# 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 AnalyzeHealthText(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaTransformer):
"""
Args:
AADToken (object): AAD Token used for authentication
CustomAuthHeader (object): A Custom Value for Authorization Header
backoffs (list): array of backoffs to use in the handler
batchSize (int): The max size of the buffer
concurrency (int): max number of concurrent calls
concurrentTimeout (float): max number seconds to wait on futures if concurrency >= 1
disableServiceLogs (object): disableServiceLogs option
errorCol (str): column to hold http errors
initialPollingDelay (int): number of milliseconds to wait before first poll for result
language (object): the language code of the text (optional for some services)
maxPollingRetries (int): number of times to poll
modelVersion (object): Version of the model
outputCol (str): The name of the output column
pollingDelay (int): number of milliseconds to wait between polling
showStats (object): Whether to include detailed statistics in the response
stringIndexType (object): Specifies the method used to interpret string offsets. Defaults to Text Elements (Graphemes) according to Unicode v8.0.0. For additional information see https://aka.ms/text-analytics-offsets
subscriptionKey (object): the API key to use
suppressMaxRetriesException (bool): set true to suppress the maxumimum retries exception and report in the error column
text (object): the text in the request body
timeout (float): number of seconds to wait before closing the connection
url (str): Url of the service
"""
AADToken = Param(Params._dummy(), "AADToken", "ServiceParam: AAD Token used for authentication")
CustomAuthHeader = Param(Params._dummy(), "CustomAuthHeader", "ServiceParam: A Custom Value for Authorization Header")
backoffs = Param(Params._dummy(), "backoffs", "array of backoffs to use in the handler", typeConverter=TypeConverters.toListInt)
batchSize = Param(Params._dummy(), "batchSize", "The max size of the buffer", typeConverter=TypeConverters.toInt)
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)
disableServiceLogs = Param(Params._dummy(), "disableServiceLogs", "ServiceParam: disableServiceLogs option")
errorCol = Param(Params._dummy(), "errorCol", "column to hold http errors", typeConverter=TypeConverters.toString)
initialPollingDelay = Param(Params._dummy(), "initialPollingDelay", "number of milliseconds to wait before first poll for result", typeConverter=TypeConverters.toInt)
language = Param(Params._dummy(), "language", "ServiceParam: the language code of the text (optional for some services)")
maxPollingRetries = Param(Params._dummy(), "maxPollingRetries", "number of times to poll", typeConverter=TypeConverters.toInt)
modelVersion = Param(Params._dummy(), "modelVersion", "ServiceParam: Version of the model")
outputCol = Param(Params._dummy(), "outputCol", "The name of the output column", typeConverter=TypeConverters.toString)
pollingDelay = Param(Params._dummy(), "pollingDelay", "number of milliseconds to wait between polling", typeConverter=TypeConverters.toInt)
showStats = Param(Params._dummy(), "showStats", "ServiceParam: Whether to include detailed statistics in the response")
stringIndexType = Param(Params._dummy(), "stringIndexType", "ServiceParam: Specifies the method used to interpret string offsets. Defaults to Text Elements (Graphemes) according to Unicode v8.0.0. For additional information see https://aka.ms/text-analytics-offsets")
subscriptionKey = Param(Params._dummy(), "subscriptionKey", "ServiceParam: the API key to use")
suppressMaxRetriesException = Param(Params._dummy(), "suppressMaxRetriesException", "set true to suppress the maxumimum retries exception and report in the error column", typeConverter=TypeConverters.toBoolean)
text = Param(Params._dummy(), "text", "ServiceParam: the text in the request body")
timeout = Param(Params._dummy(), "timeout", "number of seconds to wait before closing the connection", typeConverter=TypeConverters.toFloat)
url = Param(Params._dummy(), "url", "Url of the service", typeConverter=TypeConverters.toString)
@keyword_only
def __init__(
self,
java_obj=None,
AADToken=None,
AADTokenCol=None,
CustomAuthHeader=None,
CustomAuthHeaderCol=None,
backoffs=[100,500,1000],
batchSize=10,
concurrency=1,
concurrentTimeout=None,
disableServiceLogs=None,
disableServiceLogsCol=None,
errorCol="AnalyzeHealthText_53c1cf950d83_error",
initialPollingDelay=300,
language=None,
languageCol=None,
maxPollingRetries=1000,
modelVersion=None,
modelVersionCol=None,
outputCol="AnalyzeHealthText_53c1cf950d83_output",
pollingDelay=300,
showStats=None,
showStatsCol=None,
stringIndexType=None,
stringIndexTypeCol=None,
subscriptionKey=None,
subscriptionKeyCol=None,
suppressMaxRetriesException=False,
text=None,
textCol=None,
timeout=60.0,
url=None
):
super(AnalyzeHealthText, self).__init__()
if java_obj is None:
self._java_obj = self._new_java_obj("com.microsoft.azure.synapse.ml.services.text.AnalyzeHealthText", self.uid)
else:
self._java_obj = java_obj
self._setDefault(backoffs=[100,500,1000])
self._setDefault(batchSize=10)
self._setDefault(concurrency=1)
self._setDefault(errorCol="AnalyzeHealthText_53c1cf950d83_error")
self._setDefault(initialPollingDelay=300)
self._setDefault(maxPollingRetries=1000)
self._setDefault(outputCol="AnalyzeHealthText_53c1cf950d83_output")
self._setDefault(pollingDelay=300)
self._setDefault(suppressMaxRetriesException=False)
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,
AADToken=None,
AADTokenCol=None,
CustomAuthHeader=None,
CustomAuthHeaderCol=None,
backoffs=[100,500,1000],
batchSize=10,
concurrency=1,
concurrentTimeout=None,
disableServiceLogs=None,
disableServiceLogsCol=None,
errorCol="AnalyzeHealthText_53c1cf950d83_error",
initialPollingDelay=300,
language=None,
languageCol=None,
maxPollingRetries=1000,
modelVersion=None,
modelVersionCol=None,
outputCol="AnalyzeHealthText_53c1cf950d83_output",
pollingDelay=300,
showStats=None,
showStatsCol=None,
stringIndexType=None,
stringIndexTypeCol=None,
subscriptionKey=None,
subscriptionKeyCol=None,
suppressMaxRetriesException=False,
text=None,
textCol=None,
timeout=60.0,
url=None
):
"""
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.services.text.AnalyzeHealthText"
@staticmethod
def _from_java(java_stage):
module_name=AnalyzeHealthText.__module__
module_name=module_name.rsplit(".", 1)[0] + ".AnalyzeHealthText"
return from_java(java_stage, module_name)
[docs] def setAADToken(self, value):
"""
Args:
AADToken: AAD Token used for authentication
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setAADToken(value)
return self
[docs] def setAADTokenCol(self, value):
"""
Args:
AADToken: AAD Token used for authentication
"""
self._java_obj = self._java_obj.setAADTokenCol(value)
return self
[docs] def setBackoffs(self, value):
"""
Args:
backoffs: array of backoffs to use in the handler
"""
self._set(backoffs=value)
return self
[docs] def setBatchSize(self, value):
"""
Args:
batchSize: The max size of the buffer
"""
self._set(batchSize=value)
return self
[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 setDisableServiceLogs(self, value):
"""
Args:
disableServiceLogs: disableServiceLogs option
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setDisableServiceLogs(value)
return self
[docs] def setDisableServiceLogsCol(self, value):
"""
Args:
disableServiceLogs: disableServiceLogs option
"""
self._java_obj = self._java_obj.setDisableServiceLogsCol(value)
return self
[docs] def setErrorCol(self, value):
"""
Args:
errorCol: column to hold http errors
"""
self._set(errorCol=value)
return self
[docs] def setInitialPollingDelay(self, value):
"""
Args:
initialPollingDelay: number of milliseconds to wait before first poll for result
"""
self._set(initialPollingDelay=value)
return self
[docs] def setLanguage(self, value):
"""
Args:
language: the language code of the text (optional for some services)
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setLanguage(value)
return self
[docs] def setLanguageCol(self, value):
"""
Args:
language: the language code of the text (optional for some services)
"""
self._java_obj = self._java_obj.setLanguageCol(value)
return self
[docs] def setMaxPollingRetries(self, value):
"""
Args:
maxPollingRetries: number of times to poll
"""
self._set(maxPollingRetries=value)
return self
[docs] def setModelVersion(self, value):
"""
Args:
modelVersion: Version of the model
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setModelVersion(value)
return self
[docs] def setModelVersionCol(self, value):
"""
Args:
modelVersion: Version of the model
"""
self._java_obj = self._java_obj.setModelVersionCol(value)
return self
[docs] def setOutputCol(self, value):
"""
Args:
outputCol: The name of the output column
"""
self._set(outputCol=value)
return self
[docs] def setPollingDelay(self, value):
"""
Args:
pollingDelay: number of milliseconds to wait between polling
"""
self._set(pollingDelay=value)
return self
[docs] def setShowStats(self, value):
"""
Args:
showStats: Whether to include detailed statistics in the response
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setShowStats(value)
return self
[docs] def setShowStatsCol(self, value):
"""
Args:
showStats: Whether to include detailed statistics in the response
"""
self._java_obj = self._java_obj.setShowStatsCol(value)
return self
[docs] def setStringIndexType(self, value):
"""
Args:
stringIndexType: Specifies the method used to interpret string offsets. Defaults to Text Elements (Graphemes) according to Unicode v8.0.0. For additional information see https://aka.ms/text-analytics-offsets
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setStringIndexType(value)
return self
[docs] def setStringIndexTypeCol(self, value):
"""
Args:
stringIndexType: Specifies the method used to interpret string offsets. Defaults to Text Elements (Graphemes) according to Unicode v8.0.0. For additional information see https://aka.ms/text-analytics-offsets
"""
self._java_obj = self._java_obj.setStringIndexTypeCol(value)
return self
[docs] def setSubscriptionKey(self, value):
"""
Args:
subscriptionKey: the API key to use
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setSubscriptionKey(value)
return self
[docs] def setSubscriptionKeyCol(self, value):
"""
Args:
subscriptionKey: the API key to use
"""
self._java_obj = self._java_obj.setSubscriptionKeyCol(value)
return self
[docs] def setSuppressMaxRetriesException(self, value):
"""
Args:
suppressMaxRetriesException: set true to suppress the maxumimum retries exception and report in the error column
"""
self._set(suppressMaxRetriesException=value)
return self
[docs] def setText(self, value):
"""
Args:
text: the text in the request body
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setText(value)
return self
[docs] def setTextCol(self, value):
"""
Args:
text: the text in the request body
"""
self._java_obj = self._java_obj.setTextCol(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 setUrl(self, value):
"""
Args:
url: Url of the service
"""
self._set(url=value)
return self
[docs] def getAADToken(self):
"""
Returns:
AADToken: AAD Token used for authentication
"""
return self._java_obj.getAADToken()
[docs] def getBackoffs(self):
"""
Returns:
backoffs: array of backoffs to use in the handler
"""
return self.getOrDefault(self.backoffs)
[docs] def getBatchSize(self):
"""
Returns:
batchSize: The max size of the buffer
"""
return self.getOrDefault(self.batchSize)
[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 getDisableServiceLogs(self):
"""
Returns:
disableServiceLogs: disableServiceLogs option
"""
return self._java_obj.getDisableServiceLogs()
[docs] def getErrorCol(self):
"""
Returns:
errorCol: column to hold http errors
"""
return self.getOrDefault(self.errorCol)
[docs] def getInitialPollingDelay(self):
"""
Returns:
initialPollingDelay: number of milliseconds to wait before first poll for result
"""
return self.getOrDefault(self.initialPollingDelay)
[docs] def getLanguage(self):
"""
Returns:
language: the language code of the text (optional for some services)
"""
return self._java_obj.getLanguage()
[docs] def getMaxPollingRetries(self):
"""
Returns:
maxPollingRetries: number of times to poll
"""
return self.getOrDefault(self.maxPollingRetries)
[docs] def getModelVersion(self):
"""
Returns:
modelVersion: Version of the model
"""
return self._java_obj.getModelVersion()
[docs] def getOutputCol(self):
"""
Returns:
outputCol: The name of the output column
"""
return self.getOrDefault(self.outputCol)
[docs] def getPollingDelay(self):
"""
Returns:
pollingDelay: number of milliseconds to wait between polling
"""
return self.getOrDefault(self.pollingDelay)
[docs] def getShowStats(self):
"""
Returns:
showStats: Whether to include detailed statistics in the response
"""
return self._java_obj.getShowStats()
[docs] def getStringIndexType(self):
"""
Returns:
stringIndexType: Specifies the method used to interpret string offsets. Defaults to Text Elements (Graphemes) according to Unicode v8.0.0. For additional information see https://aka.ms/text-analytics-offsets
"""
return self._java_obj.getStringIndexType()
[docs] def getSubscriptionKey(self):
"""
Returns:
subscriptionKey: the API key to use
"""
return self._java_obj.getSubscriptionKey()
[docs] def getSuppressMaxRetriesException(self):
"""
Returns:
suppressMaxRetriesException: set true to suppress the maxumimum retries exception and report in the error column
"""
return self.getOrDefault(self.suppressMaxRetriesException)
[docs] def getText(self):
"""
Returns:
text: the text in the request body
"""
return self._java_obj.getText()
[docs] def getTimeout(self):
"""
Returns:
timeout: number of seconds to wait before closing the connection
"""
return self.getOrDefault(self.timeout)
[docs] def getUrl(self):
"""
Returns:
url: Url of the service
"""
return self.getOrDefault(self.url)
[docs] def setCustomServiceName(self, value):
self._java_obj = self._java_obj.setCustomServiceName(value)
return self
[docs] def setEndpoint(self, value):
self._java_obj = self._java_obj.setEndpoint(value)
return self
[docs] def setDefaultInternalEndpoint(self, value):
self._java_obj = self._java_obj.setDefaultInternalEndpoint(value)
return self
def _transform(self, dataset: DataFrame) -> DataFrame:
return super()._transform(dataset)
[docs] def setLocation(self, value):
self._java_obj = self._java_obj.setLocation(value)
return self
[docs] def setLinkedService(self, value):
self._java_obj = self._java_obj.setLinkedService(value)
return self