def real_test(self):
self._test_xs, self._test_ys = ST.load_data(self.test_path)
ST.replace_url(self._test_xs, fill='H')
ST.replace_target(self._test_xs, fill='T')
#x_y = [(self.discret_txt(txt), y) for txt, y in zip(self._test_xs, self._test_ys)]
test_mat = self.build_sparse_X(self._test_xs)
self.accuracy(test_mat, self._test_ys)
def test():
obj_stats_path = '../train_data/stat_obj_train_data'
out_path = '../train_data/Dg_obj_stats'
txts = []
with open(obj_stats_path, 'r') as f:
for line in f:
dic = json.loads(line.strip())
tag, txt = dic.items()[0]
txts.append(txt)
linfo('obj stats count: %s' % (len(txts)))
ST.replace_url(txts, fill='H')
ST.replace_target(txts, fill='T')
for x in txts:
dic = {'O':x}
write(out_path, 'a', '%s\n' % json.dumps(dic))
def test():
obj_stats_path = '../train_data/stat_obj_train_data'
out_path = '../train_data/Dg_obj_stats'
txts = []
with open(obj_stats_path, 'r') as f:
for line in f:
dic = json.loads(line.strip())
tag, txt = dic.items()[0]
txts.append(txt)
linfo('obj stats count: %s' % (len(txts)))
ST.replace_url(txts, fill='H')
ST.replace_target(txts, fill='T')
for x in txts:
dic = {'O': x}
write(out_path, 'a', '%s\n' % json.dumps(dic))
def train(self,cross_validation=False, fold_sz=10, test_path='../../test_data/tri_test_data'):
self._train_xs, self._train_ys = ST.load_data(self._path)
if not self._emoticon:
ST.remove_emoticon(self._train_xs)
self.gram2gid = self._discretize_gram2gid()
if cross_validation:
linfo('begin to cross train')
self._cross_train(fold_sz)
else:
classifier = self._train(self._train_xs, self._train_ys)
self._test_xs, self._test_ys = ST.load_data(test_path)
ST.replace_url(self._test_xs, fill='H')
ST.replace_target(self._test_xs, fill='T')
test_set = [(self._feature_encoding(txt), tag) for txt, tag in zip(self._test_xs, self._test_ys)]
linfo('maxent classifier precision: %.4f' % classify.accuracy(classifier, test_set))