python实现朴素贝叶斯

最新推荐文章于 2025-09-06 09:26:50 发布

weixin_34128237

最新推荐文章于 2025-09-06 09:26:50 发布

阅读量93

点赞数

CC 4.0 BY-SA版权

文章标签：人工智能 python

原文链接：http://www.cnblogs.com/vachester/p/7475821.html

参考：《机器学习实战》- Machine Learning in Action

一、基本思想

简单的说，用概率的高低来决定数据属于哪一类别，这就是贝叶斯决策理论的核心思想，即选择具有最高概率的决策。朴素贝叶斯，则是在贝叶斯基础上做了一些最原始、最简单的假设。在朴素贝叶斯中，假设特征之间是相互独立的，比如假设a这个单词出现在am后的概率和出现在am前的概率是一样的。另外的一个假设是，每个特征同等重要。

二、代码

背景：对文档进行贝叶斯分类，判断其是否属于侮辱性文档。

#-*- coding:utf8 -*-
from numpy import *

#原始数据，训练样本
def loadDataSet():
    postingList = [
        ['my', 'dog', 'has', 'flea', 'problem', 'help', 'Please'],
        ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],
        ['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],
        ['stop', 'posting', 'stupid', 'worthless', 'garbage'],
        ['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],
        ['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']

    ]

    classVec = [0,1,0,1,0,1]
    return postingList, classVec

#得到所有词的列表
def createVocabList(dataSet):
    vocabSet = set([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    return list(vocabSet)

#某个文档的向量
def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1
        else:
            print "the word: %s is not in my Vocabulary!" % word

    return returnVec

#训练函数0
def trainNB0(trainMatrix, trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    p0Num = zeros(numWords)
    p1Num = zeros(numWords)
    p0Denom = 0.0
    p1Denom = 0.0
    for i in range(numTrainDocs):
        if trainCategory[i] == 1:
            plNum += trainMatrix[i]
            plDenom += sum(trainMatrix)
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix)
    p0Vect = p0Num/p0Denom
    p1Vect = p1Num/p1Denom
    return p0Vect, p1Vect, pAbusive

转载于:https://www.cnblogs.com/vachester/p/7475821.html