rec = rec_set[fid]
result = calculator.calculate(lab, rec)
acc = float(result['cor'] - result['ins']) * 100.0 / result['all']
print('acc: %4.2f %%' % acc, end = ' ')
# print('acc: {acc}'.format(acc = acc*100), end = ' ')
print('N: {total}'.format(total = result['all']), end = ' ')
print('C: {correct}'.format(correct = result['cor']), end = ' ')
print('S: {substitution}'.format(substitution = result['sub']), end = ' ')
print('D: {deletion}'.format(deletion = result['del']), end = ' ')
print('I: {insertion}'.format(insertion = result['ins']))
space = {}
space['lab'] = []
space['rec'] = []
for idx in xrange(len(result['lab'])) :
len_lab = len(result['lab'][idx])
if is_chinese(result['lab'][idx]) :
len_lab = len_lab * 2
len_rec = len(result['rec'][idx])
if is_chinese(result['rec'][idx]) :
len_rec = len_rec * 2
length = max(len_lab, len_rec)
space['lab'].append(length-len_lab)
space['rec'].append(length-len_rec)
print('lab:', end = ' ')
for idx, token in enumerate(result['lab']) :
print('{token}'.format(token = token.encode('utf-8')), end = ' ')
for n in xrange(space['lab'][idx]) :
print(' ', end = '')
print()
print('rec:', end = ' ')
for idx, token in enumerate(result['rec']) :
# coding = utf-8
from Accuracy import is_chinese
import re
import sys
if __name__ == '__main__':
cluster = {}
cluster['ch'] = {}
cluster['en'] = {}
for line in sys.stdin:
line = line.decode('utf-8')
word = line[0:line.find(' ') - 1]
if is_chinese(word):
for char in word:
cluster['ch'][char] = 1
else:
cluster['en'][word] = 1
print('<English>')
for token in cluster['en']:
print(token.encode('utf-8'))
print('<Mandarin>')
for token in cluster['ch']:
print(token.encode('utf-8'))
# coding = utf-8
from Accuracy import is_chinese
import re
import sys
if __name__ == '__main__':
cluster = {}
cluster['ch'] = {}
cluster['en'] = {}
for line in sys.stdin :
line = line.decode('utf-8')
word = line[0:line.find(' ')-1]
if is_chinese(word) :
for char in word :
cluster['ch'][char] = 1
else :
cluster['en'][word] = 1
print('<English>')
for token in cluster['en'] :
print(token.encode('utf-8'))
print('<Mandarin>')
for token in cluster['ch'] :
print(token.encode('utf-8'))
