贝叶斯拼写检查器

本拼写检查器是基于朴素贝叶斯的基础来写的，贝叶斯公式以及原理就不在详述。直接上代码

 

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

alphabet = 'abcdefghijklmnopqrstuvwxyz'
NWORDS = train(words(open('D:/big.txt').read()))


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]
    )

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):
    cindidates = known([word]) or known(edits1(word)) or known_edits2(word) or [word]
    return max(cindidates, key=lambda w: NWORDS[w])

print(correct('tess'))

以我现在的水平，现在看贝叶斯的原理还是懂的，但是编辑距离还不是很懂，以后慢慢变懂