`sparknlp_jsl.annotator.qa.qa_ner_generator`#

This module is a wrapper for the NerQuestionGenerator class in the Scala API.

Module Contents#

Classes#

NerQuestionGenerator

Automatically generates questions for NER.

class NerQuestionGenerator(classname='com.johnsnowlabs.nlp.annotators.qa.NerQuestionGenerator', java_model=None)#

Bases: sparknlp_jsl.common.AnnotatorModelInternal

Automatically generates questions for NER.

This annotator takes an NER chunk (obtained by, e.g., NerConverterInternal) and generates a questions based on two entity types, a pronoun and a strategy.

The question is generated in the form of [QUESTIONPRONOUN] [ENTITY1] [ENTITY2] [QUESTIONMARK].

The generated question can be used by `QuestionAnswerer`annotator to find answers to the generated questions.

Input Annotation types	Output Annotation type
`CHUNK`	`LABEL_DEPENDENCY`

Parameters:

pronoun (str) – Pronoun to be used in the question. E.g., ‘When’, ‘Where’, ‘Why’, ‘How’, ‘Who’, ‘What’.
strategyType (str) – Strategy for the proccess. Either Paired or Combined.
questionMark (bool) – Whether to add a question mark at the end of the question.
entities1 (list) – List with the entity types of entities that appear first in the question.
entities2 (list) – List with the entity types of entities that appear second in the question.

Examples

>>> qagenerator = (
...    NerQuestionGenerator()
...    .setInputCols(["ner_chunk"])
...    .setOutputCol("question")
...    .setQuestionMark(True)
...    .setQuestionPronoun("When")
...    .setStrategyType("Paired")
...    .setEntities1(["PATIENT"])
...    .setEntities2(["ADMISSION"])
... )
>>> qagenerator..fit(data).transform(data).select("question").show(truncate=False)
+--------------------------------------------------------+
|question                                                |
+--------------------------------------------------------+
|[{document, 0, 25, When John Smith was admitted ? ...}] |
+--------------------------------------------------------+

entities1#

entities2#

getter_attrs = []#

inputAnnotatorTypes#

inputCols#

lazyAnnotator#

name = 'NerQuestionGenerator'#

optionalInputAnnotatorTypes = []#

outputAnnotatorType = 'document'#

outputCol#

questionMark#

questionPronoun#

skipLPInputColsValidation = True#

strategyType#

uid = ''#

clear(param: pyspark.ml.param.Param) → None#: Clears a param from the param map if it has been explicitly set.

copy(extra: pyspark.ml._typing.ParamMap | None = None) → JP#

Creates a copy of this instance with the same uid and some extra params. This implementation first calls Params.copy and then make a copy of the companion Java pipeline component with extra params. So both the Python wrapper and the Java pipeline component get copied.

Parameters:: extra (dict, optional) – Extra parameters to copy to the new instance
Returns:: Copy of this instance
Return type:: JavaParams

explainParam(param: str | Param) → str#: Explains a single param and returns its name, doc, and optional default value and user-supplied value in a string.

explainParams() → str#: Returns the documentation of all params with their optionally default values and user-supplied values.

extractParamMap(extra: pyspark.ml._typing.ParamMap | None = None) → pyspark.ml._typing.ParamMap#

Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values < user-supplied values < extra.

Parameters:: extra (dict, optional) – extra param values
Returns:: merged param map
Return type:: dict

getInputCols()#: Gets current column names of input annotations.

getLazyAnnotator()#: Gets whether Annotator should be evaluated lazily in a RecursivePipeline.

getOrDefault(param: str) → Any#
getOrDefault(param: Param[T]) → T: Gets the value of a param in the user-supplied param map or its default value. Raises an error if neither is set.

getOutputCol()#: Gets output column name of annotations.

getParam(paramName: str) → Param#: Gets a param by its name.

getParamValue(paramName)#

Gets the value of a parameter.

Parameters:: paramName (str) – Name of the parameter

hasDefault(param: str | Param[Any]) → bool#: Checks whether a param has a default value.

hasParam(paramName: str) → bool#: Tests whether this instance contains a param with a given (string) name.

inputColsValidation(value)#

isDefined(param: str | Param[Any]) → bool#: Checks whether a param is explicitly set by user or has a default value.

isSet(param: str | Param[Any]) → bool#: Checks whether a param is explicitly set by user.

classmethod load(path: str) → RL#: Reads an ML instance from the input path, a shortcut of read().load(path).

classmethod read()#: Returns an MLReader instance for this class.

save(path: str) → None#: Save this ML instance to the given path, a shortcut of ‘write().save(path)’.

set(param: Param, value: Any) → None#: Sets a parameter in the embedded param map.

setEntities1(entities: list)#

Sets the list of entity types that appear first in the question.

Parameters:: entities (list) – List of entity types.

setEntities2(entities)#

Sets the list of entity types that appear second in the question.

Parameters:: entities (list) – List of entity types.

setForceInputTypeValidation(etfm)#

setInputCols(*value)#

Sets column names of input annotations.

Parameters:: *value (List[str]) – Input columns for the annotator

setLazyAnnotator(value)#

Sets whether Annotator should be evaluated lazily in a RecursivePipeline.

Parameters:: value (bool) – Whether Annotator should be evaluated lazily in a RecursivePipeline

setOutputCol(value)#

Sets output column name of annotations.

Parameters:: value (str) – Name of output column

setParamValue(paramName)#

Sets the value of a parameter.

Parameters:: paramName (str) – Name of the parameter

setParams()#

setQuestionMark(value: bool)#

Sets whether we want to add a question mark at the end of the question.

Defaults to False.

Parameters:: value (bool) – True if we want to add a question mark at the end of the question, False otherwise.

setQuestionPronoun(pronoun)#

Sets the pronoun to be used in the question.

E.g., ‘When’, ‘Where’, ‘Why’, ‘How’, ‘Who’, ‘What’. Defaults to empty string (“”).

Parameters:: pronoun (str) – The pronoun to be used.

setStrategyType(value: str)#

Sets the strategy to be used in the proccess. Either Paired or Combined.

If set to Paired (default), applies a one-vs-one strategy. In this case, the number of chunks in Entity 1 must be aligned with the number of chunks in Entity 2. E.g., if Entity 1 has 3 chunks and Entity 2 has 3 chunks, the first chunk of Entity 1 will be grouped with first chunk of Entity 2, the second with second, third with third, etc.

If set to Combined, applies a one-vs-all strategy. In this case, the number of chunks in Entity 1 don’t need to be the same as the number of chunks in Entity 2, and each chunk in Entity 1 will be grouped with all chunks in Entity 2.

Parameters:: value (str) – The strategy to be used.

transform(dataset: pyspark.sql.dataframe.DataFrame, params: pyspark.ml._typing.ParamMap | None = None) → pyspark.sql.dataframe.DataFrame#

Transforms the input dataset with optional parameters.

New in version 1.3.0.

Parameters:

dataset (pyspark.sql.DataFrame) – input dataset
params (dict, optional) – an optional param map that overrides embedded params.

Returns:

transformed dataset

Return type:

pyspark.sql.DataFrame

write() → JavaMLWriter#: Returns an MLWriter instance for this ML instance.

sparknlp_jsl.annotator.qa.qa_ner_generator#

Module Contents#

Classes#

`sparknlp_jsl.annotator.qa.qa_ner_generator`#