python贝叶斯算法识别垃圾短信

概率及初始模型

#!/usr/bin/env python
# coding: utf-8

import pandas as pd
import codecs
import numpy as np
import math
import jieba

#计算对数先验概率
def getLogPrior(train):
    '''
        totals:{'y':单词总数,'no':'单词总数'}
        samples:{'y':样本数,'n':样本数}
        logPrior:{'y':先验概率,'no':先验概率}
    '''

    a1 = train[train['1']==0]
    a2 = train[train['1']==1]
    samples={'y':len(a1),'n':len(a2)}
    docSum = samples['y']+samples['n']
    prior={'y':samples['y']/docSum, 'n':samples['n']/docSum}
    logPrior={'y':math.log(prior['y']), 'n':math.log(prior['n'])}
    return (docSum,samples,logPrior,prior)


def getConditionPro(train):
    conditionPro={'y':{},'n':{}}
    logConditionPro={'y':{},'n':{}}
    docSum,samples,logPrior,prior=getLogPrior(train)
    a1 = train[train['1']==0]
    a2 = train[train['1']==1]
    classNum=2
    wordSet=set()
    for X_word in train['2']:
        for word in X_word:
            wordSet.add(word)
    #分类别计算词出现的次数
    words={'y':{},'n':{}}
    for messge in a1['2']:
        settemp=set(messge)
        for ch in messge:
            if ch in words['y']:
                words['y'][ch]+=1
            else:
                words['y'].setdefault(ch,1)

    for messge in a2['2']:
        settemp=set(messge)
        for ch in messge: