# 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 PartitionConsolidator(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaTransformer):
"""
Args:
concurrency (int): max number of concurrent calls (default: 1)
concurrentTimeout (double): max number seconds to wait on futures if concurrency >= 1 (default: 100.0)
inputCol (str): The name of the input column
outputCol (str): The name of the output column
timeout (double): number of seconds to wait before closing the connection (default: 60.0)
"""
@keyword_only
def __init__(self, concurrency=1, concurrentTimeout=100.0, inputCol=None, outputCol=None, timeout=60.0):
super(PartitionConsolidator, self).__init__()
self._java_obj = self._new_java_obj("com.microsoft.ml.spark.io.http.PartitionConsolidator")
self.concurrency = Param(self, "concurrency", "concurrency: max number of concurrent calls (default: 1)")
self._setDefault(concurrency=1)
self.concurrentTimeout = Param(self, "concurrentTimeout", "concurrentTimeout: max number seconds to wait on futures if concurrency >= 1 (default: 100.0)")
self._setDefault(concurrentTimeout=100.0)
self.inputCol = Param(self, "inputCol", "inputCol: The name of the input column")
self.outputCol = Param(self, "outputCol", "outputCol: The name of the output column")
self.timeout = Param(self, "timeout", "timeout: number of seconds to wait before closing the connection (default: 60.0)")
self._setDefault(timeout=60.0)
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
self.setParams(**kwargs)
[docs] @keyword_only
def setParams(self, concurrency=1, concurrentTimeout=100.0, inputCol=None, outputCol=None, timeout=60.0):
"""
Set the (keyword only) parameters
Args:
concurrency (int): max number of concurrent calls (default: 1)
concurrentTimeout (double): max number seconds to wait on futures if concurrency >= 1 (default: 100.0)
inputCol (str): The name of the input column
outputCol (str): The name of the output column
timeout (double): number of seconds to wait before closing the connection (default: 60.0)
"""
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
return self._set(**kwargs)
[docs] def setConcurrency(self, value):
"""
Args:
concurrency (int): max number of concurrent calls (default: 1)
"""
self._set(concurrency=value)
return self
[docs] def getConcurrency(self):
"""
Returns:
int: max number of concurrent calls (default: 1)
"""
return self.getOrDefault(self.concurrency)
[docs] def setConcurrentTimeout(self, value):
"""
Args:
concurrentTimeout (double): max number seconds to wait on futures if concurrency >= 1 (default: 100.0)
"""
self._set(concurrentTimeout=value)
return self
[docs] def getConcurrentTimeout(self):
"""
Returns:
double: max number seconds to wait on futures if concurrency >= 1 (default: 100.0)
"""
return self.getOrDefault(self.concurrentTimeout)
[docs] def setOutputCol(self, value):
"""
Args:
outputCol (str): The name of the output column
"""
self._set(outputCol=value)
return self
[docs] def getOutputCol(self):
"""
Returns:
str: The name of the output column
"""
return self.getOrDefault(self.outputCol)
[docs] def setTimeout(self, value):
"""
Args:
timeout (double): number of seconds to wait before closing the connection (default: 60.0)
"""
self._set(timeout=value)
return self
[docs] def getTimeout(self):
"""
Returns:
double: number of seconds to wait before closing the connection (default: 60.0)
"""
return self.getOrDefault(self.timeout)
[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.io.http.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)