hypertools.tools.gensim_models.HdpVectorizer

class hypertools.tools.gensim_models.HdpVectorizer(max_topics=20, seed=0)

Semantic-stage model: gensim’s HdpModel (Hierarchical Dirichlet Process), which discovers its own number of topics from the data rather than taking a fixed num_topics (unlike LdaVectorizer/ LsiVectorizer). Because the discovered topic count varies by corpus, transform produces a fixed-width dense matrix by truncating to the first max_topics HDP topic indices (dropping – not renormalizing – any probability mass assigned to topics beyond max_topics); increase max_topics to capture more of the tail.

Parameters:

max_topicsint

Fixed output width – the number of (leading) HDP topic indices to keep. Default: 20.

seedint or None

Random state for reproducible training (gensim’s random_state). Default: 0.

Attributes:

model_gensim.models.HdpModel

The trained HDP model (set by fit).

n_features_int

Vocabulary size seen during fit; transform requires the same width.

Methods

fit(X[, y])	Fit an HDP model to a dense document-term matrix.
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)	Compute (truncated) topic proportions for a dense document-term matrix.

__init__(max_topics=20, seed=0)

Methods

__init__([max_topics, seed])
fit(X[, y])	Fit an HDP model to a dense document-term matrix.
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)	Compute (truncated) topic proportions for a dense document-term matrix.