o ڭjd @sdZddlmZddlmZddlmZmZGdddeZGdddeZ Gd d d eZ Gd d d eZ Gd ddeZ GdddeZ dS)z1Xgboost pyspark integration submodule for params.)Dict)TypeConverters)ParamParamsc@s*eZdZUdZeeddZded<dS)HasArbitraryParamsDictz This is a Params based class that is extended by _SparkXGBParams and holds the variable to store the **kwargs parts of the XGBoost input. arbitrary_params_dictzarbitrary_params_dict This parameter holds all of the additional parameters which are not exposed as the XGBoost Spark estimator params but can be recognized by underlying XGBoost library. It is stored as a dictionary.z Param[Dict]N) __name__ __module__ __qualname____doc__rr_dummyr__annotations__rrQ/var/www/html/CropPilot/venv/lib/python3.10/site-packages/xgboost/spark/params.pyr s rc@&eZdZdZeeddejdZ dS)HasBaseMarginColz This is a Params based class that is extended by _SparkXGBParams and holds the variable to store the base margin column part of XGboost. base_margin_colz6This stores the name for the column of the base margin typeConverterN) rr r r rrr rtoStringrrrrrrs rc8eZdZdZeeddejdZ d fdd Z Z S) HasFeaturesColsz Mixin for param features_cols: a list of feature column names. This parameter is taken effect only when GPU is enabled. features_colszfeature column names.rreturnNcst|jgddS)N)rsuper__init__ _setDefaultself __class__rrr4 zHasFeaturesCols.__init__rN) rr r r rrr r toListStringrr __classcell__rrr rr'srcr) HasEnableSparseDataOptimz This is a Params based class that is extended by _SparkXGBParams and holds the variable to store the boolean config of enabling sparse data optimization. enable_sparse_data_optima4This stores the boolean config of enabling sparse data optimization, if enabled, Xgboost DMatrix object will be constructed from sparse matrix instead of dense matrix. This config is disabled by default. If most of examples in your training dataset contains sparse features, we suggest to enable this config.rrNcst|jdddS)NF)r'rrr rrrIr"z!HasEnableSparseDataOptim.__init__r#) rr r r rrr r toBooleanr'rr%rrr rr&9s r&c@r) HasQueryIdColz8 Mixin for param qid_col: query id column name. qid_colzquery id column namerN) rr r r rrr rrr*rrrrr)Ns r)c@s0eZdZUdZeeddejdZ de d<dS)HasContribPredictionColz Mixin for param pred_contrib_col: contribution prediction column name. Output is a 3-dim array, with (rows, groups, columns + 1) for classification case. Else, it can be a 2 dimension for regression case. pred_contrib_colz0feature contributions to individual predictions.rz Param[str]N) rr r r rrr rrr,r rrrrr+[s r+N)r typingrpyspark.ml.paramrpyspark.ml.param.sharedrrrrrr&r)r+rrrrs