朴素贝叶斯(垃圾邮件分类)

邮箱训练集下载地址

  邮件训练集下载地址https://pan.baidu.com/s/1uwDJJeJAr-DX82XlCRGR9Q

模块导入

import re
import os
from jieba import cut
from itertools import chain
from collections import Counter
import numpy as np
from sklearn.naive_bayes import MultinomialNB

文本预处理

def get_words(filename):
    """读取文本并过滤无效字符和长度为1的词"""
    words = []
    with open(filename, 'r', encoding='utf-8') as fr:
        for line in fr:
            line = line.strip()
            # 过滤无效字符
            line = re.sub(r'[.【】0-9、——。，！~\*]', '', line)
            # 使用jieba.cut()方法对文本切词处理
            line = cut(line)
            # 过滤长度为1的词
            line = filter(lambda word: len(word) > 1, line)
            words.extend(line)

    return words

遍历邮件