朴素贝叶斯思想的拼写检查器_朴素贝叶斯拼写检查

#encoding=utf-8
import re,collections

#把语料中的单词都抽取出来，变成小写a-z，去掉特殊符号
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('wor.txt').read()))

alphabet='abcdefghijklmnopqrstuvwxyz'

def editsl(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])

def known_edits2(word):
    return set(e2 for e1 in editsl(word)   for e2 in editsl(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(editsl(word)) or known_edits2(word) or [word]
    return max(candidates,key=lambda w:NWORDS[w])

import torch
print(torch.cuda.is_available())
print(correct('mor'))



1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40