朴树贝叶斯分类-拼写检查

#coding=utf-8

'''
贝叶斯分类之拼写检查

原理：
    1.统计每个单词出现的概率
    2.计算输入单词与词典中正确单词的距离
    3.找到概率最大的单词


'''

import  re
import  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 = 'important information about your specific rights and restrictions'
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 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)

def correct(word):
    candidates = known([word]) or known(edits1(word)) or known_edits2(word) or [word]
    return max(candidates, key=NWORDS.get)

print correct('you')