Merge branch 'branch-25.02' into main-2502-release

Author: nvliyuan

.github/workflows/add-to-project.yml

@@ -1,4 +1,4 @@
-# Copyright (c) 2024, NVIDIA CORPORATION.
+# Copyright (c) 2024-2025, NVIDIA CORPORATION.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -23,13 +23,11 @@ on:
       - opened
 
 jobs:
-  add-to-project:
-    if: github.repository == 'NVIDIA/spark-rapids-examples'
-    name: Add new issues and pull requests to project
+  Add-to-project:
+    if: github.repository_owner == 'NVIDIA' # avoid adding issues from forks
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/[email protected]
+      - name: add-to-project
+        uses: NVIDIA/spark-rapids-common/add-to-project@main
         with:
-          project-url: https://github.com/orgs/NVIDIA/projects/4
-          github-token: ${{ secrets.PROJECT_TOKEN }}
-
+          token: ${{ secrets.PROJECT_TOKEN }}

.github/workflows/license-header-check.yml

@@ -0,0 +1,54 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# A workflow to check copyright/license header
+name: license header check
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+
+jobs:
+  license-header-check:
+    runs-on: ubuntu-latest
+    if: "!contains(github.event.pull_request.title, '[bot]')"
+    steps:
+      - name: Get checkout depth
+        run: |
+          echo "PR_FETCH_DEPTH=$(( ${{ github.event.pull_request.commits }} + 10 ))" >> $GITHUB_ENV
+
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: ${{ env.PR_FETCH_DEPTH }}
+
+      - name: license-header-check
+        uses: NVIDIA/spark-rapids-common/license-header-check@main
+        with:
+          included_file_patterns: |
+            *.sh,
+            *.java,
+            *.py,
+            *.pbtxt,
+            *Dockerfile*,
+            *Jenkinsfile*,
+            *.yml,
+            *.yaml,
+            *.cpp,
+            *.hpp,
+            *.txt,
+            *.cu,
+            *.scala,
+            *.ini,
+            *.xml

dockerfile/gpu_executor_template.yaml

@@ -1,3 +1,17 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
 apiVersion: v1
 kind: Pod
 spec:

docs/get-started/xgboost-examples/csp/databricks/databricks.md

@@ -21,7 +21,7 @@ Navigate to your home directory in the UI and select **Create** > **File** from
 create an `init.sh` scripts with contents:   
    ```bash
    #!/bin/bash
-   sudo wget -O /databricks/jars/rapids-4-spark_2.12-24.12.0.jar https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/24.12.0/rapids-4-spark_2.12-24.12.0.jar
+   sudo wget -O /databricks/jars/rapids-4-spark_2.12-25.02.1.jar https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/25.02.1/rapids-4-spark_2.12-25.02.1.jar
    ```
 1. Select the Databricks Runtime Version from one of the supported runtimes specified in the
    Prerequisites section.
@@ -68,7 +68,7 @@ create an `init.sh` scripts with contents:
     ```bash
     spark.rapids.sql.python.gpu.enabled true
     spark.python.daemon.module rapids.daemon_databricks
-    spark.executorEnv.PYTHONPATH /databricks/jars/rapids-4-spark_2.12-24.12.0.jar:/databricks/spark/python
+    spark.executorEnv.PYTHONPATH /databricks/jars/rapids-4-spark_2.12-25.02.1.jar:/databricks/spark/python
     ```
    Note that since python memory pool require installing the cudf library, so you need to install cudf library in 
    each worker nodes `pip install cudf-cu11 --extra-index-url=https://pypi.nvidia.com` or disable python memory pool

docs/get-started/xgboost-examples/csp/databricks/init.sh

@@ -1,7 +1,21 @@
+# Copyright (c) 2024, NVIDIA CORPORATION.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
 sudo rm -f /databricks/jars/spark--maven-trees--ml--10.x--xgboost-gpu--ml.dmlc--xgboost4j-gpu_2.12--ml.dmlc__xgboost4j-gpu_2.12__1.5.2.jar
 sudo rm -f /databricks/jars/spark--maven-trees--ml--10.x--xgboost-gpu--ml.dmlc--xgboost4j-spark-gpu_2.12--ml.dmlc__xgboost4j-spark-gpu_2.12__1.5.2.jar
 
-sudo wget -O /databricks/jars/rapids-4-spark_2.12-24.12.0.jar https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/24.12.0/rapids-4-spark_2.12-24.12.0.jar
+sudo wget -O /databricks/jars/rapids-4-spark_2.12-25.02.1.jar https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/25.02.1/rapids-4-spark_2.12-25.02.1.jar
 sudo wget -O /databricks/jars/xgboost4j-gpu_2.12-1.7.1.jar https://repo1.maven.org/maven2/ml/dmlc/xgboost4j-gpu_2.12/1.7.1/xgboost4j-gpu_2.12-1.7.1.jar
 sudo wget -O /databricks/jars/xgboost4j-spark-gpu_2.12-1.7.1.jar https://repo1.maven.org/maven2/ml/dmlc/xgboost4j-spark-gpu_2.12/1.7.1/xgboost4j-spark-gpu_2.12-1.7.1.jar
 ls -ltr

docs/get-started/xgboost-examples/on-prem-cluster/kubernetes-scala.md

@@ -40,7 +40,7 @@ export SPARK_DOCKER_IMAGE=<gpu spark docker image repo and name>
 export SPARK_DOCKER_TAG=<spark docker image tag>
 
 pushd ${SPARK_HOME}
-wget https://github.com/NVIDIA/spark-rapids-examples/raw/branch-24.12/dockerfile/Dockerfile
+wget https://github.com/NVIDIA/spark-rapids-examples/raw/branch-25.02/dockerfile/Dockerfile
 
 # Optionally install additional jars into ${SPARK_HOME}/jars/
 

docs/get-started/xgboost-examples/prepare-package-data/preparation-python.md

@@ -5,7 +5,7 @@ For simplicity export the location to these jars. All examples assume the packag
 ### Download the jars
 
 Download the RAPIDS Accelerator for Apache Spark plugin jar
-  * [RAPIDS Spark Package](https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/24.12.0/rapids-4-spark_2.12-24.12.0.jar)
+  * [RAPIDS Spark Package](https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/25.02.1/rapids-4-spark_2.12-25.02.1.jar)
 
 ### Build XGBoost Python Examples
 

docs/get-started/xgboost-examples/prepare-package-data/preparation-scala.md

@@ -5,7 +5,7 @@ For simplicity export the location to these jars. All examples assume the packag
 ### Download the jars
 
 1. Download the RAPIDS Accelerator for Apache Spark plugin jar
-   * [RAPIDS Spark Package](https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/24.12.0/rapids-4-spark_2.12-24.12.0.jar)
+   * [RAPIDS Spark Package](https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/25.02.1/rapids-4-spark_2.12-25.02.1.jar)
 
 ### Build XGBoost Scala Examples
 

examples/ML+DL-Examples/Optuna-Spark/README.md

@@ -147,8 +147,8 @@ We use [RAPIDS](https://docs.rapids.ai/install/#get-rapids) for GPU-accelerated
 ``` shell
 sudo apt install libmysqlclient-dev
 
-conda create -n rapids-24.12 -c rapidsai -c conda-forge -c nvidia  \
-    cudf=24.12 cuml=24.12 python=3.10 'cuda-version>=12.0,<=12.5'
+conda create -n rapids-25.02 -c rapidsai -c conda-forge -c nvidia  \
+    cudf=25.02 cuml=25.02 python=3.10 'cuda-version>=12.0,<=12.5'
 conda activate optuna-spark
 pip install mysqlclient
 pip install optuna joblib joblibspark ipywidgets

examples/ML+DL-Examples/Optuna-Spark/optuna-examples/databricks/init_optuna.sh

@@ -41,7 +41,7 @@ fi
 
 
 # rapids import
-SPARK_RAPIDS_VERSION=24.12.0
+SPARK_RAPIDS_VERSION=25.02.1
 curl -L https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/${SPARK_RAPIDS_VERSION}/rapids-4-spark_2.12-${SPARK_RAPIDS_VERSION}.jar -o \
     /databricks/jars/rapids-4-spark_2.12-${SPARK_RAPIDS_VERSION}.jar
 
@@ -54,7 +54,7 @@ ln -s /usr/local/cuda-11.8 /usr/local/cuda
 
 sudo /databricks/python3/bin/pip3 install \
     --extra-index-url=https://pypi.nvidia.com \
-    "cudf-cu11==24.12.*" "cuml-cu11==24.12.*"
+    "cudf-cu11==25.02.*" "cuml-cu11==25.02.*"
 
 # setup python environment
 sudo apt clean && sudo apt update --fix-missing -y

examples/ML+DL-Examples/Optuna-Spark/optuna-examples/databricks/start_cluster.sh

@@ -12,7 +12,7 @@ json_config=$(cat <<EOF
     "spark_version": "13.3.x-gpu-ml-scala2.12",
     "spark_conf": {
         "spark.task.resource.gpu.amount": "1",
-        "spark.executorEnv.PYTHONPATH": "/databricks/jars/rapids-4-spark_2.12-24.12.0.jar:/databricks/spark/python:/databricks/python3",
+        "spark.executorEnv.PYTHONPATH": "/databricks/jars/rapids-4-spark_2.12-25.02.1.jar:/databricks/spark/python:/databricks/python3",
         "spark.executor.cores": "8",
         "spark.rapids.memory.gpu.minAllocFraction": "0.0001",
         "spark.plugins": "com.nvidia.spark.SQLPlugin",

examples/ML+DL-Examples/Optuna-Spark/optuna-examples/optuna-dataframe.ipynb

@@ -444,14 +444,14 @@
       "24/12/11 23:47:52 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable\n",
       "Setting default log level to \"WARN\".\n",
       "To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).\n",
-      "24/12/11 23:47:52 WARN RapidsPluginUtils: RAPIDS Accelerator 24.12.0 using cudf 24.12.0, private revision bd4e99e18e20234ee0c54f95f4b0bfce18a6255e\n",
+      "24/12/11 23:47:52 WARN RapidsPluginUtils: RAPIDS Accelerator 25.02.1 using cudf 25.02.1, private revision bd4e99e18e20234ee0c54f95f4b0bfce18a6255e\n",
       "24/12/11 23:47:52 WARN RapidsPluginUtils: RAPIDS Accelerator is enabled, to disable GPU support set `spark.rapids.sql.enabled` to false.\n"
      ]
     }
    ],
    "source": [
     "def get_rapids_jar():\n",
-    "    SPARK_RAPIDS_VERSION = \"24.12.0\"\n",
+    "    SPARK_RAPIDS_VERSION = \"25.02.1\"\n",
     "    rapids_jar = f\"rapids-4-spark_2.12-{SPARK_RAPIDS_VERSION}.jar\"\n",
     "    if not os.path.exists(rapids_jar):\n",
     "        print(\"Downloading Spark Rapids jar\")\n",