merge v2.0.3 from upstream

tests/buildkite/build-jvm-packages.sh

@@ -8,13 +8,18 @@ echo "--- Build XGBoost JVM packages scala 2.12"
 tests/ci_build/ci_build.sh jvm docker tests/ci_build/build_jvm_packages.sh \
   ${SPARK_VERSION}
 
+echo "--- Stash XGBoost4J JARs (Scala 2.12)"
+buildkite-agent artifact upload "jvm-packages/xgboost4j/target/*.jar"
+buildkite-agent artifact upload "jvm-packages/xgboost4j-spark/target/*.jar"
+buildkite-agent artifact upload "jvm-packages/xgboost4j-flink/target/*.jar"
+buildkite-agent artifact upload "jvm-packages/xgboost4j-example/target/*.jar"
 
 echo "--- Build XGBoost JVM packages scala 2.13"
 
 tests/ci_build/ci_build.sh jvm docker tests/ci_build/build_jvm_packages.sh \
   ${SPARK_VERSION} "" "" "true"
 
-echo "--- Stash XGBoost4J JARs"
+echo "--- Stash XGBoost4J JARs (Scala 2.13)"
 buildkite-agent artifact upload "jvm-packages/xgboost4j/target/*.jar"
 buildkite-agent artifact upload "jvm-packages/xgboost4j-spark/target/*.jar"
 buildkite-agent artifact upload "jvm-packages/xgboost4j-flink/target/*.jar"

tests/buildkite/pipeline-mac-m1.yml

@@ -0,0 +1,8 @@
+steps:
+  - block: ":rocket: Run this test job"
+    if: build.pull_request.id != null || build.branch =~ /^dependabot\//
+  - label: ":macos: Build and Test XGBoost for MacOS M1 with Clang 11"
+    command: "tests/buildkite/test-macos-m1-clang11.sh"
+    key: mac-m1-appleclang11
+    agents:
+      queue: mac-mini-m1

tests/buildkite/test-macos-m1-clang11.sh

@@ -0,0 +1,50 @@
+#!/bin/bash
+
+set -euo pipefail
+
+source tests/buildkite/conftest.sh
+
+# Display system info
+echo "--- Display system information"
+set -x
+system_profiler SPSoftwareDataType
+sysctl -n machdep.cpu.brand_string
+uname -m
+set +x
+
+# Build XGBoost4J binary
+echo "--- Build libxgboost4j.dylib"
+set -x
+mkdir build
+pushd build
+export JAVA_HOME=$(/usr/libexec/java_home)
+cmake .. -GNinja -DJVM_BINDINGS=ON -DUSE_OPENMP=OFF -DCMAKE_OSX_DEPLOYMENT_TARGET=10.15
+ninja -v
+popd
+rm -rf build
+set +x
+
+echo "--- Upload Python wheel"
+set -x
+pushd lib
+mv -v libxgboost4j.dylib libxgboost4j_m1_${BUILDKITE_COMMIT}.dylib
+buildkite-agent artifact upload libxgboost4j_m1_${BUILDKITE_COMMIT}.dylib
+if [[ ($is_pull_request == 0) && ($is_release_branch == 1) ]]
+then
+  aws s3 cp libxgboost4j_m1_${BUILDKITE_COMMIT}.dylib \
+    s3://xgboost-nightly-builds/${BRANCH_NAME}/libxgboost4j/ \
+    --acl public-read --no-progress
+fi
+popd
+set +x
+
+# Ensure that XGBoost can be built with Clang 11
+echo "--- Build and Test XGBoost with MacOS M1, Clang 11"
+set -x
+LLVM11_PATH=$(brew --prefix llvm\@11)
+mkdir build
+pushd build
+cmake .. -GNinja -DCMAKE_C_COMPILER=${LLVM11_PATH}/bin/clang \
+  -DCMAKE_CXX_COMPILER=${LLVM11_PATH}/bin/clang++ -DGOOGLE_TEST=ON \
+  -DUSE_DMLC_GTEST=ON
+ninja -v

tests/ci_build/build_jvm_packages.sh

@@ -27,6 +27,9 @@ fi
 mvn_profile_string=""
 if [ "x$use_scala213" != "x" ]; then
   export mvn_profile_string="-Pdefault,scala-2.13"
+  cd ..
+  python dev/change_scala_version.py --scala-version 2.13 --purge-artifacts
+  cd jvm-packages
 fi
 
 mvn --no-transfer-progress package $mvn_profile_string -Dspark.version=${spark_version} $gpu_options

tests/ci_build/conda_env/macos_cpu_test.yml

@@ -32,11 +32,10 @@ dependencies:
 - jsonschema
 - boto3
 - awscli
-- py-ubjson
 - cffi
 - pyarrow
 - pyspark>=3.4.0
 - cloudpickle
 - pip:
   - sphinx_rtd_theme
-  - datatable
+  - py-ubjson

tests/ci_build/deploy_jvm_packages.sh

@@ -27,6 +27,9 @@ rm -rf ../build/
 # Deploy to S3 bucket xgboost-maven-repo
 mvn --no-transfer-progress package deploy -P default,gpu,release-to-s3 -Dspark.version=${spark_version} -DskipTests
 # Deploy scala 2.13 to S3 bucket xgboost-maven-repo
+cd ..
+python dev/change_scala_version.py --scala-version 2.13 --purge-artifacts
+cd jvm-packages/
 mvn --no-transfer-progress package deploy -P release-to-s3,default,scala-2.13 -Dspark.version=${spark_version} -DskipTests
 
 

tests/ci_build/test_jvm_cross.sh

@@ -21,9 +21,18 @@ if [ ! -z "$RUN_INTEGRATION_TEST" ]; then
 fi
 
 # including maven profiles for different scala versions: 2.12 is the default at the moment.
-for _maven_profile_string in "" "-Pdefault,scala-2.13"; do
+for scala_binary_version in "2.12" "2.13"; do
+  cd ..
+  python dev/change_scala_version.py --scala-version ${scala_binary_version}
+  cd jvm-packages
   scala_version=$(mvn help:evaluate $_maven_profile_string -Dexpression=scala.version -q -DforceStdout)
-  scala_binary_version=$(mvn help:evaluate $_maven_profile_string -Dexpression=scala.binary.version -q -DforceStdout)
+  if [[ "$scala_binary_version" == "2.12" ]]; then
+    _maven_profile_string=""
+  elif [[ "$scala_binary_version" == "2.13" ]]; then
+    _maven_profile_string="-Pdefault,scala-2.13"
+  else
+    echo "Unexpected scala version: $scala_version ($scala_binary_version)."
+  fi
 
   # Install XGBoost4J JAR into local Maven repository
   mvn --no-transfer-progress install:install-file -Dfile=./xgboost4j/target/xgboost4j_${scala_binary_version}-${xgboost4j_version}.jar -DgroupId=ml.dmlc -DartifactId=xgboost4j_${scala_binary_version} -Dversion=${xgboost4j_version} -Dpackaging=jar

tests/python-gpu/test_gpu_with_sklearn.py

@@ -9,7 +9,7 @@ import pytest
 
 import xgboost as xgb
 from xgboost import testing as tm
-from xgboost.testing.ranking import run_ranking_qid_df
+from xgboost.testing.ranking import run_ranking_categorical, run_ranking_qid_df
 
 sys.path.append("tests/python")
 import test_with_sklearn as twskl  # noqa
@@ -165,6 +165,11 @@ def test_ranking_qid_df():
     run_ranking_qid_df(cudf, "gpu_hist")
 
 
+@pytest.mark.skipif(**tm.no_pandas())
+def test_ranking_categorical() -> None:
+    run_ranking_categorical(device="cuda")
+
+
 @pytest.mark.skipif(**tm.no_cupy())
 @pytest.mark.mgpu
 def test_device_ordinal() -> None:

tests/python/test_with_sklearn.py

@@ -12,7 +12,7 @@ from sklearn.utils.estimator_checks import parametrize_with_checks
 
 import xgboost as xgb
 from xgboost import testing as tm
-from xgboost.testing.ranking import run_ranking_qid_df
+from xgboost.testing.ranking import run_ranking_categorical, run_ranking_qid_df
 from xgboost.testing.shared import get_feature_weights, validate_data_initialization
 from xgboost.testing.updater import get_basescore
 
@@ -173,6 +173,11 @@ def test_ranking():
     np.testing.assert_almost_equal(pred, pred_orig)
 
 
+@pytest.mark.skipif(**tm.no_pandas())
+def test_ranking_categorical() -> None:
+    run_ranking_categorical(device="cpu")
+
+
 def test_ranking_metric() -> None:
     from sklearn.metrics import roc_auc_score
 
@@ -935,6 +940,7 @@ def save_load_model(model_path):
     predt_0 = clf.predict(X)
     clf.save_model(model_path)
     clf.load_model(model_path)
+    assert clf.booster == "gblinear"
     predt_1 = clf.predict(X)
     np.testing.assert_allclose(predt_0, predt_1)
     assert clf.best_iteration == best_iteration
@@ -950,25 +956,26 @@ def save_load_model(model_path):
 
 def test_save_load_model():
     with tempfile.TemporaryDirectory() as tempdir:
-        model_path = os.path.join(tempdir, 'digits.model')
+        model_path = os.path.join(tempdir, "digits.model")
         save_load_model(model_path)
 
     with tempfile.TemporaryDirectory() as tempdir:
-        model_path = os.path.join(tempdir, 'digits.model.json')
+        model_path = os.path.join(tempdir, "digits.model.json")
         save_load_model(model_path)
 
     from sklearn.datasets import load_digits
     from sklearn.model_selection import train_test_split
 
     with tempfile.TemporaryDirectory() as tempdir:
-        model_path = os.path.join(tempdir, 'digits.model.ubj')
+        model_path = os.path.join(tempdir, "digits.model.ubj")
         digits = load_digits(n_class=2)
-        y = digits['target']
-        X = digits['data']
-        booster = xgb.train({'tree_method': 'hist',
-                             'objective': 'binary:logistic'},
-                            dtrain=xgb.DMatrix(X, y),
-                            num_boost_round=4)
+        y = digits["target"]
+        X = digits["data"]
+        booster = xgb.train(
+            {"tree_method": "hist", "objective": "binary:logistic"},
+            dtrain=xgb.DMatrix(X, y),
+            num_boost_round=4,
+        )
         predt_0 = booster.predict(xgb.DMatrix(X))
         booster.save_model(model_path)
         cls = xgb.XGBClassifier()
@@ -1002,6 +1009,8 @@ def test_save_load_model():
         clf = xgb.XGBClassifier()
         clf.load_model(model_path)
         assert clf.classes_.size == 10
+        assert clf.objective == "multi:softprob"
+
         np.testing.assert_equal(clf.classes_, np.arange(10))
         assert clf.n_classes_ == 10
 

tests/test_distributed/test_with_dask/test_with_dask.py

@@ -1932,6 +1932,7 @@ class TestWithDask:
         cls.client = client
         cls.fit(X, y)
         predt_0 = cls.predict(X)
+        proba_0 = cls.predict_proba(X)
 
         with tempfile.TemporaryDirectory() as tmpdir:
             path = os.path.join(tmpdir, "model.pkl")
@@ -1941,7 +1942,9 @@ class TestWithDask:
             with open(path, "rb") as fd:
                 cls = pickle.load(fd)
             predt_1 = cls.predict(X)
+            proba_1 = cls.predict_proba(X)
             np.testing.assert_allclose(predt_0.compute(), predt_1.compute())
+            np.testing.assert_allclose(proba_0.compute(), proba_1.compute())
 
             path = os.path.join(tmpdir, "cls.json")
             cls.save_model(path)
@@ -1950,16 +1953,20 @@ class TestWithDask:
             cls.load_model(path)
             assert cls.n_classes_ == 10
             predt_2 = cls.predict(X)
+            proba_2 = cls.predict_proba(X)
 
             np.testing.assert_allclose(predt_0.compute(), predt_2.compute())
+            np.testing.assert_allclose(proba_0.compute(), proba_2.compute())
 
             # Use single node to load
             cls = xgb.XGBClassifier()
             cls.load_model(path)
             assert cls.n_classes_ == 10
             predt_3 = cls.predict(X_)
+            proba_3 = cls.predict_proba(X_)
 
             np.testing.assert_allclose(predt_0.compute(), predt_3)
+            np.testing.assert_allclose(proba_0.compute(), proba_3)
 
 
 def test_dask_unsupported_features(client: "Client") -> None: