代码思想很好理解
- 首先读取并处理文件文件(全部小写),并将其转化成字典的格式(NWORDS)。单词为键 出现的次数为值
- 通过input输入需要判断的单词,并调用correct
- 在crrect中,判断四种情:
1.(known)是否是NWORDS中的单词,如不满足到2
2.(known(edits1(word)))经过补充,缺失,转换 后的单词是否属于NWORDS,如不满足到3
3.(known_edits2(word)再重复2的操作,如果还不满足那么到4
4.([word])将这个单词返回- 将返回的set对象中的值从字典中取出,比较出现次数的大小。然后返回次数最多的单词
数据集下载地址
import re, collections
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
def edits1(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 edits1(word) for e2 in edits1(e1) if e2 in NWORDS)
def known(words):
x = set(w for w in words if w in NWORDS)
for w in words:
print(w)
return x
def correct(word):
candidates = known([word]) or known(edits1(word)) or known_edits2(word) or [word]
# print(known([word]),'1', known(edits1(word)), known_edits2(word))
return max(candidates, key=lambda w: NWORDS[w])
if __name__ == "__main__":
NWORDS = train(words(open('big.txt').read()))
alphabet = 'abcdefghijklmnopqrstuvwxy'
while True:
str1 = input('请输入要书写的单词')
print(correct(str1))