21行代码拼音检测
原理:
基于贝叶斯来实现计算,理论依据:
相关论文显示,80-95%的拼写错误跟想要拼写的单词都只有1个编辑距离,如果觉得一次编辑不够,那再来一次计算
import re, collections
def words(text): return re.findall('[a-z]+', text.lower())
def train(features):
model = collections.defaultdict(lambda: 1)
for f in features:
model[f] += 1
return model
NWORDS = train(words(file('big.txt').read()))
alphabet = 'abcdefghijklmnopqrstuvwxyz'
def edits1(word):
splits = [(word[:i], word[i:]) for i in range(len(word) + 1)]
deletes = [a + b[1:] for a, b in splits if b]
transposes = [a + b[1] + b[0] + b[2:] for a, b in splits if len(b)>1]
replaces = [a + c + b[1:] for a, b in splits for c in alphabet if b]
inserts = [a + c + b for a, b in splits for c in alphabet]
return set(deletes + transposes + replaces + inserts)
def known_edits2(word):
return set(e2 for e1 in edits1(word) for e2 in edits1(e1) if e2 in NWORDS)
def known(words): return set(w for w in words if w in NWORDS)
def correct(word):
candidates = known([word]) or known(edits1(word)) or known_edits2(word) or [word]
return max(candidates, key=NWORDS.get)
原文
http://blog.csdn.net/Pwiling/article/details/50573650
http://norvig.com/spell-correct.html