(Python re+collections)实现贝叶斯单词检查器

# -*-encoding:utf-8-*-
import re,collections
# 把语料库中的单词全部抽取出来，转成小写，并去除单词中间的特殊符号
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(open(r'C:\Users\86156\Desktop\nlp\big.txt').read()))
alphabet = 'abcdefghijklmnnopqrstuvwxyz'
# 返回所有与单词w编辑距离为1的集合
def edits1(word):
    n = len(word)
    return set([word[0:i]+word[i+1:] for i in range(n)]+
              [word[0:i]+word[i+1]+word[i]+word[i+2:] for i in range(n-1)]+
              [word[0:i]+c+word[i+1:] for i in range(n) for c in alphabet]+
              [word[0:i]+c+word[i:] for i in range(n+1) for c in alphabet])
# 返回所有与单词w编辑距离为2的集合
# 在这些编辑距离小于2的词中词，只把那些正确的词作为候选词
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)
# 如果known(set)得空，candidate就会选取这个集合，而不继续计算后面的
def correct(word):
    candidates = known([word]) or known(edits1(word)) or known_edits2(word) or [word]
    return max(candidates,key=lambda w:NWORDS[w])
print(correct('likr'))

敬请指正！