# 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.platform import running_on_synapse_internal
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 PartitionConsolidator(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaTransformer):
"""
Args:
concurrency (int): max number of concurrent calls
concurrentTimeout (float): max number seconds to wait on futures if concurrency >= 1
inputCol (str): The name of the input column
outputCol (str): The name of the output column
timeout (float): number of seconds to wait before closing the connection
"""
concurrency = Param(Params._dummy(), "concurrency", "max number of concurrent calls", typeConverter=TypeConverters.toInt)
concurrentTimeout = Param(Params._dummy(), "concurrentTimeout", "max number seconds to wait on futures if concurrency >= 1", typeConverter=TypeConverters.toFloat)
inputCol = Param(Params._dummy(), "inputCol", "The name of the input column", typeConverter=TypeConverters.toString)
outputCol = Param(Params._dummy(), "outputCol", "The name of the output column", typeConverter=TypeConverters.toString)
timeout = Param(Params._dummy(), "timeout", "number of seconds to wait before closing the connection", typeConverter=TypeConverters.toFloat)
@keyword_only
def __init__(
self,
java_obj=None,
concurrency=1,
concurrentTimeout=None,
inputCol=None,
outputCol=None,
timeout=60.0
):
super(PartitionConsolidator, self).__init__()
if java_obj is None:
self._java_obj = self._new_java_obj("com.microsoft.azure.synapse.ml.stages.PartitionConsolidator", self.uid)
else:
self._java_obj = java_obj
self._setDefault(concurrency=1)
self._setDefault(timeout=60.0)
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,
concurrency=1,
concurrentTimeout=None,
inputCol=None,
outputCol=None,
timeout=60.0
):
"""
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.stages.PartitionConsolidator"
@staticmethod
def _from_java(java_stage):
module_name=PartitionConsolidator.__module__
module_name=module_name.rsplit(".", 1)[0] + ".PartitionConsolidator"
return from_java(java_stage, module_name)
[docs] def setConcurrency(self, value):
"""
Args:
concurrency: max number of concurrent calls
"""
self._set(concurrency=value)
return self
[docs] def setConcurrentTimeout(self, value):
"""
Args:
concurrentTimeout: max number seconds to wait on futures if concurrency >= 1
"""
self._set(concurrentTimeout=value)
return self
[docs] def setOutputCol(self, value):
"""
Args:
outputCol: The name of the output column
"""
self._set(outputCol=value)
return self
[docs] def setTimeout(self, value):
"""
Args:
timeout: number of seconds to wait before closing the connection
"""
self._set(timeout=value)
return self
[docs] def getConcurrency(self):
"""
Returns:
concurrency: max number of concurrent calls
"""
return self.getOrDefault(self.concurrency)
[docs] def getConcurrentTimeout(self):
"""
Returns:
concurrentTimeout: max number seconds to wait on futures if concurrency >= 1
"""
return self.getOrDefault(self.concurrentTimeout)
[docs] def getOutputCol(self):
"""
Returns:
outputCol: The name of the output column
"""
return self.getOrDefault(self.outputCol)
[docs] def getTimeout(self):
"""
Returns:
timeout: number of seconds to wait before closing the connection
"""
return self.getOrDefault(self.timeout)