def __init__(self, dict, model_source, tag_source):
utils.jieba_add_dict(dict)
self.tag_repo = []
self.tags_repo = []
for line in open(tag_source):
self.tags_repo.append(line)
self.model = gensim.models.Word2Vec.load(model_source)
def __init__(self,dict,model_source,tag_source):
utils.jieba_add_dict(dict)
self.tag_repo=[]
self.tags_repo=[]
for line in open(tag_source):
self.tags_repo.append(line)
self.model = gensim.models.Word2Vec.load(model_source)
def train_word_vector(source,dict,wordvec):
utils.jieba_add_dict(dict)
comments_df = DataFrame.from_csv(source,sep = '\t')
document = []
for line in comments_df['comment'].values:
line = utils.remove_punctuation(line)
cutted_line = jieba.cut(line)
document.append(list(cutted_line))
model = gensim.models.Word2Vec(document)
print 'saving word vector model'
model.save(wordvec)
return model
def train_word_vector(source, dict, wordvec):
utils.jieba_add_dict(dict)
comments_df = DataFrame.from_csv(source, sep='\t')
document = []
for line in comments_df['comment'].values:
line = utils.remove_punctuation(line)
cutted_line = jieba.cut(line)
document.append(list(cutted_line))
model = gensim.models.Word2Vec(document)
print 'saving word vector model'
model.save(wordvec)
return model
