output_file = codecs.open("data/doc_vec.txt", 'wb', encoding='utf-8')
pg.pg_init()
# 将教育经历的两个属性合并
'''for ele in segment.seg(pg.get_edu()):
print len(ele)'''
# 测试
'''for mlist in segment.seg(pg.get_edu()):
for ele in mlist:
for x in ele:
output_file.write(x+' ')
output_file.write('\t||\t')
output_file.write('\n')
'''
raw = list()
people = pg.get_edu(0, 0)
raw = map(lambda x: x[0] + x[1], segment.seg(people))
topic_model.build_lsi(raw)
'''topic_model._build_corpus(raw)
tfidf = topic_model._build_tfidf()
corpus_tfidf = tfidf[topic_model.corpus]
for ele in corpus_tfidf:
print ele
'''
'''for ele in topic_model.dictionary.token2id:
from __future__ import absolute_import
import codecs
import segment
import pg
output_file = codecs.open("data/seg_data1.txt", 'wb', encoding='utf-8')
pg.pg_init()
# print segment.seg(pg.get_edu())
bias = 1000
counter = 0
raw = '1'
while len(raw) != 0:
raw = pg.get_edu(bias, counter)
for mlist in segment.seg(raw):
for ele in mlist:
for x in ele:
output_file.write(x+' ')
output_file.write('\t')
output_file.write('\n')
counter += 1
'''raw = pg.get_edu(bias, counter)
for mlist in segment.seg(raw):
for ele in mlist:
for x in ele:
output_file.write(x+' ')
output_file.write('\t||\t')
output_file.write('\n')'''