贝叶斯实现单词纠错----代码篇

今天承接上一篇，手写单词纠错

需要准备语料库- -

代码

'''贝叶斯要解决的问题是  逆概 问题'''
import re,collections
import pandas as pd
txt = ''
csv = 'frequency.csv'
# 获取文本中的英文单词 (作为先验概率的数据) 单词方案1 统计文章中出现的单词的频率
def words(test): return re.findall('[a-z]+', test.lower())
# def train(features):
#     mode1 = collections.defaultdict(lambda :1)
#     for f in features:
#         mode1[f] += 1
#     return mode1
# ---------------------------------------------------------------------------

# 单词方案2 加载词频文本
def train(csv):
    model = collections.defaultdict(lambda :1)
    data = pd.read_csv(csv,header=None,names=['words'],encoding='utf-8')
    for w in range(1,len(data)+1):
        model[data['words'][w-1]] = w
    # print(model)
    return model
#NWORDS = train(words(open(txt).read()))
NWORDS = train(csv)
alphabet = 'abcdefghijklmnopqrstuvwxyz'

# 编辑距离
# 返回所有与单词w编辑距离为1的集合
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) for c in alphabet]       # insetion
    )

# 编辑距离为2
def edits2(word):
    return set(e2 for e1 in edits1(word) for e2 in edits1(e1))

def know(words):
    return set(w for w in words if w in NWORDS)

# 如果know(set) 非空， candidate 就会选择这个集合，而不会继续计算后面的
def correct(word):
    candidate = know([word]) or know(edits1(word)) or know(edits2(word)) or [word]
    return max(candidate, key=lambda  w : NWORDS[w])

while True:
    a = input("请输入一个单词：")
    print('你可能想输入的单词是 ：{}'.format(correct(a)))
    print('-'*20)

需要语料库的下方发邮箱。。。

（来不及解释代码了，快上车。。。。又水一篇，下周解释）