def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None,
train_words=False, learn_doctags=True, learn_words=True, learn_hidden=True,
word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None):
"""
Update distributed bag of words model ("PV-DBOW") by training on a single document.
Called internally from `Doc2Vec.train()` and `Doc2Vec.infer_vector()`.
The document is provided as `doc_words`, a list of word tokens which are looked up
in the model's vocab dictionary, and `doctag_indexes`, which provide indexes
into the doctag_vectors array.
If `train_words` is True, simultaneously train word-to-word (not just doc-to-word)
examples, exactly as per Word2Vec skip-gram training. (Without this option,
word vectors are neither consulted nor updated during DBOW doc vector training.)
Any of `learn_doctags', `learn_words`, and `learn_hidden` may be set False to
prevent learning-updates to those respective model weights, as if using the
(partially-)frozen model to infer other compatible vectors.
This is the non-optimized, Python version. If you have cython installed, gensim
will use the optimized version from doc2vec_inner instead.
"""
if doctag_vectors is None:
doctag_vectors = model.docvecs.doctag_syn0
if doctag_locks is None:
doctag_locks = model.docvecs.doctag_syn0_lockf
if train_words and learn_words:
train_batch_sg(model, [doc_words], alpha, work)
for doctag_index in doctag_indexes:
for word in doc_words:
train_sg_pair(
model, word, doctag_index, alpha, learn_vectors=learn_doctags, learn_hidden=learn_hidden,
context_vectors=doctag_vectors, context_locks=doctag_locks
)
return len(doc_words)
def train_document_dbow(model, doc_words, doctag_indexes, alpha, work=None,
train_words=False, learn_doctags=True, learn_words=True, learn_hidden=True,
word_vectors=None, word_locks=None, doctag_vectors=None, doctag_locks=None):
"""
Update distributed bag of words model ("PV-DBOW") by training on a single document.
Called internally from `Doc2Vec.train()` and `Doc2Vec.infer_vector()`.
The document is provided as `doc_words`, a list of word tokens which are looked up
in the model's vocab dictionary, and `doctag_indexes`, which provide indexes
into the doctag_vectors array.
If `train_words` is True, simultaneously train word-to-word (not just doc-to-word)
examples, exactly as per Word2Vec skip-gram training. (Without this option,
word vectors are neither consulted nor updated during DBOW doc vector training.)
Any of `learn_doctags', `learn_words`, and `learn_hidden` may be set False to
prevent learning-updates to those respective model weights, as if using the
(partially-)frozen model to infer other compatible vectors.
This is the non-optimized, Python version. If you have cython installed, gensim
will use the optimized version from doc2vec_inner instead.
"""
if doctag_vectors is None:
doctag_vectors = model.docvecs.doctag_syn0
if doctag_locks is None:
doctag_locks = model.docvecs.doctag_syn0_lockf
if train_words and learn_words:
train_batch_sg(model, [doc_words], alpha, work)
for doctag_index in doctag_indexes:
for word in doc_words:
train_sg_pair(
model, word, doctag_index, alpha, learn_vectors=learn_doctags, learn_hidden=learn_hidden,
context_vectors=doctag_vectors, context_locks=doctag_locks
)
return len(doc_words)
