def prepare(topic_model, corpus, dictionary, doc_topic_dist=None, **kwargs):
"""Transforms the Gensim TopicModel and related corpus and dictionary into
the data structures needed for the visualization.
Parameters
----------
topic_model : gensim.models.hdpmodel.HdpModel
An already trained Gensim HdpModel.
corpus : array-like list of bag of word docs in tuple form or scipy CSC matrix
The corpus in bag of word form, the same docs used to train the model.
The corpus is transformed into a csc matrix internally, if you intend to
call prepare multiple times it is a good idea to first call
`gensim.matutils.corpus2csc(corpus)` and pass in the csc matrix instead.
For example: [(50, 3), (63, 5), ....]
dictionary: gensim.corpora.Dictionary
The dictionary object used to create the corpus. Needed to extract the
actual terms (not ids).
doc_topic_dist (optional): Document topic distribution from LDA (default=None)
The document topic distribution that is eventually visualised, if you will
be calling `prepare` multiple times it's a good idea to explicitly pass in
`doc_topic_dist` as inferring this for large corpora can be quite
expensive.
**kwargs :
additional keyword arguments are passed through to :func:`pyldavis.prepare`.
Returns
-------
prepared_data : PreparedData
the data structures used in the visualization
Example
--------
For example usage please see this notebook:
http://nbviewer.ipython.org/github/bmabey/pyLDAvis/blob/master/notebooks/Gensim%20Newsgroup.ipynb
See
------
See `pyLDAvis.prepare` for **kwargs.
"""
# we use sklearn's multi-dimensional scaling as the default measure to approximate distance between topics
# should be a slightly more stable implementation compared to skbio's PCoA
if 'mds' not in kwargs:
kwargs['mds'] = js_MDS
opts = fp.merge(_extract_data(topic_model, corpus, dictionary, doc_topic_dist), kwargs)
return vis_prepare(**opts)
def prepare(corpus, dictionary, doc_topic_file, topic_term_file, **kwargs):
"""Transforms the Mahout LDA and related corpus and dictionary into
the data structures needed for the visualization.
Parameters
----------
corpus : array-like list of bag of word docs in tuple form or scipy CSC matrix
The corpus in bag of word form, the same docs used to train the model.
The corpus is transformed into a csc matrix internally, if you intend to
call prepare multiple times it is a good idea to first call
`gensim.matutils.corpus2csc(corpus)` and pass in the csc matrix instead.
For example: [(50, 3), (63, 5), ....]
dictionary: gensim.corpora.Dictionary
The dictionary object used to create the corpus. Needed to extract the
actual terms (not ids).
doc_topic_file : file handle to Document topic distribution from Mahout LDA
The document topic distribution that is eventually visualised
topic_term_file : file handle to topic term distribution from Mahout LDA
The document topic distribution that is eventually visualised
**kwargs :
additional keyword arguments are passed through to :func:`pyldavis.prepare`.
Returns
-------
prepared_data : PreparedData
the data structures used in the visualization
See
------
See `pyLDAvis.prepare` for **kwargs.
"""
# we use sklearn's multi-dimensional scaling as the default measure to approximate distance between topics
# should be a slightly more stable implementation compared to skbio's PCoA
if 'mds' not in kwargs:
kwargs['mds'] = js_MDS
doc_topic_dist = get_doc_topic(doc_topic_file)
topic_term_dists = get_topic_term(topic_term_file, dictionary)
opts = fp.merge(_extract_data(corpus, dictionary, doc_topic_dist, topic_term_dists), kwargs)
return vis_prepare(**opts)
def prepare(topic_model, corpus, dictionary, doc_topic_dist=None, **kwargs):
"""Transforms the Gensim TopicModel and related corpus and dictionary into
the data structures needed for the visualization.
Parameters
----------
topic_model : gensim.models.ldamodel.LdaModel
An already trained Gensim LdaModel. The other gensim model types are
not supported (PRs welcome).
corpus : array-like list of bag of word docs in tuple form or scipy CSC matrix
The corpus in bag of word form, the same docs used to train the model.
The corpus is transformed into a csc matrix internally, if you intend to
call prepare multiple times it is a good idea to first call
`gensim.matutils.corpus2csc(corpus)` and pass in the csc matrix instead.
For example: [(50, 3), (63, 5), ....]
dictionary: gensim.corpora.Dictionary
The dictionary object used to create the corpus. Needed to extract the
actual terms (not ids).
doc_topic_dist (optional): Document topic distribution from LDA (default=None)
The document topic distribution that is eventually visualised, if you will
be calling `prepare` multiple times it's a good idea to explicitly pass in
`doc_topic_dist` as inferring this for large corpora can be quite
expensive.
**kwargs :
additional keyword arguments are passed through to :func:`pyldavis.prepare`.
Returns
-------
prepared_data : PreparedData
the data structures used in the visualization
Example
--------
For example usage please see this notebook:
http://nbviewer.ipython.org/github/bmabey/pyLDAvis/blob/master/notebooks/Gensim%20Newsgroup.ipynb
See
------
See `pyLDAvis.prepare` for **kwargs.
"""
opts = fp.merge(_extract_data(topic_model, corpus, dictionary, doc_topic_dist), kwargs)
return vis_prepare(**opts)
