def train_document_dm_concat_xy_generator(model, docs):
for doc in docs:
indexed_doctags = model.docvecs.indexed_doctags(doc.tags)
doctag_indexes, doctag_vectors, doctag_locks, ignored = indexed_doctags
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]
#doctag_len = len(doctag_indexes)
#if doctag_len != model.dm_tag_count:
null_word = model.vocab['\0']
pre_pad_count = model.window
post_pad_count = model.window
padded_document_indexes = (
(pre_pad_count * [null_word.index]) # pre-padding
+ [word.index for word in word_vocabs if word is not None] # elide out-of-Vocabulary words
+ (post_pad_count * [null_word.index]) # post-padding
)
for pos in range(pre_pad_count, len(padded_document_indexes) - post_pad_count):
word_context_indexes = (
padded_document_indexes[(pos - pre_pad_count): pos] # preceding words
+ padded_document_indexes[(pos + 1):(pos + 1 + post_pad_count)] # following words
)
#word_context_len = len(word_context_indexes)
#print word_context_len
predict_word = model.vocab[model.index2word[padded_document_indexes[pos]]]
xy = train_cbow_pair(model, predict_word, word_context_indexes)
x2=doctag_indexes
xy1=[xy[0],x2,xy[1],xy[2]]
yield xy1
def train_batch_dm_xy_generator(model, docs):
for doc in docs:
indexed_doctags = model.docvecs.indexed_doctags(doc.tags)
doctag_indexes, doctag_vectors, doctag_locks, ignored = indexed_doctags
word_vocabs = [
model.wv.vocab[w] for w in doc.words if w in model.wv.vocab
and model.wv.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
start = max(0, pos - model.window + reduced_window)
window_pos = enumerate(
word_vocabs[start:(pos + model.window + 1 - reduced_window)],
start)
word2_indexes = [
word2.index for pos2, word2 in window_pos if pos2 != pos
]
xy_gen = train_cbow_pair(model, word, word2_indexes)
x2 = doctag_indexes
for xy in xy_gen:
if xy != None:
yield [xy[0], x2, xy[1], xy[2]]
def train_document_dm_concat_xy_generator(model, docs):
for doc in docs:
indexed_doctags = model.docvecs.indexed_doctags(doc.tags)
doctag_indexes, doctag_vectors, doctag_locks, ignored = indexed_doctags
word_vocabs = [
model.wv.vocab[w] for w in doc.words if w in model.wv.vocab
and model.wv.vocab[w].sample_int > model.random.rand() * 2**32
]
null_word = model.wv.vocab['\0']
pre_pad_count = model.window
post_pad_count = model.window
padded_document_indexes = (
(pre_pad_count * [null_word.index]) # pre-padding
+ [word.index for word in word_vocabs if word is not None
] # elide out-of-Vocabulary words
+ (post_pad_count * [null_word.index]) # post-padding
)
for pos in range(pre_pad_count,
len(padded_document_indexes) - post_pad_count):
word_context_indexes = (
padded_document_indexes[(pos -
pre_pad_count):pos] # preceding words
+ padded_document_indexes[
(pos + 1):(pos + 1 + post_pad_count)] # following words
)
predict_word = model.wv.vocab[model.index2word[
padded_document_indexes[pos]]]
xy_gen = train_cbow_pair(model, predict_word, word_context_indexes)
for xy in xy_gen:
if xy != None:
x2 = doctag_indexes
xy1 = [xy[0], x2, xy[1], xy[2]]
yield xy1
def train_batch_score_cbow_xy_generator(model, scored_word_sentences):
for scored_word_sentence in scored_word_sentences:
#print scored_word_sentence
scored_word_vocabs = [
[model.vocab[w], s] for [w, s] in scored_word_sentence
if w in model.vocab
and model.vocab[w].sample_int > model.random.rand() * 2**32
]
for pos, scored_word in enumerate(scored_word_vocabs):
reduced_window = model.random.randint(
model.window) # `b` in the original word2vec code
start = max(0, pos - model.window + reduced_window)
window_pos = enumerate(
scored_word_vocabs[start:(pos + model.window + 1 -
reduced_window)], start)
word2_indices = [
scored_word2[0].index for pos2, scored_word2 in window_pos
if (scored_word2 is not None and scored_word2[0] is not None
and pos2 != pos)
]
xy_gen = train_cbow_pair(model, scored_word[0], word2_indices,
None, None)
for xy in xy_gen:
if xy != None:
xy1 = [xy[0], xy[1], xy[2], [scored_word[1]]]
yield xy1
def train_batch_dm_xy_generator(model, docs):
for doc in docs:
indexed_doctags = model.docvecs.indexed_doctags(doc.tags)
doctag_indexes, doctag_vectors, doctag_locks, ignored = indexed_doctags
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]
for pos, word in enumerate(word_vocabs):
reduced_window = model.random.randint(model.window) # `b` in the original doc2vec code
start = max(0, pos - model.window + reduced_window)
window_pos = enumerate(word_vocabs[start:(pos + model.window + 1 - reduced_window)], start)
word2_indexes = [word2.index for pos2, word2 in window_pos if pos2 != pos]
xy_gen=train_cbow_pair(model, word, word2_indexes) #, l1=None, alpha=None,learn_vectors=False, learn_hidden=learn_hidden)
xy_gen=train_cbow_pair(model, word , word2_indices , None, None)
x2=doctag_indexes
for xy in xy_gen:
if xy !=None:
yield [xy[0],x2,xy[1],xy[2]]
def train_batch_score_cbow_xy_generator(model, scored_word_sentences):
for scored_word_sentence in scored_word_sentences:
#print scored_word_sentence
scored_word_vocabs = [[model.vocab[w],s] for [w,s] in scored_word_sentence if w in model.vocab and model.vocab[w].sample_int > model.random.rand() * 2**32]
for pos, scored_word in enumerate(scored_word_vocabs):
reduced_window = model.random.randint(model.window) # `b` in the original word2vec code
start = max(0, pos - model.window + reduced_window)
window_pos = enumerate(scored_word_vocabs[start:(pos + model.window + 1 - reduced_window)], start)
word2_indices = [scored_word2[0].index for pos2, scored_word2 in window_pos if (scored_word2 is not None and scored_word2[0] is not None and pos2 != pos)]
xy=train_cbow_pair(model, scored_word[0] , word2_indices , None, None)
if xy !=None:
xy1=[xy[0],xy[1],xy[2],scored_word[1]]
yield xy1
