`sparknlp_jsl.annotator.ner.pretrained_zero_shot_ner`#

Module Contents#

Classes#

PretrainedZeroShotNER

Zero shot named entity recognition based on RoBertaForQuestionAnswering.

class PretrainedZeroShotNER(classname='com.johnsnowlabs.nlp.annotators.ner.PretrainedZeroShotNER', java_model=None)#

Bases: sparknlp_jsl.common.AnnotatorModelInternal

Zero shot named entity recognition based on RoBertaForQuestionAnswering.

Input Annotation types	Output Annotation type
`DOCUMENT`	`NAMED_ENTITY`

Parameters:

labels –
A list of labels descriving the entities. For example:
```
>>>    ["person", "location"]
```
predictionThreshold – Minimal confidence score to encode an entity (Default: 0.01f)

Examples

>>> document_assembler = DocumentAssembler() \
...     .setInputCol("text") \
...     .setOutputCol("document")
>>> sentence_detector = annotators.SentenceDetector()\
...     .setInputCols(["document"])\
...     .setOutputCol("sentence")
>>> pretrained_zero_shot_ner = PretrainedZeroShotNER()\
...     .pretrained()\
...     .setLabels(["person", "location"]
...     .setInputCols(["sentence"])\
...     .setOutputCol("entities")\
>>> data = spark.createDataFrame(
...         [["My name is Clara, I live in New York and Hellen lives in Paris."]]
...     ).toDF("text")
>>> Pipeline() \
...     .setStages([document_assembler, sentence_detector, pretrained_zero_shot_ner]) \
...     .fit(data) \
...     .transform(data) \
...     .selectExpr("document", "explode(entities) AS entity")\
...     .select(
...         "document.result",
...         "entity.result",
...         "entity.metadata.word",
...         "entity.metadata.confidence")\
...     .show(truncate=False)
    +-----------------------------------------------------------------+---------+-------+----------+
    |result                                                           |result   |word   |confidence|
    +-----------------------------------------------------------------+---------+-------+----------+
    |[My name is Clara, I live in New York and Hellen lives in Paris.]|person  |Clara   |0.9360068 |
    |[My name is Clara, I live in New York and Hellen lives in Paris.]|location|New York|0.83294415|
    |[My name is Clara, I live in New York and Hellen lives in Paris.]|person  |Hellen  |0.9360068 |
    |[My name is Clara, I live in New York and Hellen lives in Paris.]|location|Paris   |0.5328949 |
    +-----------------------------------------------------------------+--------+--------+----------+

getter_attrs = []#

inputAnnotatorTypes#

inputCols#

labels#

lazyAnnotator#

name = 'PretrainedZeroShotNER'#

optionalInputAnnotatorTypes = []#

outputAnnotatorType = 'named_entity'#

outputCol#

predictionThreshold#

skipLPInputColsValidation = True#

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.

getLabels()#: Returns the list of entities which are recognized.

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).

static loadSavedModel(folder, spark_session)#

Loads a locally saved model.

Parameters:

folder (str) – Folder of the saved model
spark_session (pyspark.sql.SparkSession) – The current SparkSession

Returns:

The restored model

Return type:

AutoGGUFModel

static pretrained(name='zeroshot_ner_deid_subentity_merged_medium', lang='en', remote_loc='clinical/models')#

Download a pre-trained PretrainedZeroShotNER.

Parameters:

name (str) – Name of the pre-trained model, by default “pretrained_zeroshot_ner”
lang (str) – Language of the pre-trained model, by default “en”
remote_loc (str) – Remote location of the pre-trained model. If None, use the open-source location. Other values are “clinical/models”, “finance/models”, or “legal/models”.

Returns:

A pre-trained PretrainedZeroShotNER.

Return type:

PretrainedZeroShotNER

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.

setForceInputTypeValidation(etfm)#

setInputCols(*value)#

Sets column names of input annotations.

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

setLabels(labels: list)#

Set entity descriptions.

Parameters:: labels (list[str]) – entity descriptions

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()#

setPredictionThreshold(threshold: float)#

Sets the minimal confidence score to encode an entity.

Parameters:: threshold (float) – minimal confidence score to encode an entity (default is 0.1)

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.ner.pretrained_zero_shot_ner#

Module Contents#

Classes#

`sparknlp_jsl.annotator.ner.pretrained_zero_shot_ner`#