# 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.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 DataConversion(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaTransformer):
"""
Args:
cols (list): Comma separated list of columns whose type will be converted
convertTo (str): The result type (default: )
dateTimeFormat (str): Format for DateTime when making DateTime:String conversions (default: yyyy-MM-dd HH:mm:ss)
"""
@keyword_only
def __init__(self, cols=None, convertTo="", dateTimeFormat="yyyy-MM-dd HH:mm:ss"):
super(DataConversion, self).__init__()
self._java_obj = self._new_java_obj("com.microsoft.ml.spark.featurize.DataConversion")
self.cols = Param(self, "cols", "cols: Comma separated list of columns whose type will be converted")
self.convertTo = Param(self, "convertTo", "convertTo: The result type (default: )")
self._setDefault(convertTo="")
self.dateTimeFormat = Param(self, "dateTimeFormat", "dateTimeFormat: Format for DateTime when making DateTime:String conversions (default: yyyy-MM-dd HH:mm:ss)")
self._setDefault(dateTimeFormat="yyyy-MM-dd HH:mm:ss")
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
self.setParams(**kwargs)
[docs] @keyword_only
def setParams(self, cols=None, convertTo="", dateTimeFormat="yyyy-MM-dd HH:mm:ss"):
"""
Set the (keyword only) parameters
Args:
cols (list): Comma separated list of columns whose type will be converted
convertTo (str): The result type (default: )
dateTimeFormat (str): Format for DateTime when making DateTime:String conversions (default: yyyy-MM-dd HH:mm:ss)
"""
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
return self._set(**kwargs)
[docs] def setCols(self, value):
"""
Args:
cols (list): Comma separated list of columns whose type will be converted
"""
self._set(cols=value)
return self
[docs] def getCols(self):
"""
Returns:
list: Comma separated list of columns whose type will be converted
"""
return self.getOrDefault(self.cols)
[docs] def setConvertTo(self, value):
"""
Args:
convertTo (str): The result type (default: )
"""
self._set(convertTo=value)
return self
[docs] def getConvertTo(self):
"""
Returns:
str: The result type (default: )
"""
return self.getOrDefault(self.convertTo)
[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.DataConversion"
@staticmethod
def _from_java(java_stage):
module_name=DataConversion.__module__
module_name=module_name.rsplit(".", 1)[0] + ".DataConversion"
return from_java(java_stage, module_name)