sparknlp.annotator.WordEmbeddingsModel

class sparknlp.annotator.WordEmbeddingsModel(classname='com.johnsnowlabs.nlp.embeddings.WordEmbeddingsModel', java_model=None)[source]

Bases: sparknlp.common.AnnotatorModel, sparknlp.common.HasEmbeddingsProperties, sparknlp.common.HasStorageModel

Word Embeddings lookup annotator that maps tokens to vectors

This is the instantiated model of WordEmbeddings.

Pretrained models can be loaded with pretrained() of the companion object:

>>> embeddings = WordEmbeddingsModel.pretrained() \
...       .setInputCols(["document", "token"]) \
...       .setOutputCol("embeddings")

The default model is "glove_100d", if no name is provided. For available pretrained models please see the Models Hub.

For extended examples of usage, see the Spark NLP Workshop.

Input Annotation types

Output Annotation type

DOCUMENT, TOKEN

WORD_EMBEDDINGS

Parameters
dimension

Number of embedding dimensions

readCacheSize

Cache size for items retrieved from storage. Increase for performance but higher memory consumption

Notes

There are also two convenient functions to retrieve the embeddings coverage with respect to the transformed dataset:

  • withCoverageColumn(): Adds a custom column with word coverage stats for the embedded field. This creates a new column with statistics for each row.

  • overallCoverage(): Calculates overall word coverage for the whole data in the embedded field. This returns a single coverage object considering all rows in the field.

Examples

>>> import sparknlp
>>> from sparknlp.base import *
>>> from sparknlp.annotator import *
>>> from pyspark.ml import Pipeline
>>> documentAssembler = DocumentAssembler() \
...     .setInputCol("text") \
...     .setOutputCol("document")
>>> tokenizer = Tokenizer() \
...     .setInputCols(["document"]) \
...     .setOutputCol("token")
>>> embeddings = WordEmbeddingsModel.pretrained() \
...     .setInputCols(["document", "token"]) \
...     .setOutputCol("embeddings")
>>> embeddingsFinisher = EmbeddingsFinisher() \
...     .setInputCols(["embeddings"]) \
...     .setOutputCols("finished_embeddings") \
...     .setOutputAsVector(True) \
...     .setCleanAnnotations(False)
>>> pipeline = Pipeline() \
...     .setStages([
...       documentAssembler,
...       tokenizer,
...       embeddings,
...       embeddingsFinisher
...     ])
>>> data = spark.createDataFrame([["This is a sentence."]]).toDF("text")
>>> result = pipeline.fit(data).transform(data)
>>> result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+--------------------------------------------------------------------------------+
|                                                                          result|
+--------------------------------------------------------------------------------+
|[-0.570580005645752,0.44183000922203064,0.7010200023651123,-0.417129993438720...|
|[-0.542639970779419,0.4147599935531616,1.0321999788284302,-0.4024400115013122...|
|[-0.2708599865436554,0.04400600120425224,-0.020260000601410866,-0.17395000159...|
|[0.6191999912261963,0.14650000631809235,-0.08592499792575836,-0.2629800140857...|
|[-0.3397899866104126,0.20940999686717987,0.46347999572753906,-0.6479200124740...|
+--------------------------------------------------------------------------------+

Methods

__init__([classname, java_model])

Initialize this instance with a Java model object.

clear(param)

Clears a param from the param map if it has been explicitly set.

copy([extra])

Creates a copy of this instance with the same uid and some extra params.

explainParam(param)

Explains a single param and returns its name, doc, and optional default value and user-supplied value in a string.

explainParams()

Returns the documentation of all params with their optionally default values and user-supplied values.

extractParamMap([extra])

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.

getCaseSensitive()

Gets whether to ignore case in tokens for embeddings matching.

getDimension()

Gets embeddings dimension.

getIncludeStorage()

Gets whether to include indexed storage in trained model.

getInputCols()

Gets current column names of input annotations.

getLazyAnnotator()

Gets whether Annotator should be evaluated lazily in a RecursivePipeline.

getOrDefault(param)

Gets the value of a param in the user-supplied param map or its default value.

getOutputCol()

Gets output column name of annotations.

getParam(paramName)

Gets a param by its name.

getParamValue(paramName)

Gets the value of a parameter.

getStorageRef()

Gets unique reference name for identification.

hasDefault(param)

Checks whether a param has a default value.

hasParam(paramName)

Tests whether this instance contains a param with a given (string) name.

isDefined(param)

Checks whether a param is explicitly set by user or has a default value.

isSet(param)

Checks whether a param is explicitly set by user.

load(path)

Reads an ML instance from the input path, a shortcut of read().load(path).

loadStorage(path, spark, storage_ref)

Loads the model from storage.

loadStorages(path, spark, storage_ref, databases)

overallCoverage(dataset, embeddings_col)

Calculates overall word coverage for the whole data in the embedded field.

pretrained([name, lang, remote_loc])

Downloads and loads a pretrained model.

read()

Returns an MLReader instance for this class.

save(path)

Save this ML instance to the given path, a shortcut of 'write().save(path)'.

saveStorage(path, spark)

Saves the current model to storage.

set(param, value)

Sets a parameter in the embedded param map.

setCaseSensitive(value)

Sets whether to ignore case in tokens for embeddings matching.

setDimension(value)

Sets embeddings dimension.

setIncludeStorage(value)

Sets whether to include indexed storage in trained model.

setInputCols(*value)

Sets column names of input annotations.

setLazyAnnotator(value)

Sets whether Annotator should be evaluated lazily in a RecursivePipeline.

setOutputCol(value)

Sets output column name of annotations.

setParamValue(paramName)

Sets the value of a parameter.

setParams()

setReadCacheSize(v)

Sets cache size for items retrieved from storage.

setStorageRef(value)

Sets unique reference name for identification.

transform(dataset[, params])

Transforms the input dataset with optional parameters.

withCoverageColumn(dataset, embeddings_col)

Adds a custom column with word coverage stats for the embedded field.

write()

Returns an MLWriter instance for this ML instance.

Attributes

caseSensitive

databases

dimension

getter_attrs

includeStorage

inputCols

lazyAnnotator

name

outputCol

params

Returns all params ordered by name.

readCacheSize

storageRef

clear(param)

Clears a param from the param map if it has been explicitly set.

copy(extra=None)

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 – Extra parameters to copy to the new instance

Returns

Copy of this instance

explainParam(param)

Explains a single param and returns its name, doc, and optional default value and user-supplied value in a string.

explainParams()

Returns the documentation of all params with their optionally default values and user-supplied values.

extractParamMap(extra=None)

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 – extra param values

Returns

merged param map

getCaseSensitive()

Gets whether to ignore case in tokens for embeddings matching.

Returns
bool

Whether to ignore case in tokens for embeddings matching

getDimension()

Gets embeddings dimension.

getIncludeStorage()

Gets whether to include indexed storage in trained model.

Returns
bool

Whether to include indexed storage in trained model

getInputCols()

Gets current column names of input annotations.

getLazyAnnotator()

Gets whether Annotator should be evaluated lazily in a RecursivePipeline.

getOrDefault(param)

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)

Gets a param by its name.

getParamValue(paramName)

Gets the value of a parameter.

Parameters
paramNamestr

Name of the parameter

getStorageRef()

Gets unique reference name for identification.

Returns
str

Unique reference name for identification

hasDefault(param)

Checks whether a param has a default value.

hasParam(paramName)

Tests whether this instance contains a param with a given (string) name.

isDefined(param)

Checks whether a param is explicitly set by user or has a default value.

isSet(param)

Checks whether a param is explicitly set by user.

classmethod load(path)

Reads an ML instance from the input path, a shortcut of read().load(path).

static loadStorage(path, spark, storage_ref)[source]

Loads the model from storage.

Parameters
pathstr

Path to the model

sparkpyspark.sql.SparkSession

The current SparkSession

storage_refstr

Identifiers for the model parameters

static overallCoverage(dataset, embeddings_col)[source]

Calculates overall word coverage for the whole data in the embedded field.

This returns a single coverage object considering all rows in the field.

Parameters
datasetpyspark.sql.DataFrame

The dataset with embeddings column

embeddings_colstr

Name of the embeddings column

Returns
CoverageResult

CoverateResult object with extracted information

Examples

>>> wordsOverallCoverage = WordEmbeddingsModel.overallCoverage(
...     resultDF,"embeddings"
... ).percentage
1.0
property params

Returns all params ordered by name. The default implementation uses dir() to get all attributes of type Param.

static pretrained(name='glove_100d', lang='en', remote_loc=None)[source]

Downloads and loads a pretrained model.

Parameters
namestr, optional

Name of the pretrained model, by default “glove_100d”

langstr, optional

Language of the pretrained model, by default “en”

remote_locstr, optional

Optional remote address of the resource, by default None. Will use Spark NLPs repositories otherwise.

Returns
WordEmbeddingsModel

The restored model

classmethod read()

Returns an MLReader instance for this class.

save(path)

Save this ML instance to the given path, a shortcut of ‘write().save(path)’.

saveStorage(path, spark)

Saves the current model to storage.

Parameters
pathstr

Path for saving the model.

sparkpyspark.sql.SparkSession

The current SparkSession

set(param, value)

Sets a parameter in the embedded param map.

setCaseSensitive(value)

Sets whether to ignore case in tokens for embeddings matching.

Parameters
valuebool

Whether to ignore case in tokens for embeddings matching

setDimension(value)

Sets embeddings dimension.

Parameters
valueint

Embeddings dimension

setIncludeStorage(value)

Sets whether to include indexed storage in trained model.

Parameters
valuebool

Whether to include indexed storage in trained model

setInputCols(*value)

Sets column names of input annotations.

Parameters
*valuestr

Input columns for the annotator

setLazyAnnotator(value)

Sets whether Annotator should be evaluated lazily in a RecursivePipeline.

Parameters
valuebool

Whether Annotator should be evaluated lazily in a RecursivePipeline

setOutputCol(value)

Sets output column name of annotations.

Parameters
valuestr

Name of output column

setParamValue(paramName)

Sets the value of a parameter.

Parameters
paramNamestr

Name of the parameter

setReadCacheSize(v)[source]

Sets cache size for items retrieved from storage. Increase for performance but higher memory consumption.

Parameters
vint

Cache size for items retrieved from storage

setStorageRef(value)

Sets unique reference name for identification.

Parameters
valuestr

Unique reference name for identification

transform(dataset, params=None)

Transforms the input dataset with optional parameters.

Parameters
  • dataset – input dataset, which is an instance of pyspark.sql.DataFrame

  • params – an optional param map that overrides embedded params.

Returns

transformed dataset

New in version 1.3.0.

uid

A unique id for the object.

static withCoverageColumn(dataset, embeddings_col, output_col='coverage')[source]

Adds a custom column with word coverage stats for the embedded field. This creates a new column with statistics for each row.

Parameters
datasetpyspark.sql.DataFrame

The dataset with embeddings column

embeddings_colstr

Name of the embeddings column

output_colstr, optional

Name for the resulting column, by default ‘coverage’

Returns
pyspark.sql.DataFrame

Dataframe with calculated coverage

Examples

>>> wordsCoverage = WordEmbeddingsModel.withCoverageColumn(resultDF, "embeddings", "cov_embeddings")
>>> wordsCoverage.select("text","cov_embeddings").show(truncate=False)
+-------------------+--------------+
|text               |cov_embeddings|
+-------------------+--------------+
|This is a sentence.|[5, 5, 1.0]   |
+-------------------+--------------+
write()

Returns an MLWriter instance for this ML instance.