def train_batch_dbow(model,
docs, 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,
batch_size=100):
#print 'train_batch_dbow'
batch_count=0
train_x0=[[0]]*batch_size
train_x1=[[0]]*batch_size
train_y=[[0]]*batch_size
while 1:
for doc in docs:
for doctag_index in doc.tags:
for word in doc.words:
xy=train_sg_pair(model, word, doctag_index, alpha, learn_vectors=learn_doctags,
learn_hidden=learn_hidden, context_vectors=doctag_vectors,
context_locks=doctag_locks)
if xy !=None:
(x0,x1,y)=xy
#print xy
train_x0[batch_count]=[x0]
train_x1[batch_count]=x1
train_y[batch_count]=y
batch_count += 1
if batch_count >= batch_size :
yield { 'index':np.array(train_x0), 'point':np.array(train_x1), 'code':np.array(train_y)}
batch_count=0
def train_batch_dbow(model, docs, sub_batch_size=256, batch_size=256):
batch_count = 0
sub_batch_count = 0
train_x0 = np.zeros((batch_size, sub_batch_size), dtype='int32')
train_x1 = np.zeros((batch_size, sub_batch_size), dtype='int32')
train_y = np.zeros((batch_size, sub_batch_size), dtype='int8')
while 1:
for doc in docs:
for doctag_index in doc.tags:
for word in doc.words:
xy_gen = train_sg_pair(
model,
word,
doctag_index,
)
for xy in xy_gen:
if xy != None:
(x0, x1, y) = xy
train_x0[batch_count][sub_batch_count] = x0
train_x1[batch_count][sub_batch_count] = x1
train_y[batch_count][sub_batch_count] = y
sub_batch_count += 1
if sub_batch_count >= sub_batch_size:
batch_count += 1
sub_batch_count = 0
if batch_count >= batch_size:
yield {
'index': train_x0,
'point': train_x1,
'code': train_y
}
batch_count = 0
def train_batch_dbow(model,
docs,
sub_batch_size=256,batch_size=256
):
batch_count=0
sub_batch_count=0
train_x0 =np.zeros((batch_size,sub_batch_size),dtype='int32')
train_x1 =np.zeros((batch_size,sub_batch_size),dtype='int32')
train_y =np.zeros((batch_size,sub_batch_size),dtype='int8')
while 1:
for doc in docs:
for doctag_index in doc.tags:
for word in doc.words:
xy_gen=train_sg_pair(model, word, doctag_index,)
for xy in xy_gen :
if xy !=None:
(x0,x1,y)=xy
train_x0[batch_count][sub_batch_count]=x0
train_x1[batch_count][sub_batch_count]=x1
train_y[batch_count][sub_batch_count]=y
sub_batch_count += 1
if sub_batch_count >= sub_batch_size :
batch_count += 1
sub_batch_count=0
if batch_count >= batch_size :
yield { 'index':train_x0, 'point':train_x1, 'code':train_y}
batch_count=0
def train_batch_score_sg(model, scored_word_sentences,
score_vector_size,
alpha=None, work=None,
sub_batch_size=256,
batch_size=256):
batch_count=0
sub_batch_count=0
train_x0 =np.zeros((batch_size,sub_batch_size),dtype='int32')
train_x1 =np.zeros((batch_size,sub_batch_size),dtype='int32')
train_y0 =np.zeros((batch_size,sub_batch_size),dtype='int8')
train_y1 =np.zeros((batch_size,sub_batch_size,score_vector_size),dtype='float32')
# train_x0=[[0]]*batch_size
# train_x1=[[0]]*batch_size
# train_y0=[[0]]*batch_size
# train_y1=[[0]]*batch_size
while 1:
for scored_word_sentence in scored_word_sentences:
#sentence=[scored_word2word(scored_word) for scored_word in scored_word_sentence]
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(word_vocabs):
reduced_window = model.random.randint(model.window) # `b` in the original word2vec code
word=scored_word2word(scored_word)
# now go over all words from the (reduced) window, predicting each one in turn
start = max(0, pos - model.window + reduced_window)
for pos2, scored_word2 in enumerate(word_vocabs[start:(pos + model.window + 1 - reduced_window)], start):
word2=scored_word2word(scored_word2)
# don't train on the `word` itself
if pos2 != pos:
xy_gen=train_sg_pair(model, model.index2word[word.index], word2.index) #, alpha)
for xy in xy_gen :
if xy !=None:
(x0,x1,y0)=xy
y1=scored_word2score(scored_word)
train_x0[batch_count][sub_batch_count]=x0
train_x1[batch_count][sub_batch_count]=x1
train_y0[batch_count][sub_batch_count]=y0
train_y1[batch_count][sub_batch_count]=y1
sub_batch_count += 1
if sub_batch_count >= sub_batch_size :
batch_count += 1
sub_batch_count=0
if batch_count >= batch_size :
yield { 'index':train_x0, 'point':train_x1, 'code':train_y0,'score':train_y1}
batch_count=0
def train_batch_score_sg(model, scored_word_sentences, alpha=None, work=None,batch_size=100):
batch_count=0
train_x0=[[0]]*batch_size
train_x1=[[0]]*batch_size
train_y0=[[0]]*batch_size
train_y1=[[0]]*batch_size
while 1:
for scored_word_sentence in scored_word_sentences:
#sentence=[scored_word2word(scored_word) for scored_word in scored_word_sentence]
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(word_vocabs):
reduced_window = model.random.randint(model.window) # `b` in the original word2vec code
word=scored_word2word(scored_word)
# now go over all words from the (reduced) window, predicting each one in turn
start = max(0, pos - model.window + reduced_window)
for pos2, scored_word2 in enumerate(word_vocabs[start:(pos + model.window + 1 - reduced_window)], start):
word2=scored_word2word(scored_word2)
# don't train on the `word` itself
if pos2 != pos:
xy=train_sg_pair(model, model.index2word[word.index], word2.index, alpha)
if xy !=None:
(x0,x1,y0)=xy
y1=scored_word2score(scored_word)
train_x0[batch_count]=[x0]
train_x1[batch_count]=x1
train_y0[batch_count]=y0
train_y1[batch_count]=y1
#print train_x0,train_y1,
batch_count += 1
if batch_count >= batch_size :
#print { 'index':np.array(train_x0), 'point':np.array(train_x1), 'code':np.array(train_y0),'score':np.array(train_y1)}
#yield { 'index':np.array(train_x0), 'point':np.array(train_x1), 'code':np.array(train_y0),'score':np.array(train_y1,dtype=float32)}
yield { 'index':np.array(train_x0), 'point':np.array(train_x1), 'code':np.array(train_y0),'score':np.array(train_y1)}
batch_count=0
def train_batch_score_sg(model,
scored_word_sentences,
score_vector_size,
alpha=None,
work=None,
sub_batch_size=256,
batch_size=256):
batch_count = 0
sub_batch_count = 0
train_x0 = np.zeros((batch_size, sub_batch_size), dtype='int32')
train_x1 = np.zeros((batch_size, sub_batch_size), dtype='int32')
train_y0 = np.zeros((batch_size, sub_batch_size), dtype='int8')
train_y1 = np.zeros((batch_size, sub_batch_size, score_vector_size),
dtype='float32')
# train_x0=[[0]]*batch_size
# train_x1=[[0]]*batch_size
# train_y0=[[0]]*batch_size
# train_y1=[[0]]*batch_size
while 1:
for scored_word_sentence in scored_word_sentences:
#sentence=[scored_word2word(scored_word) for scored_word in scored_word_sentence]
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(word_vocabs):
reduced_window = model.random.randint(
model.window) # `b` in the original word2vec code
word = scored_word2word(scored_word)
# now go over all words from the (reduced) window, predicting each one in turn
start = max(0, pos - model.window + reduced_window)
for pos2, scored_word2 in enumerate(
word_vocabs[start:(pos + model.window + 1 -
reduced_window)], start):
word2 = scored_word2word(scored_word2)
# don't train on the `word` itself
if pos2 != pos:
xy_gen = train_sg_pair(model,
model.index2word[word.index],
word2.index) #, alpha)
for xy in xy_gen:
if xy != None:
(x0, x1, y0) = xy
y1 = scored_word2score(scored_word)
train_x0[batch_count][sub_batch_count] = x0
train_x1[batch_count][sub_batch_count] = x1
train_y0[batch_count][sub_batch_count] = y0
train_y1[batch_count][sub_batch_count] = y1
sub_batch_count += 1
if sub_batch_count >= sub_batch_size:
batch_count += 1
sub_batch_count = 0
if batch_count >= batch_size:
yield {
'index': train_x0,
'point': train_x1,
'code': train_y0,
'score': train_y1
}
batch_count = 0