数据:
https://github.com/w1449550206/Spelling-checker-based-on-Python
代码:
import re, collections
#查找每一个单词,返回一个列表
def words(text): return re.findall('[a-z]+', text.lower())
def train(features):
#为字典提供默认的值
model = collections.defaultdict(lambda: 1)
for f in features:
#将每一个单词都转变为键 默认值都为一
model[f] += 1
return model
NWORDS = train(words(open('big.txt').read()))
alphabet = 'abcdefghijklmnopqrstuvwxyz'
def edits1(word):
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 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=lambda w: NWORDS[w])
尝试:
#appl #appla #learw #tess #morw
correct('wolrd')