Release 1.2.0

* Fix sklearn doc. (#5980)

* Enforce tree order in JSON. (#5974)

* Make JSON model IO more future proof by using tree id in model loading.

* Fix dask predict shape infer. (#5989)

* [Breaking] Fix .predict() method and add .predict_proba() in xgboost.dask.DaskXGBClassifier (#5986)

Jenkinsfile

@@ -92,7 +92,7 @@ pipeline {
             'test-python-gpu-cuda10.2': { TestPythonGPU(host_cuda_version: '10.2') },
             'test-python-gpu-cuda11.0-cross': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '11.0') },
             'test-python-gpu-cuda11.0': { TestPythonGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
-            'test-python-mgpu-cuda10.2': { TestPythonGPU(artifact_cuda_version: '10.2', host_cuda_version: '10.2', multi_gpu: true) },
+            'test-python-mgpu-cuda10.2': { TestPythonGPU(artifact_cuda_version: '10.0', host_cuda_version: '10.2', multi_gpu: true) },
             'test-cpp-gpu-cuda10.2': { TestCppGPU(artifact_cuda_version: '10.2', host_cuda_version: '10.2') },
             'test-cpp-gpu-cuda11.0': { TestCppGPU(artifact_cuda_version: '11.0', host_cuda_version: '11.0') },
             'test-jvm-jdk8-cuda10.0': { CrossTestJVMwithJDKGPU(artifact_cuda_version: '10.0', host_cuda_version: '10.0') },
@@ -285,7 +285,7 @@ def BuildCUDA(args) {
 }
 
 def BuildJVMPackagesWithCUDA(args) {
-  node('linux && gpu') {
+  node('linux && mgpu') {
     unstash name: 'srcs'
     echo "Build XGBoost4J-Spark with Spark ${args.spark_version}, CUDA ${args.cuda_version}"
     def container_type = "jvm_gpu_build"
@@ -472,10 +472,11 @@ def DeployJVMPackages(args) {
     unstash name: 'srcs'
     if (env.BRANCH_NAME == 'master' || env.BRANCH_NAME.startsWith('release')) {
       echo 'Deploying to xgboost-maven-repo S3 repo...'
-      def container_type = "jvm"
-      def docker_binary = "docker"
       sh """
-      ${dockerRun} ${container_type} ${docker_binary} tests/ci_build/deploy_jvm_packages.sh ${args.spark_version}
+      ${dockerRun} jvm docker tests/ci_build/deploy_jvm_packages.sh ${args.spark_version} 0
+      """
+      sh """
+      ${dockerRun} jvm_gpu_build docker --build-arg CUDA_VERSION=10.0 tests/ci_build/deploy_jvm_packages.sh ${args.spark_version} 1
       """
     }
     deleteDir()

cmake/Python_version.in

@@ -1 +1 @@
-@xgboost_VERSION_MAJOR@.@xgboost_VERSION_MINOR@.@xgboost_VERSION_PATCH@-SNAPSHOT
+@xgboost_VERSION_MAJOR@.@xgboost_VERSION_MINOR@.@xgboost_VERSION_PATCH@

jvm-packages/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>ml.dmlc</groupId>
     <artifactId>xgboost-jvm_2.12</artifactId>
-    <version>1.2.0-SNAPSHOT</version>
+    <version>1.2.0</version>
     <packaging>pom</packaging>
     <name>XGBoost JVM Package</name>
     <description>JVM Package for XGBoost</description>

jvm-packages/xgboost4j-example/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.2.0-SNAPSHOT</version>
+        <version>1.2.0</version>
     </parent>
     <artifactId>xgboost4j-example_2.12</artifactId>
-    <version>1.2.0-SNAPSHOT</version>
+    <version>1.2.0</version>
     <packaging>jar</packaging>
     <build>
         <plugins>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-spark_${scala.binary.version}</artifactId>
-            <version>1.2.0-SNAPSHOT</version>
+            <version>1.2.0</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>
@@ -37,7 +37,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j-flink_${scala.binary.version}</artifactId>
-            <version>1.2.0-SNAPSHOT</version>
+            <version>1.2.0</version>
         </dependency>
         <dependency>
             <groupId>org.apache.commons</groupId>

jvm-packages/xgboost4j-flink/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.2.0-SNAPSHOT</version>
+        <version>1.2.0</version>
     </parent>
     <artifactId>xgboost4j-flink_2.12</artifactId>
-    <version>1.2.0-SNAPSHOT</version>
+    <version>1.2.0</version>
     <build>
         <plugins>
             <plugin>
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>ml.dmlc</groupId>
             <artifactId>xgboost4j_${scala.binary.version}</artifactId>
-            <version>1.2.0-SNAPSHOT</version>
+            <version>1.2.0</version>
         </dependency>
         <dependency>
             <groupId>org.apache.commons</groupId>

jvm-packages/xgboost4j-spark/pom.xml

@@ -6,7 +6,7 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.2.0-SNAPSHOT</version>
+        <version>1.2.0</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>1.2.0-SNAPSHOT</version>
+            <version>1.2.0</version>
         </dependency>
         <dependency>
             <groupId>org.apache.spark</groupId>

jvm-packages/xgboost4j/pom.xml

@@ -6,10 +6,10 @@
     <parent>
         <groupId>ml.dmlc</groupId>
         <artifactId>xgboost-jvm_2.12</artifactId>
-        <version>1.2.0-SNAPSHOT</version>
+        <version>1.2.0</version>
     </parent>
     <artifactId>xgboost4j_2.12</artifactId>
-    <version>1.2.0-SNAPSHOT</version>
+    <version>1.2.0</version>
     <packaging>jar</packaging>
 
     <dependencies>

python-package/xgboost/VERSION

@@ -1 +1 @@
-1.2.0-SNAPSHOT
+1.2.0

python-package/xgboost/dask.py

@@ -738,7 +738,8 @@ async def _predict_async(client: Client, model, data, *args,
             predt = booster.predict(data=local_x,
                                     validate_features=local_x.num_row() != 0,
                                     *args)
-            ret = (delayed(predt), order)
+            columns = 1 if len(predt.shape) == 1 else predt.shape[1]
+            ret = ((delayed(predt), columns), order)
             predictions.append(ret)
         return predictions
 
@@ -775,7 +776,9 @@ async def _predict_async(client: Client, model, data, *args,
     # See https://docs.dask.org/en/latest/array-creation.html
     arrays = []
     for i, shape in enumerate(shapes):
-        arrays.append(da.from_delayed(results[i], shape=(shape[0], ),
+        arrays.append(da.from_delayed(
+            results[i][0], shape=(shape[0],)
+            if results[i][1] == 1 else (shape[0], results[i][1]),
             dtype=numpy.float32))
     predictions = await da.concatenate(arrays, axis=0)
     return predictions
@@ -978,6 +981,7 @@ class DaskScikitLearnBase(XGBModel):
     def client(self, clt):
         self._client = clt
 
+
 @xgboost_model_doc("""Implementation of the Scikit-Learn API for XGBoost.""",
                    ['estimators', 'model'])
 class DaskXGBRegressor(DaskScikitLearnBase, XGBRegressorBase):
@@ -1032,9 +1036,6 @@ class DaskXGBRegressor(DaskScikitLearnBase, XGBRegressorBase):
     ['estimators', 'model']
 )
 class DaskXGBClassifier(DaskScikitLearnBase, XGBClassifierBase):
-    # pylint: disable=missing-docstring
-    _client = None
-
     async def _fit_async(self, X, y,
                          sample_weights=None,
                          eval_set=None,
@@ -1078,13 +1079,34 @@ class DaskXGBClassifier(DaskScikitLearnBase, XGBClassifierBase):
         return self.client.sync(self._fit_async, X, y, sample_weights,
                                 eval_set, sample_weight_eval_set, verbose)
 
-    async def _predict_async(self, data):
+    async def _predict_proba_async(self, data):
+        _assert_dask_support()
+
         test_dmatrix = await DaskDMatrix(client=self.client, data=data,
                                          missing=self.missing)
         pred_probs = await predict(client=self.client,
                                    model=self.get_booster(), data=test_dmatrix)
         return pred_probs
 
+    def predict_proba(self, data):  # pylint: disable=arguments-differ,missing-docstring
+        _assert_dask_support()
+        return self.client.sync(self._predict_proba_async, data)
+
+    async def _predict_async(self, data):
+        _assert_dask_support()
+
+        test_dmatrix = await DaskDMatrix(client=self.client, data=data,
+                                         missing=self.missing)
+        pred_probs = await predict(client=self.client,
+                                   model=self.get_booster(), data=test_dmatrix)
+
+        if self.n_classes_ == 2:
+            preds = (pred_probs > 0.5).astype(int)
+        else:
+            preds = da.argmax(pred_probs, axis=1)
+
+        return preds
+
     def predict(self, data):  # pylint: disable=arguments-differ
         _assert_dask_support()
         return self.client.sync(self._predict_async, data)

python-package/xgboost/sklearn.py

@@ -77,7 +77,7 @@ __model_doc = '''
     gamma : float
         Minimum loss reduction required to make a further partition on a leaf
         node of the tree.
-    min_child_weight : int
+    min_child_weight : float
         Minimum sum of instance weight(hessian) needed in a child.
     max_delta_step : int
         Maximum delta step we allow each tree's weight estimation to be.
@@ -750,7 +750,10 @@ class XGBModel(XGBModelBase):
 
 @xgboost_model_doc(
     "Implementation of the scikit-learn API for XGBoost classification.",
-    ['model', 'objective'])
+    ['model', 'objective'], extra_parameters='''
+    n_estimators : int
+        Number of boosting rounds.
+''')
 class XGBClassifier(XGBModel, XGBClassifierBase):
     # pylint: disable=missing-docstring,invalid-name,too-many-instance-attributes
     def __init__(self, objective="binary:logistic", **kwargs):
@@ -1033,7 +1036,10 @@ class XGBRegressor(XGBModel, XGBRegressorBase):
 
 @xgboost_model_doc(
     "scikit-learn API for XGBoost random forest regression.",
-    ['model', 'objective'])
+    ['model', 'objective'], extra_parameters='''
+    n_estimators : int
+        Number of trees in random forest to fit.
+''')
 class XGBRFRegressor(XGBRegressor):
     # pylint: disable=missing-docstring
     def __init__(self, learning_rate=1, subsample=0.8, colsample_bynode=0.8,

src/gbm/gbtree_model.cc

@@ -1,6 +1,8 @@
 /*!
- * Copyright 2019 by Contributors
+ * Copyright 2019-2020 by Contributors
  */
+#include <utility>
+
 #include "xgboost/json.h"
 #include "xgboost/logging.h"
 #include "gbtree_model.h"
@@ -41,15 +43,14 @@ void GBTreeModel::SaveModel(Json* p_out) const {
   auto& out = *p_out;
   CHECK_EQ(param.num_trees, static_cast<int>(trees.size()));
   out["gbtree_model_param"] = ToJson(param);
-  std::vector<Json> trees_json;
+  std::vector<Json> trees_json(trees.size());
-  size_t t = 0;
+
-  for (auto const& tree : trees) {
+  for (size_t t = 0; t < trees.size(); ++t) {
+    auto const& tree = trees[t];
     Json tree_json{Object()};
     tree->SaveModel(&tree_json);
-    // The field is not used in XGBoost, but might be useful for external project.
+    tree_json["id"] = Integer(static_cast<Integer::Int>(t));
-    tree_json["id"] = Integer(t);
+    trees_json[t] = std::move(tree_json);
-    trees_json.emplace_back(tree_json);
-    t++;
   }
 
   std::vector<Json> tree_info_json(tree_info.size());
@@ -70,9 +71,10 @@ void GBTreeModel::LoadModel(Json const& in) {
   auto const& trees_json = get<Array const>(in["trees"]);
   trees.resize(trees_json.size());
 
-  for (size_t t = 0; t < trees.size(); ++t) {
+  for (size_t t = 0; t < trees_json.size(); ++t) {  // NOLINT
-    trees[t].reset( new RegTree() );
+    auto tree_id = get<Integer>(trees_json[t]["id"]);
-    trees[t]->LoadModel(trees_json[t]);
+    trees.at(tree_id).reset(new RegTree());
+    trees.at(tree_id)->LoadModel(trees_json[t]);
   }
 
   tree_info.resize(param.num_trees);

tests/ci_build/Dockerfile.gpu

@@ -17,8 +17,8 @@ ENV PATH=/opt/python/bin:$PATH
 
 # Create new Conda environment with cuDF, Dask, and cuPy
 RUN \
-    conda create -n gpu_test -c rapidsai -c nvidia -c conda-forge -c defaults \
+    conda create -n gpu_test -c rapidsai-nightly -c rapidsai -c nvidia -c conda-forge -c defaults \
-        python=3.7 cudf=0.14 cudatoolkit=$CUDA_VERSION dask dask-cuda dask-cudf cupy \
+        python=3.7 cudf=0.15* cudatoolkit=$CUDA_VERSION dask dask-cuda dask-cudf cupy \
         numpy pytest scipy scikit-learn pandas matplotlib wheel python-kubernetes urllib3 graphviz hypothesis
 
 ENV GOSU_VERSION 1.10

tests/ci_build/deploy_jvm_packages.sh

@@ -3,22 +3,32 @@
 set -e
 set -x
 
-if [ $# -ne 1 ]; then
+if [ $# -ne 2 ]; then
-  echo "Usage: $0 [spark version]"
+  echo "Usage: $0 [spark version] [build_gpu? 0 or 1]"
   exit 1
 fi
 
 spark_version=$1
+build_gpu=$2
 
 # Initialize local Maven repository
 ./tests/ci_build/initialize_maven.sh
 
-rm -rf build/
 cd jvm-packages
+rm -rf $(find . -name target)
+rm -rf ../build/
 
 # Re-build package without Mock Rabit
 # Deploy to S3 bucket xgboost-maven-repo
-mvn --no-transfer-progress package deploy -P release-to-s3 -Dspark.version=${spark_version} -DskipTests
+if [[ "$build_gpu" == "0" ]]
+then
+  # Build CPU artifact
+  mvn --no-transfer-progress package deploy -P release-to-s3 -Dspark.version=${spark_version} -DskipTests
+else
+  # Build GPU artifact
+  sed -i -e 's/<artifactId>xgboost\(.*\)_\(.*\)<\/artifactId>/<artifactId>xgboost\1-gpu_\2<\/artifactId>/' $(find . -name pom.xml)
+  mvn --no-transfer-progress package deploy -Duse.cuda=ON -P release-to-s3 -Dspark.version=${spark_version} -DskipTests
+fi
 
 set +x
 set +e

tests/cpp/test_learner.cc

@@ -148,7 +148,16 @@ TEST(Learner, JsonModelIO) {
     Json out { Object() };
     learner->SaveModel(&out);
 
-    learner->LoadModel(out);
+    dmlc::TemporaryDirectory tmpdir;
+
+    std::ofstream fout (tmpdir.path + "/model.json");
+    fout << out;
+    fout.close();
+
+    auto loaded_str = common::LoadSequentialFile(tmpdir.path + "/model.json");
+    Json loaded = Json::Load(StringView{loaded_str.c_str(), loaded_str.size()});
+
+    learner->LoadModel(loaded);
     learner->Configure();
 
     Json new_in { Object() };

tests/python/test_cli.py

@@ -121,6 +121,8 @@ eval[test] = {data_path}
         v = xgboost.__version__
         if v.find('SNAPSHOT') != -1:
             assert msg.split(':')[1].strip() == v.split('-')[0]
+        elif v.find('rc') != -1:
+            assert msg.split(':')[1].strip() == v.split('rc')[0]
         else:
             assert msg.split(':')[1].strip() == v
 

tests/python/test_with_dask.py

@@ -5,6 +5,7 @@ import sys
 import numpy as np
 import json
 import asyncio
+from sklearn.datasets import make_classification
 
 if sys.platform.startswith("win"):
     pytest.skip("Skipping dask tests on Windows", allow_module_level=True)
@@ -36,7 +37,7 @@ def generate_array():
 
 
 def test_from_dask_dataframe():
-    with LocalCluster(n_workers=5) as cluster:
+    with LocalCluster(n_workers=kWorkers) as cluster:
         with Client(cluster) as client:
             X, y = generate_array()
 
@@ -74,7 +75,7 @@ def test_from_dask_dataframe():
 
 
 def test_from_dask_array():
-    with LocalCluster(n_workers=5, threads_per_worker=5) as cluster:
+    with LocalCluster(n_workers=kWorkers, threads_per_worker=5) as cluster:
         with Client(cluster) as client:
             X, y = generate_array()
             dtrain = DaskDMatrix(client, X, y)
@@ -104,8 +105,28 @@ def test_from_dask_array():
             assert np.all(single_node_predt == from_arr.compute())
 
 
+def test_dask_predict_shape_infer():
+    with LocalCluster(n_workers=kWorkers) as cluster:
+        with Client(cluster) as client:
+            X, y = make_classification(n_samples=1000, n_informative=5,
+                                       n_classes=3)
+            X_ = dd.from_array(X, chunksize=100)
+            y_ = dd.from_array(y, chunksize=100)
+            dtrain = xgb.dask.DaskDMatrix(client, data=X_, label=y_)
+
+            model = xgb.dask.train(
+                client,
+                {"objective": "multi:softprob", "num_class": 3},
+                dtrain=dtrain
+            )
+
+            preds = xgb.dask.predict(client, model, dtrain)
+            assert preds.shape[0] == preds.compute().shape[0]
+            assert preds.shape[1] == preds.compute().shape[1]
+
+
 def test_dask_missing_value_reg():
-    with LocalCluster(n_workers=5) as cluster:
+    with LocalCluster(n_workers=kWorkers) as cluster:
         with Client(cluster) as client:
             X_0 = np.ones((20 // 2, kCols))
             X_1 = np.zeros((20 // 2, kCols))
@@ -144,19 +165,19 @@ def test_dask_missing_value_cls():
                                              missing=0.0)
             cls.client = client
             cls.fit(X, y, eval_set=[(X, y)])
-            dd_predt = cls.predict(X).compute()
+            dd_pred_proba = cls.predict_proba(X).compute()
 
             np_X = X.compute()
-            np_predt = cls.get_booster().predict(
+            np_pred_proba = cls.get_booster().predict(
                 xgb.DMatrix(np_X, missing=0.0))
-            np.testing.assert_allclose(np_predt, dd_predt)
+            np.testing.assert_allclose(np_pred_proba, dd_pred_proba)
 
             cls = xgb.dask.DaskXGBClassifier()
             assert hasattr(cls, 'missing')
 
 
 def test_dask_regressor():
-    with LocalCluster(n_workers=5) as cluster:
+    with LocalCluster(n_workers=kWorkers) as cluster:
         with Client(cluster) as client:
             X, y = generate_array()
             regressor = xgb.dask.DaskXGBRegressor(verbosity=1, n_estimators=2)
@@ -178,7 +199,7 @@ def test_dask_regressor():
 
 
 def test_dask_classifier():
-    with LocalCluster(n_workers=5) as cluster:
+    with LocalCluster(n_workers=kWorkers) as cluster:
         with Client(cluster) as client:
             X, y = generate_array()
             y = (y * 10).astype(np.int32)
@@ -201,7 +222,18 @@ def test_dask_classifier():
             assert len(list(history['validation_0'])) == 1
             assert len(history['validation_0']['merror']) == 2
 
+            # Test .predict_proba()
+            probas = classifier.predict_proba(X)
             assert classifier.n_classes_ == 10
+            assert probas.ndim == 2
+            assert probas.shape[0] == kRows
+            assert probas.shape[1] == 10
+
+            cls_booster = classifier.get_booster()
+            single_node_proba = cls_booster.inplace_predict(X.compute())
+
+            np.testing.assert_allclose(single_node_proba,
+                                       probas.compute())
 
             # Test with dataframe.
             X_d = dd.from_dask_array(X)
@@ -218,7 +250,7 @@ def test_dask_classifier():
 @pytest.mark.skipif(**tm.no_sklearn())
 def test_sklearn_grid_search():
     from sklearn.model_selection import GridSearchCV
-    with LocalCluster(n_workers=4) as cluster:
+    with LocalCluster(n_workers=kWorkers) as cluster:
         with Client(cluster) as client:
             X, y = generate_array()
             reg = xgb.dask.DaskXGBRegressor(learning_rate=0.1,
@@ -292,7 +324,9 @@ def run_empty_dmatrix_cls(client, parameters):
                          evals=[(dtrain, 'validation')],
                          num_boost_round=2)
     predictions = xgb.dask.predict(client=client, model=out,
-                                   data=dtrain).compute()
+                                   data=dtrain)
+    assert predictions.shape[1] == n_classes
+    predictions = predictions.compute()
     _check_outputs(out, predictions)
 
     # train has more rows than evals
@@ -315,7 +349,7 @@ def run_empty_dmatrix_cls(client, parameters):
 # environment and Exact doesn't support it.
 
 def test_empty_dmatrix_hist():
-    with LocalCluster(n_workers=5) as cluster:
+    with LocalCluster(n_workers=kWorkers) as cluster:
         with Client(cluster) as client:
             parameters = {'tree_method': 'hist'}
             run_empty_dmatrix_reg(client, parameters)
@@ -323,7 +357,7 @@ def test_empty_dmatrix_hist():
 
 
 def test_empty_dmatrix_approx():
-    with LocalCluster(n_workers=5) as cluster:
+    with LocalCluster(n_workers=kWorkers) as cluster:
         with Client(cluster) as client:
             parameters = {'tree_method': 'approx'}
             run_empty_dmatrix_reg(client, parameters)
@@ -397,7 +431,13 @@ async def run_dask_classifier_asyncio(scheduler_address):
         assert len(list(history['validation_0'])) == 1
         assert len(history['validation_0']['merror']) == 2
 
+        # Test .predict_proba()
+        probas = await classifier.predict_proba(X)
         assert classifier.n_classes_ == 10
+        assert probas.ndim == 2
+        assert probas.shape[0] == kRows
+        assert probas.shape[1] == 10
+
 
         # Test with dataframe.
         X_d = dd.from_dask_array(X)