[jvm-packages] Support spark connect #11381
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,50 @@ | ||
| # Copyright (c) 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. | ||
| # 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. | ||
|
|
||
| [project] | ||
| name = "xgboost4j" | ||
| version = "3.1.0" | ||
| authors = [ | ||
| { name = "Bobby Wang", email = "[email protected]" }, | ||
| ] | ||
| description = "XGBoost4j-Spark pyspark" | ||
| readme = "README.md" | ||
| requires-python = ">=3.10" | ||
| classifiers = [ | ||
| "Programming Language :: Python :: 3", | ||
| "Programming Language :: Python :: 3.10", | ||
| "Programming Language :: Python :: 3.11", | ||
| "Programming Language :: Python :: 3.12", | ||
| "License :: OSI Approved :: Apache Software License", | ||
| "Operating System :: OS Independent", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 11", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 11.4", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 11.5", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 11.6", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 11.7", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 11.8", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 12", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 12 :: 12.0", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 12 :: 12.1", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 12 :: 12.2", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 12 :: 12.3", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 12 :: 12.4", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 12 :: 12.5", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 12 :: 12.6", | ||
| "Environment :: GPU :: NVIDIA CUDA :: 12 :: 12.8", | ||
| ] | ||
|
|
||
| [build-system] | ||
| requires = ["setuptools>=61.0"] | ||
| build-backend = "setuptools.build_meta" | ||
Empty file.
Empty file.
Empty file.
Empty file.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| import sys | ||
|
|
||
| import xgboost4j | ||
|
|
||
| sys.modules["ml.dmlc.xgboost4j.scala.spark"] = xgboost4j |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| from .estimator import XGBoostClassificationModel, XGBoostClassifier | ||
|
|
||
| __version__ = "3.0.0" | ||
|
|
||
| __all__ = ["XGBoostClassifier", "XGBoostClassificationModel"] |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,103 @@ | ||
| from typing import Union, List, Any, Optional, Dict | ||
|
|
||
| from pyspark import keyword_only | ||
| from pyspark.ml.classification import _JavaProbabilisticClassifier, _JavaProbabilisticClassificationModel | ||
|
|
||
| from .params import XGBoostParams | ||
|
|
||
|
|
||
| class XGBoostClassifier(_JavaProbabilisticClassifier["XGBoostClassificationModel"], XGBoostParams): | ||
|
There was a problem hiding this comment. Will this be a new class that needs to be used for both normal and spark connect invocation ? Can we not modify There was a problem hiding this comment. Thx @jjayadeep06 for your reply. Well, when involving connect, things is becoming complicated. You know, we could make the existing xgboost-pyspark support spark connect by changing the RDD operations to Dataframe without using any try_remote_xxxx. Yes, we have a plan to do that. While this PR is to make xgboost jvm package to support connect by introducing a light-weight python wrapper. If we add the python wrapper over xgboost jvm package to the existing xgboost-python-pyspark, then it's going to raise an issue which backends (xgboost jvm package or python package) will be chose when running xgboost over connect? |
||
| _input_kwargs: Dict[str, Any] | ||
|
|
||
| @keyword_only | ||
| def __init__( | ||
| self, | ||
| *, | ||
| featuresCol: Union[str, List[str]] = "features", | ||
| labelCol: str = "label", | ||
| predictionCol: str = "prediction", | ||
| probabilityCol: str = "probability", | ||
| rawPredictionCol: str = "rawPrediction", | ||
| # SparkParams | ||
| numWorkers: Optional[int] = None, | ||
| numRound: Optional[int] = None, | ||
| forceRepartition: Optional[bool] = None, | ||
| numEarlyStoppingRounds: Optional[int] = None, | ||
| inferBatchSize: Optional[int] = None, | ||
| missing: Optional[float] = None, | ||
| useExternalMemory: Optional[bool] = None, | ||
| maxNumDevicePages: Optional[int] = None, | ||
| maxQuantileBatches: Optional[int] = None, | ||
| minCachePageBytes: Optional[int] = None, | ||
| feature_names: Optional[List[str]] = None, | ||
| feature_types: Optional[List[str]] = None, | ||
| # RabitParams | ||
| rabitTrackerTimeout: Optional[int] = None, | ||
| rabitTrackerHostIp: Optional[str] = None, | ||
| rabitTrackerPort: Optional[int] = None, | ||
| # GeneralParams | ||
| booster: Optional[str] = None, | ||
| device: Optional[str] = None, | ||
| verbosity: Optional[int] = None, | ||
| validate_parameters: Optional[bool] = None, | ||
| nthread: Optional[int] = None, | ||
| # TreeBoosterParams | ||
| eta: Optional[float] = None, | ||
| gamma: Optional[float] = None, | ||
| max_depth: Optional[int] = None, | ||
| min_child_weight: Optional[float] = None, | ||
| max_delta_step: Optional[float] = None, | ||
| subsample: Optional[float] = None, | ||
| sampling_method: Optional[str] = None, | ||
| colsample_bytree: Optional[float] = None, | ||
| colsample_bylevel: Optional[float] = None, | ||
| colsample_bynode: Optional[float] = None, | ||
| reg_lambda: Optional[float] = None, | ||
| alpha: Optional[float] = None, | ||
| tree_method: Optional[str] = None, | ||
| scale_pos_weight: Optional[float] = None, | ||
| updater: Optional[str] = None, | ||
| refresh_leaf: Optional[bool] = None, | ||
| process_type: Optional[str] = None, | ||
| grow_policy: Optional[str] = None, | ||
| max_leaves: Optional[int] = None, | ||
| max_bin: Optional[int] = None, | ||
| num_parallel_tree: Optional[int] = None, | ||
| monotone_constraints: Optional[List[int]] = None, | ||
| interaction_constraints: Optional[str] = None, | ||
| max_cached_hist_node: Optional[int] = None, | ||
| # LearningTaskParams | ||
| objective: Optional[str] = None, | ||
| num_class: Optional[int] = None, | ||
| base_score: Optional[float] = None, | ||
| eval_metric: Optional[str] = None, | ||
| seed: Optional[int] = None, | ||
| seed_per_iteration: Optional[bool] = None, | ||
| tweedie_variance_power: Optional[float] = None, | ||
| huber_slope: Optional[float] = None, | ||
| aft_loss_distribution: Optional[str] = None, | ||
| lambdarank_pair_method: Optional[str] = None, | ||
| lambdarank_num_pair_per_sample: Optional[int] = None, | ||
| lambdarank_unbiased: Optional[bool] = None, | ||
| lambdarank_bias_norm: Optional[float] = None, | ||
| ndcg_exp_gain: Optional[bool] = None, | ||
| # DartBoosterParams | ||
| sample_type: Optional[str] = None, | ||
| normalize_type: Optional[str] = None, | ||
| rate_drop: Optional[float] = None, | ||
| one_drop: Optional[bool] = None, | ||
| skip_drop: Optional[float] = None, | ||
| **kwargs: Any, | ||
| ): | ||
| super().__init__() | ||
| self._java_obj = self._new_java_obj( | ||
| "ml.dmlc.xgboost4j.scala.spark.XGBoostClassifier", self.uid | ||
| ) | ||
| self._set_params(**self._input_kwargs) | ||
|
|
||
| def _create_model(self, java_model: "JavaObject") -> "XGBoostClassificationModel": | ||
| return XGBoostClassificationModel(java_model) | ||
|
|
||
|
|
||
| class XGBoostClassificationModel(_JavaProbabilisticClassificationModel, XGBoostParams): | ||
| pass | ||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
These can be removed, we dropped suport for all previous versions in 3.0