Doc2Vec Iterator

DocIterator.py

from gensim.models.doc2vec import LabeledSentence
import re

class DocIterator(object):
    def __init__(self, doc_list, labels_list):
       self.labels_list = labels_list
       self.doc_list = doc_list
       
    def __iter__(self):
        for idx, doc in enumerate(self.doc_list):
            yield LabeledSentence(words=doc.split(),tags=[self.labels_list[idx]])