# 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 mmlspark.core.serialize.java_params_patch import *
from pyspark.ml.wrapper import JavaTransformer, JavaEstimator, JavaModel
from pyspark.ml.common import inherit_doc
from mmlspark.core.schema.Utils import *
[docs]@inherit_doc
class AssembleFeatures(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaEstimator):
"""
Args:
allowImages (bool): Allow featurization of images (default: false)
columnsToFeaturize (list): Columns to featurize
featuresCol (str): The name of the features column (default: features)
numberOfFeatures (int): Number of features to hash string columns to
oneHotEncodeCategoricals (bool): One-hot encode categoricals (default: true)
"""
@keyword_only
def __init__(self, allowImages=False, columnsToFeaturize=None, featuresCol="features", numberOfFeatures=None, oneHotEncodeCategoricals=True):
super(AssembleFeatures, self).__init__()
self._java_obj = self._new_java_obj("com.microsoft.ml.spark.featurize.AssembleFeatures")
self.allowImages = Param(self, "allowImages", "allowImages: Allow featurization of images (default: false)")
self._setDefault(allowImages=False)
self.columnsToFeaturize = Param(self, "columnsToFeaturize", "columnsToFeaturize: Columns to featurize")
self.featuresCol = Param(self, "featuresCol", "featuresCol: The name of the features column (default: features)")
self._setDefault(featuresCol="features")
self.numberOfFeatures = Param(self, "numberOfFeatures", "numberOfFeatures: Number of features to hash string columns to")
self.oneHotEncodeCategoricals = Param(self, "oneHotEncodeCategoricals", "oneHotEncodeCategoricals: One-hot encode categoricals (default: true)")
self._setDefault(oneHotEncodeCategoricals=True)
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
self.setParams(**kwargs)
[docs] @keyword_only
def setParams(self, allowImages=False, columnsToFeaturize=None, featuresCol="features", numberOfFeatures=None, oneHotEncodeCategoricals=True):
"""
Set the (keyword only) parameters
Args:
allowImages (bool): Allow featurization of images (default: false)
columnsToFeaturize (list): Columns to featurize
featuresCol (str): The name of the features column (default: features)
numberOfFeatures (int): Number of features to hash string columns to
oneHotEncodeCategoricals (bool): One-hot encode categoricals (default: true)
"""
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
return self._set(**kwargs)
[docs] def getAllowImages(self):
"""
Returns:
bool: Allow featurization of images (default: false)
"""
return self.getOrDefault(self.allowImages)
[docs] def getColumnsToFeaturize(self):
"""
Returns:
list: Columns to featurize
"""
return self.getOrDefault(self.columnsToFeaturize)
[docs] def getFeaturesCol(self):
"""
Returns:
str: The name of the features column (default: features)
"""
return self.getOrDefault(self.featuresCol)
[docs] def getNumberOfFeatures(self):
"""
Returns:
int: Number of features to hash string columns to
"""
return self.getOrDefault(self.numberOfFeatures)
[docs] def getOneHotEncodeCategoricals(self):
"""
Returns:
bool: One-hot encode categoricals (default: true)
"""
return self.getOrDefault(self.oneHotEncodeCategoricals)
[docs] def setAllowImages(self, value):
"""
Args:
allowImages: Allow featurization of images (default: false)
"""
self._set(allowImages=value)
return self
[docs] def setColumnsToFeaturize(self, value):
"""
Args:
columnsToFeaturize: Columns to featurize
"""
self._set(columnsToFeaturize=value)
return self
[docs] def setFeaturesCol(self, value):
"""
Args:
featuresCol: The name of the features column (default: features)
"""
self._set(featuresCol=value)
return self
[docs] def setNumberOfFeatures(self, value):
"""
Args:
numberOfFeatures: Number of features to hash string columns to
"""
self._set(numberOfFeatures=value)
return self
[docs] def setOneHotEncodeCategoricals(self, value):
"""
Args:
oneHotEncodeCategoricals: One-hot encode categoricals (default: true)
"""
self._set(oneHotEncodeCategoricals=value)
return self
[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.ml.spark.featurize.AssembleFeatures"
@staticmethod
def _from_java(java_stage):
module_name=AssembleFeatures.__module__
module_name=module_name.rsplit(".", 1)[0] + ".AssembleFeatures"
return from_java(java_stage, module_name)
def _create_model(self, java_model):
return AssembleFeaturesModel(java_model)
[docs]class AssembleFeaturesModel(ComplexParamsMixin, JavaModel, JavaMLWritable, JavaMLReadable):
"""
Model fitted by :class:`AssembleFeatures`.
"""
[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.ml.spark.featurize.AssembleFeaturesModel"
@staticmethod
def _from_java(java_stage):
module_name=AssembleFeaturesModel.__module__
module_name=module_name.rsplit(".", 1)[0] + ".AssembleFeaturesModel"
return from_java(java_stage, module_name)