def add_new_labels(sentences, model):
"""
Add new labels (for new docs) to the doc2vec model's `self.vocab`.
from: <https://gist.github.com/zseder/4201551d7f8608f0b82b>
"""
sentence_no = -1
total_words = 0
vocab = model.vocab
#model_sentence_n = len([l for l in vocab if l.startswith("SENT")])
model_sentence_n = max(int(l.split('_')[-1]) for l in vocab if l.startswith("SENT"))
n_sentences = 0
for sentence_no, sentence in enumerate(sentences):
sentence_length = len(sentence.words)
for label in sentence.labels:
label_e = label.split("_")
label_n = int(label_e[1]) + model_sentence_n
label = "{0}_{1}".format(label_e[0], label_n)
total_words += 1
if label in vocab:
vocab[label].count += sentence_length
else:
vocab[label] = Vocab(count=sentence_length)
vocab[label].index = len(model.vocab) - 1
vocab[label].code = [0]
vocab[label].sample_probability = 1.
model.index2word.append(label)
n_sentences += 1
return n_sentences
