sii]dZddlmZmZmZmZmZddlZddl m Z ddl m Z m Z ddlmZmZddlmZdd lmZmZmZd d lmZmZmZd d lmZd eedeeddfdZGddeZGddeZeeeGddeeeZ GddeZ!ee e!GddeZ"GddeZ#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 }dtdtf fd dtdtddf fd }|D]X}dt d |}ttj|| }|||Y }|D]c}dt d |}|d kr|d z }ttj|| }|||d }|D]X}dt d|}ttj|| }|||YdS)zyThis function automatically infer to xgboost parameters and set them into corresponding pyspark estimators and modelsvrc8t|tjr&tj|St|t r fd|DSt|trfd|DS|S)Nc.i|]\}}||Sr).0knvparam_value_converters ]/var/www/html/bet.cuttalo.com/ml/venv/lib/python3.11/site-packages/xgboost/spark/estimator.py zS_set_pyspark_xgb_cls_param_attrs..param_value_converter..#s+HHHUQA,,R00HHHc&g|] }|Srr)rr!r"s r# zS_set_pyspark_xgb_cls_param_attrs..param_value_converter..%s%:::"))"--:::r%) isinstancenpgenericarrayitemdictitemslist)rr"s r#r"z?_set_pyspark_xgb_cls_param_attrs..param_value_converters a $ $ &8A;;##%% % a   IHHHHaggiiHHH H a   ;::::::: :r% attr_nameparamNcZ|_t||t||dSN) typeConvertersetattr)r0r1rrr"s r#set_param_attrsz9_set_pyspark_xgb_cls_param_attrs..set_param_attrs(s53 9e,,,y%(((((r%zRefer 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_defaultrstrr keysr_xgb_clsr _dummy_get_fit_params_default_get_predict_params_default) rr params_dictr6r7r8 param_objfit_params_dictpredict_params_dictr"s `` @r# _set_pyspark_xgb_cls_param_attrsrEs[ 3355K)3)u)))))))))   "")) Li002233 L LEI L L !tEEE i((((7799O$$&& ) ) ,~i6H6H6J6J'K'K , ,%) , ,  ;   6 C &-//#>>> i((((#??AA#((**)) 0~i6H6H6J6J'K'K 0 0)- 0 0 &-//#>>> i(((( ))r%c"TeZdZdZeddddddddddddddd d eeeefd ed ed eedeedeedeede deede de de de dee de ddf fdZ edeefdZededfdZdfd ZxZS) 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_cfgrKrLrMrNrOrPrQrRrSrTrUrVrWrXkwargsrc pt|j}|jdi|dSNrsuper__init__ _input_kwargs setParams)selfrKrLrMrNrOrPrQrRrSrTrUrVrWrXrY input_kwargs __class__s r#r^zSparkXGBRegressor.__init__sA( ) &&&&&&&r%ctSr3rclss r#r=zSparkXGBRegressor._xgb_clsr%SparkXGBRegressorModelctSr3)rirfs r#_pyspark_model_clsz$SparkXGBRegressor._pyspark_model_clss%%r%ct||jrt ddS)NzCSpark Xgboost regressor estimator does not support `qid_col` param.r]_validate_params isDefinedqid_col ValueErrorrarcs r#rnz"SparkXGBRegressor._validate_paramssN   """ >>$, ' ' U   r%rN)__name__ __module__ __qualname____doc__rrr;rrintboolrrr^ classmethodrrr=rkrn __classcell__rcs@r#rGrGOsoob/9 **.26$()- $"'+0).)-%)!'''CcN+' '  ' #3- '#+3-'SM'"#'' ' '%)'#''#'' 6"!'"#'$ %'''''\'.l+[&4(@#A&&&[&r%rGc:eZdZdZedeefdZdS)rizt The model returned by :func:`xgboost.spark.SparkXGBRegressor.fit` .. Note:: This API is experimental. rctSr3rerfs r#r=zSparkXGBRegressorModel._xgb_clsrhr%N)rtrurvrwrzrrr=rr%r#ririsJ l+[r%ric&`eZdZdZedddddddddddd d d d dd d eeeefd ededededeedeedeedeede deede de de de dee de ddf$fdZ edeefdZeded fd!Zd#fd" ZxZS)$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() rHrIrJ probability rawPredictionNrFT)rKrLrMprobability_colraw_prediction_colrNrOrPrQrRrSrTrUrVrWrXrKrLrMrrrNrOrPrQrRrSrTrUrVrWrXrYrc t|j}|jdi||ddS)N) objectiver)r]r^r_r` _setDefault)rarKrLrMrrrNrOrPrQrRrSrTrUrVrWrXrYrbrcs r#r^zSparkXGBClassifier.__init__rsZ,  ) &&&&& 4(((((r%ctSr3rrfs r#r=zSparkXGBClassifier._xgb_clsr%SparkXGBClassifierModelctSr3)rrfs r#rkz%SparkXGBClassifier._pyspark_model_clss&&r%ct||jrt d|drt ddS)NzDSpark Xgboost classifier estimator does not support `qid_col` param.rzHSetting custom 'objective' param is not allowed in 'SparkXGBClassifier'.)r]rnrorprq getOrDefaultrrs r#rnz#SparkXGBClassifier._validate_paramss{   """ >>$, ' ' V    [ ) ) Z   r%rs)rtrurvrwrrr;rrrxryrrr^rzrrr=rkrnr{r|s@r#rrswwr/9 *,"1*.26$()- $"'+0).)-%)%)))CcN+) )  )  ) )#3-)#+3-)SM)"#)) ) )%)) #'!)"#'#)$6"%)&')( ))))))\)<m,['4(A#B'''['          r%rc:eZdZdZedeefdZdS)rzu The model returned by :func:`xgboost.spark.SparkXGBClassifier.fit` .. Note:: This API is experimental. rctSr3rrfs r#r=z SparkXGBClassifierModel._xgb_clsrr%N)rtrurvrwrzrrr=rr%r#rrsJ m,[r%rc$feZdZdZedddddddddddddddd d eeeefd ed ed eedeedeedeedeede deede de de de dee de ddf"fdZ edeefdZededfdZd fd ZxZS)!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() rHrIrJNrFT)rKrLrMrNrOrPrQrprRrSrTrUrVrWrXrKrLrMrNrOrPrQrprRrSrTrUrVrWrXrYrc pt|j}|jdi|dSr[r\)rarKrLrMrNrOrPrQrprRrSrTrUrVrWrXrYrbrcs r#r^zSparkXGBRanker.__init__/sA* ) &&&&&&&r%ctSr3rrfs r#r=zSparkXGBRanker._xgb_clsHr%SparkXGBRankerModelctSr3)rrfs r#rkz!SparkXGBRanker._pyspark_model_clsLs""r%ct||jst ddS)Nz@Spark Xgboost ranker estimator requires setting `qid_col` param.rmrrs r#rnzSparkXGBRanker._validate_paramsPsN   """~~dl++ R   r%rs)rtrurvrwrrr;rrrxryrrr^rzrrr=rkrnr{r|s@r#rrsxxt/9 **.26$()-!% $"'+0).)-%)#'''CcN+' '  ' #3- '#+3-'SM'"#'#'' ' '%)'#'' #'!'"6"#'$%'& ''''''\'0i[#4(=#>###[#r%rc:eZdZdZedeefdZdS)rzq The model returned by :func:`xgboost.spark.SparkXGBRanker.fit` .. Note:: This API is experimental. rctSr3rrfs r#r=zSparkXGBRankerModel._xgb_cls_rr%N)rtrurvrwrzrrr=rr%r#rrXsI i[r%r)$rwtypingrrrrrnumpyr)pysparkrpyspark.ml.paramr r pyspark.ml.param.sharedr r collectiversklearnrrrcorerrrutilsrrErGrirrrrrr%r#rs>> 43333333333333 ********JJJJJJJJ<<<<<<<<<< "!!!!!5)&'5)04^0D5) 5)5)5)5)pWWWWW*WWWt     ^   ! !24JKKKjjjjj+->@SjjjZ     2   ! !35LMMMaaaaa'aaaH     .   ! 1DEEEEEr%