Word2VecModel

class pyspark.mllib.feature.Word2VecModel(java_model: py4j.java_gateway.JavaObject)

class for Word2Vec model

Methods

call(name, *a)	Call method of java_model
findSynonyms(word, num)	Find synonyms of a word
getVectors()	Returns a map of words to their vector representations.
load(sc, path)	Load a model from the given path.
save(sc, path)	Save this model to the given path.
transform(word)	Transforms a word to its vector representation

Methods Documentation

call(name: str, *a: Any) → Any

Call method of java_model

findSynonyms(word: Union[str, VectorLike], num: int) → Iterable[Tuple[str, float]]

Find synonyms of a word

New in version 1.2.0.

Parameters

wordstr or pyspark.mllib.linalg.Vector

a word or a vector representation of word

numint

number of synonyms to find

Returns

collections.abc.Iterable

array of (word, cosineSimilarity)

Notes

Local use only

getVectors() → py4j.java_collections.JavaMap

Returns a map of words to their vector representations.

New in version 1.4.0.

classmethod load(sc: pyspark.context.SparkContext, path: str) → pyspark.mllib.feature.Word2VecModel

Load a model from the given path.

New in version 1.5.0.

save(sc: pyspark.context.SparkContext, path: str) → None

Save this model to the given path.

New in version 1.3.0.

transform(word: str) → pyspark.mllib.linalg.Vector

Transforms a word to its vector representation

New in version 1.2.0.

Parameters

wordstr

a word

Returns

pyspark.mllib.linalg.Vector

vector representation of word(s)

Notes

Local use only

previous

Word2Vec

next

ChiSqSelector