Code
def train_batch_cbow(model, sentences, alpha, work=None, neu1=None):
"""
Update CBOW model by training on a sequence of sentences.
Each sentence is a list of string tokens, which are looked up in the model's
vocab dictionary. Called internally from `Word2Vec.train()`.
This is the non-optimized, Python version. If you have cython installed, gensim
will use the optimized version from word2vec_inner instead.
"""
result = 0
for sentence in sentences:
word_vocabs = [model.wv.vocab[w] for w in sentence 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 word2vec code
start = max(0, pos - model.window + reduced_window)
window_pos = enumerate(word_vocabs[start:(pos + model.window + 1 - reduced_window)], start)
word2_indices = [word2.index for pos2, word2 in window_pos if (word2 is not None and pos2 != pos)]
l1 = np_sum(model.wv.syn0[word2_indices], axis=0) # 1 x vector_size
if word2_indices and model.cbow_mean:
l1 /= len(word2_indices)
train_cbow_pair(model, word, word2_indices, l1, alpha)
result += len(word_vocabs)
return result