基于贝叶斯算法的单词拼写检测

首先从一个有很多词的文本中，构建词库字典，操作拼写单词（只改变一到两个字母），找到在文本中出现概率最大的

import collections
import re


f = open("big.txt","r")
text = f.read()


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


def train(features):
    """建立一个字典结构，文本库中每一个词，都是字典的键
       字典的值就是单词出现的频率
    """
    model = collections.defaultdict(lambda: 1)
    for f in features:
        model[f] += 1
    return model

NWORDS = train(words(text))
f.close()


def edits1(word):
    """改变单词"""

    # 字母集
    alphabet = 'abcdefghijklmnopqrstuvwxyz'

    # 返回所有将单词分成两半元组列表
    splits = [(word[:i], word[i:]) for i in range(len(word) + 1)]
    # 返回所有删去一个单词后的列表
    deletes = [a + b[1:] for a, b in splits if b]  # a,b 在元组中
    # 交换相邻两个字母的列表
    transpose = [a + b[1] + b[0] +b[2:] for a,b in splits if len(b)>1]
    # 将word每一位替换成其他25个字母，形成新的单词
    replaces = [a + c + b[1:] for a,b in splits for c in alphabet if b]
    # 将word中插入一个字母，形成新的单词
    inserts = [a + c + b for a, b in splits for c in alphabet]

    # 返回一个集合,这里用到了列表拼接
    return set(deletes + transpose + replaces + inserts)


def known_edits(word):
    """用了两次edits,生成相差两个字母的词的集合"""
    return set(e2 for e1 in edits1(word) for e2 in edits1(e1) if e2 in NWORDS)


def known(words):
    """返回集合中所有在文本中出现过单词的子集"""
    return set(w for w in words if w in NWORDS)


def correct(word):
    """返回改正后出现率在高的单词"""
    candidates = known([word]) or known(edits1(word)) or known_edits(word) or [word]
    return max(candidates, key=NWORDS.get)

if __name__ == '__main__':
    print(correct('speling'))