【机器学习】贝叶斯拼写检查

非原创，自用

import re, collections

#提文本中的单词
def words(text):
    return re.findall('[a-z]+',text.lower())

#统计每个单词出现次数
def train(features):
    model = collections.defaultdict(lambda :1)
    for f in features:
        model[f]+=1
    return model

#测试文本
test_txt = '用于训练的文本段'
alphabet = 'abcdefghijklmnopqrstuvwxyz'

#返回所有与单词w编辑距离为1的集合
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)

#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的词中间，只把那些正确的词作为候选词 
def edits2(word):
    return set(e2 for e1 in edits1(word) for e2 in edits1(e1))

NWORDS = train(words(test_txt))
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)非空，candidate就会选取这个集合，而不继续计算后面的编辑距离为其他的集合
def correct(word):
    candidates = known([word]) or known(edits1(word)) or known_edits2(word) or [word]
    return max(candidates, key=NWORDS.get)
correct('你想打的单词')