acc = TestAccuracy(semisup_classifier, classA_test, classB_test, thresh)
print 'accuracy {0}'.format(acc)
segfun = semisup_classifier.segfun
with open("../models/init_nonum_semi%i.pkl" % (iter_num + 1), 'w') as f:
semisup_classifier.segfun = None
cPickle.dump(semisup_classifier, f)
semisup_classifier.segfun = segfun
return semisup_classifier
if __name__ == '__main__':
target = 'gender'
whereclause = "where gender is not ''" if target == 'gender' else ''
model = segmenter.load_model('../models/idmorphs_naworl.model')
segfun = segmenter.morph_segmenter(model, match='[a-z]+')
# model_semi = segmenter.load_model('../models/idmorphs.model')
# segfun_semi = segmenter.morph_segmenter(model_semi, match='[a-z]+')
users = segmenter.get_users_from_db(whereclause=whereclause)
male_ids = [user.id for user in users if user.gender == 'M']
female_ids = [user.id for user in users if user.gender == 'F']
# unlabeled_users = segmenter.get_users_from_db(tablename='naver')
# unknown_ids = [user.id for user in unlabeled_users]
unknown_ids = None
cls = DoTest(male_ids, female_ids, segfun, unknown_ids, balance=False)
# cls = cPickle.load(open("../models/init_nonum_semi3.pkl"))
__author__ = 'hee'
import pytagcloud
import segmenter
if __name__ == '__main__':
# model_path = "../models/idmorphs_naworl.model"
model_path = "../models/okcupid.model"
model = segmenter.load_model(model_path)
top_morphs = segmenter.top_morphs(model, 100, exclude_number=True, min_length=2)
tags = pytagcloud.make_tags(top_morphs, maxsize=130)
print "here"
pytagcloud.create_tag_image(tags, "../results/okcupid.bmp", size=(900, 600), rectangular=False)