Source code for SimpleHTTPTransformer
# 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 pyspark.ml.wrapper import JavaTransformer, JavaEstimator, JavaModel
from pyspark.ml.common import inherit_doc
from mmlspark.Utils import *
from mmlspark.TypeConversionUtils import generateTypeConverter, complexTypeConverter
[docs]@inherit_doc
class SimpleHTTPTransformer(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaTransformer):
"""
Args:
backoffTiming (object): times to use in backoffs (default: [I@22af2ee9)
concurrency (int): max number of concurrent calls (default: 1)
concurrentTimeout (double): max number seconds to wait on futures if concurrency >= 1 (default: 100.0)
errorCol (str): column to hold http errors (default: [self.uid]_errors)
flattenOutputBatches (bool): whether to flatten the output batches (default: false)
handlingStrategy (str): Which strategy to use when handling requests (default: advanced)
inputCol (str): The name of the input column
inputParser (object): format to parse the column to (default: JSONInputParser_fb7a4fa14efe)
miniBatcher (object): Minibatcher to use
outputCol (str): The name of the output column
outputParser (object): format to parse the column to
"""
@keyword_only
def __init__(self, backoffTiming="[I@22af2ee9", concurrency=1, concurrentTimeout=100.0, errorCol=None, flattenOutputBatches=False, handlingStrategy="advanced", inputCol=None, inputParser=None, miniBatcher=None, outputCol=None, outputParser=None):
super(SimpleHTTPTransformer, self).__init__()
self._java_obj = self._new_java_obj("com.microsoft.ml.spark.SimpleHTTPTransformer")
self._cache = {}
self.backoffTiming = Param(self, "backoffTiming", "backoffTiming: times to use in backoffs (default: [I@22af2ee9)")
self._setDefault(backoffTiming="[I@22af2ee9")
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.errorCol = Param(self, "errorCol", "errorCol: column to hold http errors (default: [self.uid]_errors)")
self._setDefault(errorCol=self.uid + "_errors")
self.flattenOutputBatches = Param(self, "flattenOutputBatches", "flattenOutputBatches: whether to flatten the output batches (default: false)")
self._setDefault(flattenOutputBatches=False)
self.handlingStrategy = Param(self, "handlingStrategy", "handlingStrategy: Which strategy to use when handling requests (default: advanced)")
self._setDefault(handlingStrategy="advanced")
self.inputCol = Param(self, "inputCol", "inputCol: The name of the input column")
self.inputParser = Param(self, "inputParser", "inputParser: format to parse the column to (default: JSONInputParser_fb7a4fa14efe)", generateTypeConverter("inputParser", self._cache, complexTypeConverter))
self.miniBatcher = Param(self, "miniBatcher", "miniBatcher: Minibatcher to use", generateTypeConverter("miniBatcher", self._cache, complexTypeConverter))
self.outputCol = Param(self, "outputCol", "outputCol: The name of the output column")
self.outputParser = Param(self, "outputParser", "outputParser: format to parse the column to", generateTypeConverter("outputParser", self._cache, complexTypeConverter))
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
self.setParams(**kwargs)
[docs] @keyword_only
def setParams(self, backoffTiming="[I@22af2ee9", concurrency=1, concurrentTimeout=100.0, errorCol=None, flattenOutputBatches=False, handlingStrategy="advanced", inputCol=None, inputParser=None, miniBatcher=None, outputCol=None, outputParser=None):
"""
Set the (keyword only) parameters
Args:
backoffTiming (object): times to use in backoffs (default: [I@22af2ee9)
concurrency (int): max number of concurrent calls (default: 1)
concurrentTimeout (double): max number seconds to wait on futures if concurrency >= 1 (default: 100.0)
errorCol (str): column to hold http errors (default: [self.uid]_errors)
flattenOutputBatches (bool): whether to flatten the output batches (default: false)
handlingStrategy (str): Which strategy to use when handling requests (default: advanced)
inputCol (str): The name of the input column
inputParser (object): format to parse the column to (default: JSONInputParser_fb7a4fa14efe)
miniBatcher (object): Minibatcher to use
outputCol (str): The name of the output column
outputParser (object): format to parse the column to
"""
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
return self._set(**kwargs)
[docs] def setBackoffTiming(self, value):
"""
Args:
backoffTiming (object): times to use in backoffs (default: [I@22af2ee9)
"""
self._set(backoffTiming=value)
return self
[docs] def getBackoffTiming(self):
"""
Returns:
object: times to use in backoffs (default: [I@22af2ee9)
"""
return self.getOrDefault(self.backoffTiming)
[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 setErrorCol(self, value):
"""
Args:
errorCol (str): column to hold http errors (default: [self.uid]_errors)
"""
self._set(errorCol=value)
return self
[docs] def getErrorCol(self):
"""
Returns:
str: column to hold http errors (default: [self.uid]_errors)
"""
return self.getOrDefault(self.errorCol)
[docs] def setFlattenOutputBatches(self, value):
"""
Args:
flattenOutputBatches (bool): whether to flatten the output batches (default: false)
"""
self._set(flattenOutputBatches=value)
return self
[docs] def getFlattenOutputBatches(self):
"""
Returns:
bool: whether to flatten the output batches (default: false)
"""
return self.getOrDefault(self.flattenOutputBatches)
[docs] def setHandlingStrategy(self, value):
"""
Args:
handlingStrategy (str): Which strategy to use when handling requests (default: advanced)
"""
self._set(handlingStrategy=value)
return self
[docs] def getHandlingStrategy(self):
"""
Returns:
str: Which strategy to use when handling requests (default: advanced)
"""
return self.getOrDefault(self.handlingStrategy)
[docs] def setInputCol(self, value):
"""
Args:
inputCol (str): The name of the input column
"""
self._set(inputCol=value)
return self
[docs] def getInputCol(self):
"""
Returns:
str: The name of the input column
"""
return self.getOrDefault(self.inputCol)
[docs] def setInputParser(self, value):
"""
Args:
inputParser (object): format to parse the column to (default: JSONInputParser_fb7a4fa14efe)
"""
self._set(inputParser=value)
return self
[docs] def getInputParser(self):
"""
Returns:
object: format to parse the column to (default: JSONInputParser_fb7a4fa14efe)
"""
return self._cache.get("inputParser", None)
[docs] def setMiniBatcher(self, value):
"""
Args:
miniBatcher (object): Minibatcher to use
"""
self._set(miniBatcher=value)
return self
[docs] def getMiniBatcher(self):
"""
Returns:
object: Minibatcher to use
"""
return self._cache.get("miniBatcher", None)
[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 setOutputParser(self, value):
"""
Args:
outputParser (object): format to parse the column to
"""
self._set(outputParser=value)
return self
[docs] def getOutputParser(self):
"""
Returns:
object: format to parse the column to
"""
return self._cache.get("outputParser", None)
[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.SimpleHTTPTransformer"
@staticmethod
def _from_java(java_stage):
module_name=SimpleHTTPTransformer.__module__
module_name=module_name.rsplit(".", 1)[0] + ".SimpleHTTPTransformer"
return from_java(java_stage, module_name)