sparknlp_jsl.annotator.chunk2_token#

Classes#

class Chunk2Token(classname='com.johnsnowlabs.nlp.annotators.Chunk2Token', java_model=None)#

Bases: sparknlp_jsl.common.AnnotatorModelInternal

Converts CHUNK type annotations into TOKEN type

Input Annotation types	Output Annotation type
CHUNK	TOKEN

Examples

>>> import sparknlp
>>> from sparknlp.base import *
>>> from sparknlp.annotator import *
>>> from pyspark.ml import Pipeline
>>> documentAssembler = DocumentAssembler().setInputCol("text").setOutputCol("document")
>>> chunkAssembler = sentenceDetector = SentenceDetector().setInputCols("document").setOutputCol("sentence")
>>> tokenizer = Tokenizer().setInputCols("sentence").setOutputCol("token")
>>> nGramGenerator = NGramGenerator().setInputCols("token").setOutputCol("ngrams") \
...     .setDelimiter("_").setN(2).setEnableCumulative(False)
>>> chunk2Token = Chunk2Token().setInputCols("ngrams").setOutputCol("ngram_tokens")
>>> data = spark.createDataFrame([["A 63-year-old man presents to the hospital."]]).toDF("text")
>>> pipeline = Pipeline() \
...     .setStages([documentAssembler, chunkAssembler, tokenizer, nGramGenerator, chunk2Token]).fit(data)
>>> result = pipeline.transform(data)
>>> result.selectExpr("ngram_tokens").show(truncate=False)
+----------------------------------------------------------------+
|result                                                          |
+----------------------------------------------------------------+
|{token, 0, 12, A_63-year-old, {sentence -> 0, chunk -> 0}, []}  |
|{token, 2, 16, 63-year-old_man, {sentence -> 0, chunk -> 1}, []}|
|{token, 14, 25, man_presents, {sentence -> 0, chunk -> 2}, []}  |
|{token, 18, 28, presents_to, {sentence -> 0, chunk -> 3}, []}   |
|{token, 27, 32, to_the, {sentence -> 0, chunk -> 4}, []}        |
|{token, 30, 41, the_hospital, {sentence -> 0, chunk -> 5}, []}  |
|{token, 34, 42, hospital_., {sentence -> 0, chunk -> 6}, []}    |
+----------------------------------------------------------------+

getter_attrs = []#

inputAnnotatorTypes#

inputCols#

lazyAnnotator#

name = 'Chunk2Token'#

optionalInputAnnotatorTypes = []#

outputAnnotatorType = 'token'#

outputCol#

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.

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.

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()#

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.