Source code for synapse.ml.featurize.CountSelectorModel

# Copyright (C) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See LICENSE in project root for information.


import sys
if sys.version >= '3':
    basestring = str

from pyspark import SparkContext, SQLContext
from pyspark.sql import DataFrame
from pyspark.ml.param.shared import *
from pyspark import keyword_only
from pyspark.ml.util import JavaMLReadable, JavaMLWritable
from synapse.ml.core.serialize.java_params_patch import *
from pyspark.ml.wrapper import JavaTransformer, JavaEstimator, JavaModel
from pyspark.ml.evaluation import JavaEvaluator
from pyspark.ml.common import inherit_doc
from synapse.ml.core.schema.Utils import *
from pyspark.ml.param import TypeConverters
from synapse.ml.core.schema.TypeConversionUtils import generateTypeConverter, complexTypeConverter


[docs]@inherit_doc class CountSelectorModel(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaModel): """ Args: indices (list): An array of indices to select features from a vector column. There can be no overlap with names. inputCol (object): The name of the input column outputCol (object): The name of the output column """ indices = Param(Params._dummy(), "indices", "An array of indices to select features from a vector column. There can be no overlap with names.", typeConverter=TypeConverters.toListInt) inputCol = Param(Params._dummy(), "inputCol", "The name of the input column") outputCol = Param(Params._dummy(), "outputCol", "The name of the output column") @keyword_only def __init__( self, java_obj=None, indices=None, inputCol=None, outputCol=None ): super(CountSelectorModel, self).__init__() if java_obj is None: self._java_obj = self._new_java_obj("com.microsoft.azure.synapse.ml.featurize.CountSelectorModel", self.uid) else: self._java_obj = java_obj if hasattr(self, "_input_kwargs"): kwargs = self._input_kwargs else: kwargs = self.__init__._input_kwargs if java_obj is None: for k,v in kwargs.items(): if v is not None: getattr(self, "set" + k[0].upper() + k[1:])(v)
[docs] @keyword_only def setParams( self, indices=None, inputCol=None, outputCol=None ): """ Set the (keyword only) parameters """ if hasattr(self, "_input_kwargs"): kwargs = self._input_kwargs else: kwargs = self.__init__._input_kwargs return self._set(**kwargs)
[docs] @classmethod def read(cls): """ Returns an MLReader instance for this class. """ return JavaMMLReader(cls)
[docs] @staticmethod def getJavaPackage(): """ Returns package name String. """ return "com.microsoft.azure.synapse.ml.featurize.CountSelectorModel"
@staticmethod def _from_java(java_stage): module_name=CountSelectorModel.__module__ module_name=module_name.rsplit(".", 1)[0] + ".CountSelectorModel" return from_java(java_stage, module_name)
[docs] def setIndices(self, value): """ Args: indices: An array of indices to select features from a vector column. There can be no overlap with names. """ self._set(indices=value) return self
[docs] def setInputCol(self, value): """ Args: inputCol: The name of the input column """ self._set(inputCol=value) return self
[docs] def setOutputCol(self, value): """ Args: outputCol: The name of the output column """ self._set(outputCol=value) return self
[docs] def getIndices(self): """ Returns: indices: An array of indices to select features from a vector column. There can be no overlap with names. """ return self.getOrDefault(self.indices)
[docs] def getInputCol(self): """ Returns: inputCol: The name of the input column """ return self.getOrDefault(self.inputCol)
[docs] def getOutputCol(self): """ Returns: outputCol: The name of the output column """ return self.getOrDefault(self.outputCol)