hypertools.tools.gensim_models.FastTextVectorizer

class hypertools.tools.gensim_models.FastTextVectorizer(vector_size=100, window=5, min_count=1, epochs=10, seed=0, workers=None)

Vectorizer-stage model: a document’s vector is the mean of its tokens’ trained gensim FastText word vectors. Unlike Word2VecVectorizer, out-of-vocabulary tokens are subword-safe: FastText represents every word (seen or unseen) as the sum of its character n-gram vectors, so transform can produce meaningful vectors for words never seen during fit.

Parameters:

vector_sizeint

Dimensionality of the word (and document) vectors. Default: 100.

windowint

Maximum distance between the current and predicted word within a sentence. Default: 5.

min_countint

Ignores all words with total frequency lower than this. Default: 1.

epochsint

Number of training epochs. Default: 10.

seedint or None

Random seed for reproducible training. Default: 0. See Word2VecVectorizer for the single-worker determinism note.

workersint or None

Number of worker threads. Default: None (resolves per _effective_workers).

Attributes:

model_gensim.models.FastText

The trained FastText model (set by fit).

Methods

fit(X[, y])	Train a FastText model on the given documents.
fit_transform(X[, y])	Fit to data, then transform it.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
set_output(*[, transform])	Set output container.
set_params(**params)	Set the parameters of this estimator.
transform(X)	Embed documents as the mean of their (subword-safe) word vectors.

__init__(vector_size=100, window=5, min_count=1, epochs=10, seed=0, workers=None)

Methods

__init__([vector_size, window, min_count, ...])
fit(X[, y])	Train a FastText model on the given documents.
fit_transform(X[, y])	Fit to data, then transform it.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
set_output(*[, transform])	Set output container.
set_params(**params)	Set the parameters of this estimator.
transform(X)	Embed documents as the mean of their (subword-safe) word vectors.