
        cls.get_booster().save_model('test_deterministic_gpu_hist-1.json')
@@ -40,7 +30,24 @@ class TestGPUBasicModels(unittest.TestCase):
        with open('test_deterministic_gpu_hist-1.json', 'r') as fd:
            model_1 = fd.read()

-        assert hash(model_0) == hash(model_1)
-
        os.remove('test_deterministic_gpu_hist-0.json')
        os.remove('test_deterministic_gpu_hist-1.json')
+
+        return hash(model_0), hash(model_1)
+
+    def test_eta_decay_gpu_hist(self):
+        self.cputest.run_eta_decay('gpu_hist')
+
+    def test_deterministic_gpu_hist(self):
+        kRows = 1000
+        kCols = 64
+        kClasses = 4
+        # Create large values to force rounding.
+        X = np.random.randn(kRows, kCols) * 1e4
+        y = np.random.randint(0, kClasses, size=kRows) * 1e4
+
+        model_0, model_1 = self.run_cls(X, y, True)
+        assert model_0 == model_1
+
+        model_0, model_1 = self.run_cls(X, y, False)
+        assert model_0 != model_1
--- a/tests/python/test_basic_models.py
+++ b/tests/python/test_basic_models.py
@@ -325,7 +325,7 @@ class TestModels(unittest.TestCase):
        assert locale.getpreferredencoding(False) == loc

    @pytest.mark.skipif(**tm.no_json_schema())
-    def test_json_schema(self):
+    def test_json_io_schema(self):
        import jsonschema
        model_path = 'test_json_schema.json'
        path = os.path.dirname(
@@ -342,3 +342,35 @@ class TestModels(unittest.TestCase):
        jsonschema.validate(instance=json_model(model_path, parameters),
                            schema=schema)
        os.remove(model_path)
+
+    @pytest.mark.skipif(**tm.no_json_schema())
+    def test_json_dump_schema(self):
+        import jsonschema
+
+        def validate_model(parameters):
+            X = np.random.random((100, 30))
+            y = np.random.randint(0, 4, size=(100,))
+
+            parameters['num_class'] = 4
+            m = xgb.DMatrix(X, y)
+
+            booster = xgb.train(parameters, m)
+            dump = booster.get_dump(dump_format='json')
+
+            for i in range(len(dump)):
+                jsonschema.validate(instance=json.loads(dump[i]),
+                                    schema=schema)
+
+        path = os.path.dirname(
+            os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+        doc = os.path.join(path, 'doc', 'dump.schema')
+        with open(doc, 'r') as fd:
+            schema = json.load(fd)
+
+        parameters = {'tree_method': 'hist', 'booster': 'gbtree',
+                      'objective': 'multi:softmax'}
+        validate_model(parameters)
+
+        parameters = {'tree_method': 'hist', 'booster': 'dart',
+                      'objective': 'multi:softmax'}
+        validate_model(parameters)
--- a/tests/python/test_model_compatibility.py
+++ b/tests/python/test_model_compatibility.py
@@ -4,6 +4,7 @@ import generate_models as gm
 import json
 import zipfile
 import pytest
+import copy


 def run_model_param_check(config):
@@ -124,6 +125,9 @@ def test_model_compatibility():
        if name.startswith('xgboost-'):
            booster = xgboost.Booster(model_file=path)
            run_booster_check(booster, name)
+            # Do full serialization.
+            booster = copy.copy(booster)
+            run_booster_check(booster, name)
        elif name.startswith('xgboost_scikit'):
            run_scikit_model_check(name, path)
        else:
Author	SHA1	Message	Date
Philip Hyunsu Cho	34408a7fdc	Release patch release 1.1.1 with faster CPU performance (#5732 ) * Fix release degradation (#5720) * fix release degradation, related to 5666 * less resizes Co-authored-by: SHVETS, KIRILL <kirill.shvets@intel.com> * Make 1.1.1 patch release * Disable too-many-function-args pylint warning for predict() * Fix Windows CI * Remove cpplint Co-authored-by: ShvetsKS <33296480+ShvetsKS@users.noreply.github.com> Co-authored-by: SHVETS, KIRILL <kirill.shvets@intel.com>	2020-06-04 10:56:07 -07:00
Philip Hyunsu Cho	f9b246f5ee	Add pkgconfig to cmake (#5744 ) (#5748 ) * Add pkgconfig to cmake * Move xgboost.pc.in to cmake/ Co-authored-by: Peter Jung <peter@jung.ninja> Co-authored-by: Peter Jung <peter.jung@heureka.cz> Co-authored-by: Hyunsu Cho <chohyu01@cs.washington.edu>	2020-06-02 12:04:27 -07:00
Jiaming Yuan	8467880aeb	Fix loading old model. (#5724 ) (#5737 ) * Add test.	2020-06-01 04:32:24 +08:00
Jiaming Yuan	e74560c86a	[CI] Backport Remove CUDA 9.0 from Windows CI. (#5674 ) (#5738 ) * [CI] Remove CUDA 9.0 from Windows CI. (#5674) * Remove CUDA 9.0 on Windows CI. * Require cuda10 tag, to differentiate Co-authored-by: Philip Hyunsu Cho <chohyu01@cs.washington.edu> * Pylint. Co-authored-by: Philip Hyunsu Cho <chohyu01@cs.washington.edu>	2020-05-31 21:35:00 +08:00
Hyunsu Cho	882b966536	[Doc] Fix typos in AFT tutorial	2020-05-27 03:09:46 -07:00
Philip Hyunsu Cho	115e4c3360	[R] Fix duplicated libomp.dylib error on Mac OSX (#5701 )	2020-05-24 23:38:42 -07:00
Hyunsu Cho	f5d4fddafe	Release 1.1.0	2020-05-17 00:26:22 -07:00
Jiaming Yuan	66690f3d07	Add JSON schema to model dump. (#5660 )	2020-05-15 12:26:49 +08:00
Rory Mitchell	c42f533ae9	Resolve vector<bool>::iterator crash (#5642 )	2020-05-11 18:14:41 +08:00
Philip Hyunsu Cho	751160b69c	Upgrade to CUDA 10.0 (#5649 ) Co-authored-by: fis <jm.yuan@outlook.com>	2020-05-11 18:04:47 +08:00
@@ -1 +1 @@
 .1.0rc2
 .1.1