错误单词的纠正实例 朴素的贝叶斯算法

#-*- coding:utf-8 -*-
import re
import collections

def words(text):
    return re.findall('[a-z]+',text.lower())#筛选

def train(features):
    model=collections.defaultdict(lambda :1)#model里面没有存在的词默认都返回1
    for f in features:#打印出每个单词出现的次数
        model[f]+=1
    return model
nw=train(words(open(r'E:\python人工智能\tb机器学习\01丶机器学习\唐宇迪-机器学习课程\机器学习算法配套案例实战\贝叶斯-拼写检查器\big.txt').read()))
alphabet = 'abcdefghijklmnopqrstuvwxyz'
#print(nw)
def editsl(word):#对输入的单词进行删除 替换 交换 已经插入
    n=len(word)
    return set([word[0:i] + word[i + 1:] for i in range(n)] +  # deletion
               [word[0:i] + word[i + 1] + word[i] + word[i + 2:] for i in range(n - 1)] +  # transposition
               [word[0:i] + c + word[i + 1:] for i in range(n) for c in alphabet] +  # alteration
               [word[0:i] + c + word[i:] for i in range(n + 1) for c in alphabet])  # insertion
def edits2(word):
    return set(e2 for el in editsl(word) for e2 in editsl(el))#返回那些距离为2的正确的拼写的单词

def known(words):#判断该单词是不是在该文件中 如果在返回出来
    return set(w for w in words if w in nw)#

def corret(word):
    candidats=known([word]) or known(editsl(word))or edits2(word)or [word]
    return max(candidats,key=lambda w:nw[w])
c=corret("lovv")#这里是程序入口
print(c)