o ڭj]@s8dZddlmZmZmZmZmZddlZddl m Z ddl m Z m Z ddlmZmZddlmZdd lmZmZmZd d lmZmZmZd d lmZd eedeeddfddZGdddeZGdddeZeeeGdddeeeZ GdddeZ!ee e!GdddeZ"GdddeZ#ee"e#dS)z8Xgboost pyspark integration submodule for estimator API.)AnyListOptionalTypeUnionN) keyword_only)ParamParams)HasProbabilityColHasRawPredictionCol)Config) XGBClassifier XGBRanker XGBRegressor)_ClassificationModel_SparkXGBEstimator_SparkXGBModel)get_class_name estimatormodelreturnc s&}dtdtffdd dtdtddffdd }|D]}d td |}tt||d }|||q" }|D]$}d td |}|dkr]|d7}tt||d }|||qG }|D]}d td|}tt||d }|||qtdS)zyThis function automatically infer to xgboost parameters and set them into corresponding pyspark estimators and modelsvrcsZt|tjr t|St|trfdd|DSt|tr+fdd|DS|S)Ncsi|] \}}||qSr).0knvparam_value_converterrT/var/www/html/CropPilot/venv/lib/python3.10/site-packages/xgboost/spark/estimator.py #szS_set_pyspark_xgb_cls_param_attrs..param_value_converter..csg|]}|qSrr)rrrrr %szS_set_pyspark_xgb_cls_param_attrs..param_value_converter..) isinstancenpgenericarrayitemdictitemslist)rrrr rs   z?_set_pyspark_xgb_cls_param_attrs..param_value_converter attr_nameparamNcs"|_t||t||dSN) typeConvertersetattr)r+r,rrrrr set_param_attrs(s z9_set_pyspark_xgb_cls_param_attrs..set_param_attrszRefer to XGBoost doc of z for this param )namedocz.fit() for this param callbackszThe callbacks can be arbitrary functions. It is saved using cloudpickle which is not a fully self-contained format. It may fail to load with different versions of dependencies.z.predict() for this param ) _get_xgb_params_defaultrstrrkeysr_xgb_clsr _dummy_get_fit_params_default_get_predict_params_default) rr params_dictr1r2r3 param_objfit_params_dictpredict_params_dictrr0r _set_pyspark_xgb_cls_param_attrssB       r@c"seZdZdZeddddddddddddddd d eeeefd ed ed eedeedeedeede deede de de de dee de ddf fddZ edeefddZededfdd Zd#fd!d" ZZS)$SparkXGBRegressoraSparkXGBRegressor is a PySpark ML estimator. It implements the XGBoost regression algorithm based on XGBoost python library, and it can be used in PySpark Pipeline and PySpark ML meta algorithms like - :py:class:`~pyspark.ml.tuning.CrossValidator`/ - :py:class:`~pyspark.ml.tuning.TrainValidationSplit`/ - :py:class:`~pyspark.ml.classification.OneVsRest` SparkXGBRegressor automatically supports most of the parameters in :py:class:`xgboost.XGBRegressor` constructor and most of the parameters used in :py:meth:`xgboost.XGBRegressor.fit` and :py:meth:`xgboost.XGBRegressor.predict` method. To enable GPU support, set `device` to `cuda` or `gpu`. SparkXGBRegressor doesn't support setting `base_margin` explicitly as well, but support another param called `base_margin_col`. see doc below for more details. SparkXGBRegressor doesn't support `validate_features` and `output_margin` param. SparkXGBRegressor doesn't support setting `nthread` xgboost param, instead, the `nthread` param for each xgboost worker will be set equal to `spark.task.cpus` config value. Parameters ---------- features_col: When the value is string, it requires the features column name to be vector type. When the value is a list of string, it requires all the feature columns to be numeric types. label_col: Label column name. Default to "label". prediction_col: Prediction column name. Default to "prediction" pred_contrib_col: Contribution prediction column name. validation_indicator_col: For params related to `xgboost.XGBRegressor` training with evaluation dataset's supervision, set :py:attr:`xgboost.spark.SparkXGBRegressor.validation_indicator_col` parameter instead of setting the `eval_set` parameter in `xgboost.XGBRegressor` fit method. weight_col: To specify the weight of the training and validation dataset, set :py:attr:`xgboost.spark.SparkXGBRegressor.weight_col` parameter instead of setting `sample_weight` and `sample_weight_eval_set` parameter in `xgboost.XGBRegressor` fit method. base_margin_col: To specify the base margins of the training and validation dataset, set :py:attr:`xgboost.spark.SparkXGBRegressor.base_margin_col` parameter instead of setting `base_margin` and `base_margin_eval_set` in the `xgboost.XGBRegressor` fit method. num_workers: How many XGBoost workers to be used to train. Each XGBoost worker corresponds to one spark task. device: .. versionadded:: 2.0.0 Device for XGBoost workers, available options are `cpu`, `cuda`, and `gpu`. force_repartition: Boolean value to specify if forcing the input dataset to be repartitioned before XGBoost training. repartition_random_shuffle: Boolean value to specify if randomly shuffling the dataset when repartitioning is required. enable_sparse_data_optim: Boolean value to specify if enabling sparse data optimization, if True, Xgboost DMatrix object will be constructed from sparse matrix instead of dense matrix. launch_tracker_on_driver: Boolean value to indicate whether the tracker should be launched on the driver side or the executor side. coll_cfg: The collective configuration. See :py:class:`~xgboost.collective.Config` kwargs: A dictionary of xgboost parameters, please refer to https://xgboost.readthedocs.io/en/stable/parameter.html Note ---- The Parameters chart above contains parameters that need special handling. For a full list of parameters, see entries with `Param(parent=...` below. This API is experimental. Examples -------- >>> from xgboost.spark import SparkXGBRegressor >>> from pyspark.ml.linalg import Vectors >>> df_train = spark.createDataFrame([ ... (Vectors.dense(1.0, 2.0, 3.0), 0, False, 1.0), ... (Vectors.sparse(3, {1: 1.0, 2: 5.5}), 1, False, 2.0), ... (Vectors.dense(4.0, 5.0, 6.0), 2, True, 1.0), ... (Vectors.sparse(3, {1: 6.0, 2: 7.5}), 3, True, 2.0), ... ], ["features", "label", "isVal", "weight"]) >>> df_test = spark.createDataFrame([ ... (Vectors.dense(1.0, 2.0, 3.0), ), ... (Vectors.sparse(3, {1: 1.0, 2: 5.5}), ) ... ], ["features"]) >>> xgb_regressor = SparkXGBRegressor(max_depth=5, missing=0.0, ... validation_indicator_col='isVal', weight_col='weight', ... early_stopping_rounds=1, eval_metric='rmse') >>> xgb_reg_model = xgb_regressor.fit(df_train) >>> xgb_reg_model.transform(df_test) featureslabel predictionNrFT) features_col label_colprediction_colpred_contrib_colvalidation_indicator_col weight_colbase_margin_col num_workersdeviceforce_repartitionrepartition_random_shuffleenable_sparse_data_optimlaunch_tracker_on_drivercoll_cfgrErFrGrHrIrJrKrLrMrNrOrPrQrRkwargsrc s$t|j}|jdi|dSNrsuper__init__ _input_kwargs setParams)selfrErFrGrHrIrJrKrLrMrNrOrPrQrRrS input_kwargs __class__rr rWs zSparkXGBRegressor.__init__cCtSr-rclsrrr r8zSparkXGBRegressor._xgb_clsSparkXGBRegressorModelcCr^r-)rcr`rrr _pyspark_model_clsrbz$SparkXGBRegressor._pyspark_model_clscs"t||jrtddS)NzCSpark Xgboost regressor estimator does not support `qid_col` param.rV_validate_params isDefinedqid_col ValueErrorrZr\rr rf  z"SparkXGBRegressor._validate_paramsrN)__name__ __module__ __qualname____doc__rrr6rrintboolr rrW classmethodrrr8rdrf __classcell__rrr\r rAOsnq     rAc@&eZdZdZedeefddZdS)rczt The model returned by :func:`xgboost.spark.SparkXGBRegressor.fit` .. Note:: This API is experimental. rcCr^r-r_r`rrr r8rbzSparkXGBRegressorModel._xgb_clsN)rmrnrorprsrrr8rrrr rcrcc&seZdZdZedddddddddddd d d d dd d eeeefd ededededeedeedeedeede deede de de de dee de ddf$fddZ edeefd d!Zeded"fd#d$Zd'fd%d& ZZS)(SparkXGBClassifieratSparkXGBClassifier is a PySpark ML estimator. It implements the XGBoost classification algorithm based on XGBoost python library, and it can be used in PySpark Pipeline and PySpark ML meta algorithms like - :py:class:`~pyspark.ml.tuning.CrossValidator`/ - :py:class:`~pyspark.ml.tuning.TrainValidationSplit`/ - :py:class:`~pyspark.ml.classification.OneVsRest` SparkXGBClassifier automatically supports most of the parameters in :py:class:`xgboost.XGBClassifier` constructor and most of the parameters used in :py:meth:`xgboost.XGBClassifier.fit` and :py:meth:`xgboost.XGBClassifier.predict` method. To enable GPU support, set `device` to `cuda` or `gpu`. SparkXGBClassifier doesn't support setting `base_margin` explicitly as well, but support another param called `base_margin_col`. see doc below for more details. SparkXGBClassifier doesn't support setting `output_margin`, but we can get output margin from the raw prediction column. See `raw_prediction_col` param doc below for more details. SparkXGBClassifier doesn't support `validate_features` and `output_margin` param. SparkXGBClassifier doesn't support setting `nthread` xgboost param, instead, the `nthread` param for each xgboost worker will be set equal to `spark.task.cpus` config value. Parameters ---------- features_col: When the value is string, it requires the features column name to be vector type. When the value is a list of string, it requires all the feature columns to be numeric types. label_col: Label column name. Default to "label". prediction_col: Prediction column name. Default to "prediction" probability_col: Column name for predicted class conditional probabilities. Default to probabilityCol raw_prediction_col: The `output_margin=True` is implicitly supported by the `rawPredictionCol` output column, which is always returned with the predicted margin values. pred_contrib_col: Contribution prediction column name. validation_indicator_col: For params related to `xgboost.XGBClassifier` training with evaluation dataset's supervision, set :py:attr:`xgboost.spark.SparkXGBClassifier.validation_indicator_col` parameter instead of setting the `eval_set` parameter in `xgboost.XGBClassifier` fit method. weight_col: To specify the weight of the training and validation dataset, set :py:attr:`xgboost.spark.SparkXGBClassifier.weight_col` parameter instead of setting `sample_weight` and `sample_weight_eval_set` parameter in `xgboost.XGBClassifier` fit method. base_margin_col: To specify the base margins of the training and validation dataset, set :py:attr:`xgboost.spark.SparkXGBClassifier.base_margin_col` parameter instead of setting `base_margin` and `base_margin_eval_set` in the `xgboost.XGBClassifier` fit method. num_workers: How many XGBoost workers to be used to train. Each XGBoost worker corresponds to one spark task. device: .. versionadded:: 2.0.0 Device for XGBoost workers, available options are `cpu`, `cuda`, and `gpu`. force_repartition: Boolean value to specify if forcing the input dataset to be repartitioned before XGBoost training. repartition_random_shuffle: Boolean value to specify if randomly shuffling the dataset when repartitioning is required. enable_sparse_data_optim: Boolean value to specify if enabling sparse data optimization, if True, Xgboost DMatrix object will be constructed from sparse matrix instead of dense matrix. launch_tracker_on_driver: Boolean value to indicate whether the tracker should be launched on the driver side or the executor side. coll_cfg: The collective configuration. See :py:class:`~xgboost.collective.Config` kwargs: A dictionary of xgboost parameters, please refer to https://xgboost.readthedocs.io/en/stable/parameter.html Note ---- The Parameters chart above contains parameters that need special handling. For a full list of parameters, see entries with `Param(parent=...` below. This API is experimental. Examples -------- >>> from xgboost.spark import SparkXGBClassifier >>> from pyspark.ml.linalg import Vectors >>> df_train = spark.createDataFrame([ ... (Vectors.dense(1.0, 2.0, 3.0), 0, False, 1.0), ... (Vectors.sparse(3, {1: 1.0, 2: 5.5}), 1, False, 2.0), ... (Vectors.dense(4.0, 5.0, 6.0), 0, True, 1.0), ... (Vectors.sparse(3, {1: 6.0, 2: 7.5}), 1, True, 2.0), ... ], ["features", "label", "isVal", "weight"]) >>> df_test = spark.createDataFrame([ ... (Vectors.dense(1.0, 2.0, 3.0), ), ... ], ["features"]) >>> xgb_classifier = SparkXGBClassifier(max_depth=5, missing=0.0, ... validation_indicator_col='isVal', weight_col='weight', ... early_stopping_rounds=1, eval_metric='logloss') >>> xgb_clf_model = xgb_classifier.fit(df_train) >>> xgb_clf_model.transform(df_test).show() rBrCrD probability rawPredictionNrFT)rErFrGprobability_colraw_prediction_colrHrIrJrKrLrMrNrOrPrQrRrErFrGrzr{rHrIrJrKrLrMrNrOrPrQrRrSrc s0t|j}|jdi||jdddS)N) objectiver)rVrWrXrY _setDefault)rZrErFrGrzr{rHrIrJrKrLrMrNrOrPrQrRrSr[r\rr rWrs zSparkXGBClassifier.__init__cCr^r-rr`rrr r8rbzSparkXGBClassifier._xgb_clsSparkXGBClassifierModelcCr^r-)rr`rrr rdrbz%SparkXGBClassifier._pyspark_model_clscs4t||jrtd|drtddS)NzDSpark Xgboost classifier estimator does not support `qid_col` param.r|zHSetting custom 'objective' param is not allowed in 'SparkXGBClassifier'.)rVrfrgrhri getOrDefaultrjr\rr rfs   z#SparkXGBClassifier._validate_paramsrl)rmrnrorprrr6rrrqrrr rrWrsrrr8rdrfrtrrr\r rwszy     rwc@ru)rzu The model returned by :func:`xgboost.spark.SparkXGBClassifier.fit` .. Note:: This API is experimental. rcCr^r-r~r`rrr r8rbz SparkXGBClassifierModel._xgb_clsN)rmrnrorprsrrr8rrrr rrvrc$seZdZdZedddddddddddddddd d eeeefd ed ed eedeedeedeedeede deede de de de dee de ddf"fddZ edeefddZededfd d!Zd$fd"d# ZZS)%SparkXGBRankeraJSparkXGBRanker is a PySpark ML estimator. It implements the XGBoost ranking algorithm based on XGBoost python library, and it can be used in PySpark Pipeline and PySpark ML meta algorithms like :py:class:`~pyspark.ml.tuning.CrossValidator`/ :py:class:`~pyspark.ml.tuning.TrainValidationSplit`/ :py:class:`~pyspark.ml.classification.OneVsRest` SparkXGBRanker automatically supports most of the parameters in :py:class:`xgboost.XGBRanker` constructor and most of the parameters used in :py:meth:`xgboost.XGBRanker.fit` and :py:meth:`xgboost.XGBRanker.predict` method. To enable GPU support, set `device` to `cuda` or `gpu`. SparkXGBRanker doesn't support setting `base_margin` explicitly as well, but support another param called `base_margin_col`. see doc below for more details. SparkXGBRanker doesn't support setting `output_margin`, but we can get output margin from the raw prediction column. See `raw_prediction_col` param doc below for more details. SparkXGBRanker doesn't support `validate_features` and `output_margin` param. SparkXGBRanker doesn't support setting `nthread` xgboost param, instead, the `nthread` param for each xgboost worker will be set equal to `spark.task.cpus` config value. Parameters ---------- features_col: When the value is string, it requires the features column name to be vector type. When the value is a list of string, it requires all the feature columns to be numeric types. label_col: Label column name. Default to "label". prediction_col: Prediction column name. Default to "prediction" pred_contrib_col: Contribution prediction column name. validation_indicator_col: For params related to `xgboost.XGBRanker` training with evaluation dataset's supervision, set :py:attr:`xgboost.spark.SparkXGBRanker.validation_indicator_col` parameter instead of setting the `eval_set` parameter in :py:class:`xgboost.XGBRanker` fit method. weight_col: To specify the weight of the training and validation dataset, set :py:attr:`xgboost.spark.SparkXGBRanker.weight_col` parameter instead of setting `sample_weight` and `sample_weight_eval_set` parameter in :py:class:`xgboost.XGBRanker` fit method. base_margin_col: To specify the base margins of the training and validation dataset, set :py:attr:`xgboost.spark.SparkXGBRanker.base_margin_col` parameter instead of setting `base_margin` and `base_margin_eval_set` in the :py:class:`xgboost.XGBRanker` fit method. qid_col: Query id column name. num_workers: How many XGBoost workers to be used to train. Each XGBoost worker corresponds to one spark task. device: .. versionadded:: 2.0.0 Device for XGBoost workers, available options are `cpu`, `cuda`, and `gpu`. force_repartition: Boolean value to specify if forcing the input dataset to be repartitioned before XGBoost training. repartition_random_shuffle: Boolean value to specify if randomly shuffling the dataset when repartitioning is required. enable_sparse_data_optim: Boolean value to specify if enabling sparse data optimization, if True, Xgboost DMatrix object will be constructed from sparse matrix instead of dense matrix. launch_tracker_on_driver: Boolean value to indicate whether the tracker should be launched on the driver side or the executor side. coll_cfg: The collective configuration. See :py:class:`~xgboost.collective.Config` kwargs: A dictionary of xgboost parameters, please refer to https://xgboost.readthedocs.io/en/stable/parameter.html .. Note:: The Parameters chart above contains parameters that need special handling. For a full list of parameters, see entries with `Param(parent=...` below. .. Note:: This API is experimental. Examples -------- >>> from xgboost.spark import SparkXGBRanker >>> from pyspark.ml.linalg import Vectors >>> ranker = SparkXGBRanker(qid_col="qid") >>> df_train = spark.createDataFrame( ... [ ... (Vectors.dense(1.0, 2.0, 3.0), 0, 0), ... (Vectors.dense(4.0, 5.0, 6.0), 1, 0), ... (Vectors.dense(9.0, 4.0, 8.0), 2, 0), ... (Vectors.sparse(3, {1: 1.0, 2: 5.5}), 0, 1), ... (Vectors.sparse(3, {1: 6.0, 2: 7.5}), 1, 1), ... (Vectors.sparse(3, {1: 8.0, 2: 9.5}), 2, 1), ... ], ... ["features", "label", "qid"], ... ) >>> df_test = spark.createDataFrame( ... [ ... (Vectors.dense(1.5, 2.0, 3.0), 0), ... (Vectors.dense(4.5, 5.0, 6.0), 0), ... (Vectors.dense(9.0, 4.5, 8.0), 0), ... (Vectors.sparse(3, {1: 1.0, 2: 6.0}), 1), ... (Vectors.sparse(3, {1: 6.0, 2: 7.0}), 1), ... (Vectors.sparse(3, {1: 8.0, 2: 10.5}), 1), ... ], ... ["features", "qid"], ... ) >>> model = ranker.fit(df_train) >>> model.transform(df_test).show() rBrCrDNrFT)rErFrGrHrIrJrKrhrLrMrNrOrPrQrRrErFrGrHrIrJrKrhrLrMrNrOrPrQrRrSrc s$t|j}|jdi|dSrTrU)rZrErFrGrHrIrJrKrhrLrMrNrOrPrQrRrSr[r\rr rW/s zSparkXGBRanker.__init__cCr^r-rr`rrr r8HrbzSparkXGBRanker._xgb_clsSparkXGBRankerModelcCr^r-)rr`rrr rdLrbz!SparkXGBRanker._pyspark_model_clscs"t||jstddS)Nz@Spark Xgboost ranker estimator requires setting `qid_col` param.rerjr\rr rfPrkzSparkXGBRanker._validate_paramsrl)rmrnrorprrr6rrrqrrr rrWrsrrr8rdrfrtrrr\r rstz     rc@ru)rzq The model returned by :func:`xgboost.spark.SparkXGBRanker.fit` .. Note:: This API is experimental. rcCr^r-rr`rrr r8_rbzSparkXGBRankerModel._xgb_clsN)rmrnrorprsrrr8rrrr rXrvr)$rptypingrrrrrnumpyr$pysparkrpyspark.ml.paramrr pyspark.ml.param.sharedr r collectiver sklearnrrrcorerrrutilsrr@rArcrwrrrrrrr s:    8 . %