def get(self, key):
if not self.handled:
self.handled = True
tmp, self.d = good_turing.main(self.d)
self.none = tmp
self.total = sum(self.d.values())+0.0
if not self.exists(key):
return False, self.none
return True, self.d[key]
def get(self, key):
if not self.handled:
self.handled = True
tmp, self.d = good_turing.main(self.d)
self.none = tmp
self.total = sum(self.d.values()) + 0.0
if not self.exists(key):
return False, self.none
return True, self.d[key]
def init(filename='SogouLabDic.dic'):
global d
with open(filename, 'r') as handle:
for line in handle:
word, freq = line.split('\t')[0:2]
try:
d[word.decode('gbk')] = int(freq)+1
except:
d[word] = int(freq)+1
tmp, d = good_turing.main(d)
d['_none_'] = tmp