sparknlp_jsl.legal.chunk_classification.resolution.docmapper#

Classes#

class DocMapperApproach(classname='com.johnsnowlabs.legal.chunk_classification.resolution.DocMapperApproach')#

Bases: sparknlp_jsl.common.AnnotatorApproachInternal, sparknlp_jsl.annotator.chunker.chunkmapper.CommonChunkMapperParams, sparknlp_jsl.annotator.chunker.chunkmapper.ChunkMapperFuzzyMatchingParams

Trains a DocMapperModel.

The chunk mapper Approach load a JsonDictionary that have the relations to be mapped in the DocMapperModel

Input Annotation types	Output Annotation type
DOCUMENT	LABEL_DEPENDENCY

Parameters:

• dictionary – Dictionary path where is the json that contains the mappinmgs columns

• rel – Relation that we going to use to map the chunk

• lowerCase – Parameter to decide if we going to use the chunk mapper or not

Examples

>>> import sparknlp
>>> from sparknlp.base import *
>>> from sparknlp_jsl.common import *
>>> from sparknlp.annotator import *
>>> from sparknlp.training import *
>>> import sparknlp_jsl
>>> from sparknlp_jsl.base import *
>>> from sparknlp_jsl.annotator import *
>>> from pyspark.ml import Pipeline
>>> documenter = DocumentAssembler()\
...     .setInputCol("text")\
...     .setOutputCol("documents")
>>> sentence_detector = SentenceDetector() \
...     .setInputCols("documents") \
...     .setOutputCol("sentences")
>>> tokenizer = Tokenizer() \
...     .setInputCols("sentences") \
...     .setOutputCol("tokens")
>>> embeddings = WordEmbeddingsModel() \
...     .pretrained("embeddings_clinical", "en", "clinical/models")\
...     .setInputCols(["sentences", "tokens"])\
...     .setOutputCol("embeddings")
>>> ner_model = MedicalNerModel()\
...     .pretrained("ner_posology_large", "en", "clinical/models")\
...     .setInputCols(["sentences", "tokens", "embeddings"])\
...     .setOutputCol("ner")
>>> ner_converter = NerConverterInternal()\
...     .setInputCols("sentences", "tokens", "ner")\
...     .setOutputCol("ner_chunks")
>>> chunkerMapperapproach = DocMapperApproach()\
...    .setInputCols(["ner_chunk"])\
...    .setOutputCol("mappings")\
...    .setDictionary("/home/jsl/mappings2.json") \
...    .setRels(["action"]) \
>>> sampleData = "The patient was given Warfarina Lusa and amlodipine 10 MG."
>>> pipeline = Pipeline().setStages([
...     documenter,
...     sentence_detector,
...     tokenizer,
...     embeddings,
...     ner_model,
...     ner_converter])
>>> results = pipeline.fit(data).transform(data)
>>> results.select("mappings").show(truncate=False)
+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|mappings                                                                                                                                                                                                                                                                                                                                                                                               |
+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|[{labeled_dependency, 22, 35, Analgesic, {chunk -> 0, relation -> action, confidence -> 0.56995, all_relations -> Antipyretic, entity -> Warfarina Lusa, sentence -> 0}, []}, {labeled_dependency, 41, 50, NONE, {entity -> amlodipine, sentence -> 0, chunk -> 1, confidence -> 0.9989}, []}, {labeled_dependency, 55, 56, NONE, {entity -> MG, sentence -> 0, chunk -> 2, confidence -> 0.9123}, []}]|
+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

allowMultiTokenChunk#

dictionary#

doExceptionHandling#

enableCharFingerprintMatching#

enableFuzzyMatching#

enableTokenFingerprintMatching#

fuzzyDistanceScalingMode#

fuzzyMatchingDistanceThresholds#

fuzzyMatchingDistances#

getter_attrs = []#

inputAnnotatorTypes#

inputCols#

lazyAnnotator#

lowerCase#

maxCharNgramFingerprint#

maxTokenNgramDroppingCharsRatio#

maxTokenNgramDroppingOperator#

maxTokenNgramDroppingTokens#

maxTokenNgramFingerprint#

minCharNgramFingerprint#

minTokenNgramFingerprint#

multivaluesRelations#

name = 'DocMapperApproach'#

optionalInputAnnotatorTypes = []#

outputAnnotatorType#

outputCol#

rel#

rels#

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

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

fit(dataset: pyspark.sql.dataframe.DataFrame, params: List[pyspark.ml._typing.ParamMap] | Tuple[pyspark.ml._typing.ParamMap]) → List[M]

Fits a model to the input dataset with optional parameters.

New in version 1.3.0.

Parameters:

• dataset (pyspark.sql.DataFrame) – input dataset.

• params (dict or list or tuple, optional) – an optional param map that overrides embedded params. If a list/tuple of param maps is given, this calls fit on each param map and returns a list of models.

Returns:

fitted model(s)

Return type:

Transformer or a list of Transformer

fitMultiple(dataset: pyspark.sql.dataframe.DataFrame, paramMaps: Sequence[pyspark.ml._typing.ParamMap]) → Iterator[Tuple[int, M]]#

Fits a model to the input dataset for each param map in paramMaps.

New in version 2.3.0.

Parameters:

• dataset (pyspark.sql.DataFrame) – input dataset.

• paramMaps (collections.abc.Sequence) – A Sequence of param maps.

Returns:

A thread safe iterable which contains one model for each param map. Each call to next(modelIterator) will return (index, model) where model was fit using paramMaps[index]. index values may not be sequential.

Return type:

_FitMultipleIterator

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.

setAllowMultiTokenChunk(mc)#

Whether to skip relations with multitokens.

Parameters:

mc (bool) – Whether to skip relations with multitokens.

setDictionary(p)#

Sets if we want to use ‘bow’ for word embeddings or ‘sentence’ for sentences”.

Parameters:

p (str) – Path where is the dictionary

setDoExceptionHandling(value: bool)#

If True, exceptions are handled. If exception causing data is passed to the model, a error annotation is emitted which has the exception message. Processing continues with the next one. This comes with a performance penalty.

Parameters:

value (bool) – If True, exceptions are handled.

setEnableCharFingerprintMatching(ecfm)#

Whether to apply char Ngram fingerprint matching.

Parameters:

ecfm (bool) – Whether to apply char Ngram fingerprint matching.

setEnableFuzzyMatching(efm: bool)#

Whether to apply fuzzy matching.

Parameters:

efm (bool) – Whether to apply fuzzy matching.

setEnableTokenFingerprintMatching(etfm: bool)#

Whether to apply partial token Ngram fingerprint matching.

This will create matching keys with partial Ngrams driven by three params: - minTokenNgramFingerprint - maxTokenNgramFingerprint - maxTokenNgramDropping

Parameters:

etfm (bool) – Whether to apply partial token Ngram fingerprint matching.

setForceInputTypeValidation(etfm)#

setFuzzyDistanceScalingMode(fdsm)#

Scaling mode for Integer Edit Distances.

Possible values are: left, right, long, short, none.

Parameters:

fdsm (str) – Scaling mode for Integer Edit Distances.

setFuzzyMatchingDistanceThresholds(fmdth)#

Thresholds for fuzzy matching.

The parameter enableFuzzyMatching must be set to true.

Parameters:

fmdth (float or list) – Threshold(s) for fuzzy matching.

setFuzzyMatchingDistances(fmd: str)#

Distance function to use for fuzzy matching.

The parameter enableFuzzyMatching must be set to true.

Possible values are: levenshtein, longest-common-subsequence, cosine, and/or jaccard.

Parameters:

fmd (str or list) – Distance function(s) to use for fuzzy matching.

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

setLowerCase(lc)#

Whether to save the keys of the dictionary in lower case or not.

Parameters:

lc (bool) – True to use the keys in lower case; False to save in the original casing.

setMaxCharNgramFingerprint(etfm: int)#

Maximum number of chars for Ngrams in Fingerprint.

The parameter enableCharFingerprintMatching must be set to true.

Parameters:

etfm (int) – Maximum number of chars for Ngrams in Fingerprint.

setMaxTokenNgramDroppingCharsRatio(etd: float)#

Maximum amount of tokens to allow dropping based on the maximum ratio of chars allowed to be dropped from the full chunk.

The parameter enableTokenNgramMatching must be set to true. Whenever it is desired for all Ngrams to be used as keys, no matter how short the final chunk is, this param should be set to 1.0.

Parameters:

etd (float) – Maximum amount of tokens to allow dropping based on the maximum ratio of chars allowed to be dropped from the full chunk.

setMaxTokenNgramDroppingOperator(etd: float)#

Maximum amount of tokens to allow dropping based on the maximum ratio of chars allowed to be dropped from the full chunk.

The parameter enableTokenNgramMatching must be set to true. Whenever it is desired for all Ngrams to be used as keys, no matter how short, this param should be set to 1.0.

Parameters:

etd (float) – Maximum amount of tokens to allow dropping based on the maximum ratio of chars allowed to be dropped from the full chunk.

setMaxTokenNgramDroppingTokens(etd: int)#

Maximum number of tokens allowed to be dropped from the full chunk.

The parameter enableTokenNgramMatching must be set to true. Whenever it is desired for all Ngrams to be used as keys, no matter how short the final chunk may be, this parameter should be set to a very high value: e.g., sys.maxsize.

Parameters:

etd (int) – Maximum number of tokens allowed to be dropped from the full chunk.

setMaxTokenNgramFingerprint(mxtnf: int)#

The max number of tokens for partial Ngrams in Fingerprint.

The parameter enableTokenFingerprintMatching must be set to true.

Parameters:

mxtnf (int) – The max number of tokens for partial Ngrams in Fingerprint.

setMinCharNgramFingerprint(etfm: int)#

Minimum number of chars for Ngrams in Fingerprint.

The parameter enableCharFingerprintMatching must be set to true.

Parameters:

etfm (int) – Minimum number of chars for Ngrams in Fingerprint.

setMinTokenNgramFingerprint(mntnf: int)#

The min number of tokens for partial Ngrams in Fingerprint.

The parameter enableTokenFingerprintMatching must be set to true.

Parameters:

mntnf (int) – The min number of tokens for partial Ngrams in Fingerprint.

setMultivaluesRelations(mc)#

Whether to send multi-chunk tokens or only single token chunks.

Parameters:

mc (bool) – Whether to send multi-chunk tokens or only single token chunks.

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

setRel(r)#

Sets the relation for the model.

Parameters:

r (str) – Relation for the model.

setRels(rs)#

Sets the relations to be mapped in the dictionary.

Parameters:

rs (list) – relations to be mapped in the dictionary.

write() → JavaMLWriter#

Returns an MLWriter instance for this ML instance.

class DocMapperModel(classname='com.johnsnowlabs.legal.chunk_classification.resolution.DocMapperModel', java_model=None)#

Bases: sparknlp_jsl.common.AnnotatorModelInternal, sparknlp_jsl.annotator.chunker.chunkmapper.CommonChunkMapperParams, sparknlp_jsl.annotator.chunker.chunkmapper.ChunkMapperFuzzyMatchingParams

Maps the chunks to the dictionary.

The chunk mapper Approach load a JsonDictionary that have the relations to be mapped in the DocMapperModel

Input Annotation types	Output Annotation type
DOCUMENT	LABEL_DEPENDENCY

Parameters:

• dictionary – Dictionary path where is the json that contains the mappinmgs columns

• rel – Relation that we going to use to map the chunk

• lowerCase – Parameter to decide if we going to use the chunk mapper or not

Examples

>>> import sparknlp
>>> from sparknlp.base import *
>>> from sparknlp_jsl.common import *
>>> from sparknlp.annotator import *
>>> from sparknlp.training import *
>>> import sparknlp_jsl
>>> from sparknlp_jsl.base import *
>>> from sparknlp_jsl.annotator import *
>>> from pyspark.ml import Pipeline
>>> documenter = DocumentAssembler()\
...     .setInputCol("text")\
...     .setOutputCol("documents")
>>> sentence_detector = SentenceDetector() \
...     .setInputCols("documents") \
...     .setOutputCol("sentences")
>>> tokenizer = Tokenizer() \
...     .setInputCols("sentences") \
...     .setOutputCol("tokens")
>>> embeddings = WordEmbeddingsModel() \
...     .pretrained("embeddings_clinical", "en", "clinical/models")\
...     .setInputCols(["sentences", "tokens"])\
...     .setOutputCol("embeddings")
>>> ner_model = MedicalNerModel()\
...     .pretrained("ner_posology_large", "en", "clinical/models")\
...     .setInputCols(["sentences", "tokens", "embeddings"])\
...     .setOutputCol("ner")
>>> ner_converter = NerConverterInternal()\
...     .setInputCols("sentences", "tokens", "ner")\
...     .setOutputCol("ner_chunks")
>>> chunkerMapperapproach = DocMapperModel()\
...    .pretrained()\
...    .setInputCols(["ner_chunk"])\
...    .setOutputCol("mappings")\
...    .setRels(["action"]) \
>>> sampleData = "The patient was given Warfarina Lusa and amlodipine 10 MG."
>>> pipeline = Pipeline().setStages([
...     documenter,
...     sentence_detector,
...     tokenizer,
...     embeddings,
...     ner_model,
...     ner_converter])
>>> results = pipeline.fit(data).transform(data)
>>> results = results \
...     .selectExpr("explode(drug_chunk_embeddings) AS drug_chunk") \
...     .selectExpr("drug_chunk.result", "slice(drug_chunk.embeddings, 1, 5) AS drug_embedding") \
...     .cache()
>>> results.show(truncate=False)
+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|mappings                                                                                                                                                                                                                                                                                                                                                                                               |
+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|[{labeled_dependency, 22, 35, Analgesic, {chunk -> 0, relation -> action, confidence -> 0.56995, all_relations -> Antipyretic, entity -> Warfarina Lusa, sentence -> 0}, []}, {labeled_dependency, 41, 50, NONE, {entity -> amlodipine, sentence -> 0, chunk -> 1, confidence -> 0.9989}, []}, {labeled_dependency, 55, 56, NONE, {entity -> MG, sentence -> 0, chunk -> 2, confidence -> 0.9123}, []}]|
+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

allowMultiTokenChunk#

doExceptionHandling#

getter_attrs = []#

inputAnnotatorTypes#

inputCols#

lazyAnnotator#

lowerCase#

multivaluesRelations#

name = 'DocMapperModel'#

optionalInputAnnotatorTypes = []#

outputAnnotatorType#

outputCol#

rel#

rels#

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).

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

Download a pre-trained DocMapperModel.

Parameters:

• name (str) – Name of the pre-trained model.

• lang (str) – Language of the pre-trained model.

• 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 DocMapperModel.

Return type:

DocMapperModel

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.

setAllowMultiTokenChunk(mc)#

Whether to skip relations with multitokens.

Parameters:

mc (bool) – Whether to skip relations with multitokens.

setDoExceptionHandling(value: bool)#

If True, exceptions are handled. If exception causing data is passed to the model, a error annotation is emitted which has the exception message. Processing continues with the next one. This comes with a performance penalty.

Parameters:

value (bool) – If True, exceptions are handled.

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

setLowerCase(lc)#

Whether to save the keys of the dictionary in lower case or not.

Parameters:

lc (bool) – True to use the keys in lower case; False to save in the original casing.

setMultivaluesRelations(mc)#

Whether to send multi-chunk tokens or only single token chunks.

Parameters:

mc (bool) – Whether to send multi-chunk tokens or only single token chunks.

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()#

setRel(r)#

Sets the relation for the model.

Parameters:

r (str) – Relation for the model.

setRels(rs)#

Sets the relations to be mapped in the dictionary.

Parameters:

rs (list) – relations to be mapped in the dictionary.

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.