# 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.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 PII(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaTransformer):
"""
Args:
concurrency (int): max number of concurrent calls
concurrentTimeout (float): max number seconds to wait on futures if concurrency >= 1
domain (object): if specified, will set the PII domain to include only a subset of the entity categories. Possible values include: 'PHI', 'none'.
errorCol (object): column to hold http errors
handler (object): Which strategy to use when handling requests
language (object): the language code of the text (optional for some services)
modelVersion (object): This value indicates which model will be used for scoring. If a model-version is not specified, the API should default to the latest, non-preview version.
outputCol (object): The name of the output column
piiCategories (object): describes the PII categories to return
showStats (object): if set to true, response will contain input and document level statistics.
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
text (object): the text in the request body
timeout (float): number of seconds to wait before closing the connection
url (object): Url of the service
"""
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)
domain = Param(Params._dummy(), "domain", "if specified, will set the PII domain to include only a subset of the entity categories. Possible values include: 'PHI', 'none'.")
errorCol = Param(Params._dummy(), "errorCol", "column to hold http errors")
handler = Param(Params._dummy(), "handler", "Which strategy to use when handling requests")
language = Param(Params._dummy(), "language", "the language code of the text (optional for some services)")
modelVersion = Param(Params._dummy(), "modelVersion", "This value indicates which model will be used for scoring. If a model-version is not specified, the API should default to the latest, non-preview version.")
outputCol = Param(Params._dummy(), "outputCol", "The name of the output column")
piiCategories = Param(Params._dummy(), "piiCategories", "describes the PII categories to return")
showStats = Param(Params._dummy(), "showStats", "if set to true, response will contain input and document level statistics.")
stringIndexType = Param(Params._dummy(), "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")
subscriptionKey = Param(Params._dummy(), "subscriptionKey", "the API key to use")
text = Param(Params._dummy(), "text", "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")
@keyword_only
def __init__(
self,
java_obj=None,
concurrency=1,
concurrentTimeout=None,
domain=None,
domainCol=None,
errorCol="PII_860b945b98ad_error",
handler=None,
language=None,
languageCol=None,
modelVersion=None,
modelVersionCol=None,
outputCol="PII_860b945b98ad_output",
piiCategories=None,
piiCategoriesCol=None,
showStats=None,
showStatsCol=None,
stringIndexType=None,
stringIndexTypeCol=None,
subscriptionKey=None,
subscriptionKeyCol=None,
text=None,
textCol=None,
timeout=60.0,
url=None
):
super(PII, self).__init__()
if java_obj is None:
self._java_obj = self._new_java_obj("com.microsoft.azure.synapse.ml.cognitive.PII", self.uid)
else:
self._java_obj = java_obj
self._setDefault(concurrency=1)
self._setDefault(errorCol="PII_860b945b98ad_error")
self._setDefault(outputCol="PII_860b945b98ad_output")
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,
domain=None,
domainCol=None,
errorCol="PII_860b945b98ad_error",
handler=None,
language=None,
languageCol=None,
modelVersion=None,
modelVersionCol=None,
outputCol="PII_860b945b98ad_output",
piiCategories=None,
piiCategoriesCol=None,
showStats=None,
showStatsCol=None,
stringIndexType=None,
stringIndexTypeCol=None,
subscriptionKey=None,
subscriptionKeyCol=None,
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.cognitive.PII"
@staticmethod
def _from_java(java_stage):
module_name=PII.__module__
module_name=module_name.rsplit(".", 1)[0] + ".PII"
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 setDomain(self, value):
"""
Args:
domain: if specified, will set the PII domain to include only a subset of the entity categories. Possible values include: 'PHI', 'none'.
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.org.apache.spark.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setDomain(value)
return self
[docs] def setDomainCol(self, value):
"""
Args:
domain: if specified, will set the PII domain to include only a subset of the entity categories. Possible values include: 'PHI', 'none'.
"""
self._java_obj = self._java_obj.setDomainCol(value)
return self
[docs] def setErrorCol(self, value):
"""
Args:
errorCol: column to hold http errors
"""
self._set(errorCol=value)
return self
[docs] def setHandler(self, value):
"""
Args:
handler: Which strategy to use when handling requests
"""
self._set(handler=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.org.apache.spark.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 setModelVersion(self, value):
"""
Args:
modelVersion: This value indicates which model will be used for scoring. If a model-version is not specified, the API should default to the latest, non-preview version.
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.org.apache.spark.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setModelVersion(value)
return self
[docs] def setModelVersionCol(self, value):
"""
Args:
modelVersion: This value indicates which model will be used for scoring. If a model-version is not specified, the API should default to the latest, non-preview version.
"""
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 setPiiCategories(self, value):
"""
Args:
piiCategories: describes the PII categories to return
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.org.apache.spark.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setPiiCategories(value)
return self
[docs] def setPiiCategoriesCol(self, value):
"""
Args:
piiCategories: describes the PII categories to return
"""
self._java_obj = self._java_obj.setPiiCategoriesCol(value)
return self
[docs] def setShowStats(self, value):
"""
Args:
showStats: if set to true, response will contain input and document level statistics.
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.org.apache.spark.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setShowStats(value)
return self
[docs] def setShowStatsCol(self, value):
"""
Args:
showStats: if set to true, response will contain input and document level statistics.
"""
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.org.apache.spark.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.org.apache.spark.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 setText(self, value):
"""
Args:
text: the text in the request body
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.org.apache.spark.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 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 getDomain(self):
"""
Returns:
domain: if specified, will set the PII domain to include only a subset of the entity categories. Possible values include: 'PHI', 'none'.
"""
return self.getOrDefault(self.domain)
[docs] def getErrorCol(self):
"""
Returns:
errorCol: column to hold http errors
"""
return self.getOrDefault(self.errorCol)
[docs] def getHandler(self):
"""
Returns:
handler: Which strategy to use when handling requests
"""
return self.getOrDefault(self.handler)
[docs] def getLanguage(self):
"""
Returns:
language: the language code of the text (optional for some services)
"""
return self.getOrDefault(self.language)
[docs] def getModelVersion(self):
"""
Returns:
modelVersion: This value indicates which model will be used for scoring. If a model-version is not specified, the API should default to the latest, non-preview version.
"""
return self.getOrDefault(self.modelVersion)
[docs] def getOutputCol(self):
"""
Returns:
outputCol: The name of the output column
"""
return self.getOrDefault(self.outputCol)
[docs] def getPiiCategories(self):
"""
Returns:
piiCategories: describes the PII categories to return
"""
return self.getOrDefault(self.piiCategories)
[docs] def getShowStats(self):
"""
Returns:
showStats: if set to true, response will contain input and document level statistics.
"""
return self.getOrDefault(self.showStats)
[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.getOrDefault(self.stringIndexType)
[docs] def getSubscriptionKey(self):
"""
Returns:
subscriptionKey: the API key to use
"""
return self.getOrDefault(self.subscriptionKey)
[docs] def getText(self):
"""
Returns:
text: the text in the request body
"""
return self.getOrDefault(self.text)
[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 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