Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

NamedVectors refactor for word2vec #819

Closed
wants to merge 4 commits into from
Closed

NamedVectors refactor for word2vec #819

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
d60f1c4
namedvecs
Aug 9, 2016
628c15b
add __contains__ to namedvecs
Aug 9, 2016
8717189
test
Aug 9, 2016
1d59b8e
Merge pull request #1 from droudy/tf2
droudy Aug 9, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions gensim/models/doc2vec.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,16 +130,16 @@ def train_document_dm(model, doc_words, doctag_indexes, alpha, work=None, neu1=N

"""
if word_vectors is None:
word_vectors = model.syn0
word_vectors = model.named_vectors.syn0
if word_locks is None:
word_locks = model.syn0_lockf
if doctag_vectors is None:
doctag_vectors = model.docvecs.doctag_syn0
if doctag_locks is None:
doctag_locks = model.docvecs.doctag_syn0_lockf

word_vocabs = [model.vocab[w] for w in doc_words if w in model.vocab and
model.vocab[w].sample_int > model.random.rand() * 2**32]
word_vocabs = [model.named_vectors.vocab[w] for w in doc_words if w in model.named_vectors.vocab and
model.named_vectors.vocab[w].sample_int > model.random.rand() * 2**32]

for pos, word in enumerate(word_vocabs):
reduced_window = model.random.randint(model.window) # `b` in the original doc2vec code
Expand Down Expand Up @@ -185,21 +185,21 @@ def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None,

"""
if word_vectors is None:
word_vectors = model.syn0
word_vectors = model.named_vectors.syn0
if word_locks is None:
word_locks = model.syn0_lockf
if doctag_vectors is None:
doctag_vectors = model.docvecs.doctag_syn0
if doctag_locks is None:
doctag_locks = model.docvecs.doctag_syn0_lockf

word_vocabs = [model.vocab[w] for w in doc_words if w in model.vocab and
model.vocab[w].sample_int > model.random.rand() * 2**32]
word_vocabs = [model.named_vectors.vocab[w] for w in doc_words if w in model.named_vectors.vocab and
model.named_vectors.vocab[w].sample_int > model.random.rand() * 2**32]
doctag_len = len(doctag_indexes)
if doctag_len != model.dm_tag_count:
return 0 # skip doc without expected number of doctag(s) (TODO: warn/pad?)

null_word = model.vocab['\0']
null_word = model.named_vectors.vocab['\0']
pre_pad_count = model.window
post_pad_count = model.window
padded_document_indexes = (
Expand All @@ -214,7 +214,7 @@ def train_document_dm_concat(model, doc_words, doctag_indexes, alpha, work=None,
+ padded_document_indexes[(pos + 1):(pos + 1 + post_pad_count)] # following words
)
word_context_len = len(word_context_indexes)
predict_word = model.vocab[model.index2word[padded_document_indexes[pos]]]
predict_word = model.named_vectors.vocab[model.named_vectors.index2word[padded_document_indexes[pos]]]
# numpy advanced-indexing copies; concatenate, flatten to 1d
l1 = concatenate((doctag_vectors[doctag_indexes], word_vectors[word_context_indexes])).ravel()
neu1e = train_cbow_pair(model, predict_word, None, l1, alpha,
Expand Down
Loading