20210104 NaiveBayes 朴素贝叶斯 分类

1、花卉数据集实验 

https://cungudafa.blog.csdn.net/article/details/104890498

 

2、新闻

https://www.jianshu.com/p/90b3d4ac8409

from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.datasets import fetch_20newsgroups


def naive_bayes():
    #1.读取数据
    news_data = fetch_20newsgroups(subset="all")
    #2.划分训练集，测试集
    x_train,x_test,y_train,y_test = train_test_split(news_data.data,news_data.target,test_size=0.25)
    #3.进行特征抽取
    tf = TfidfVectorizer()
    x_train = tf.fit_transform(x_train)
    x_test = tf.transform(x_test)
    #4.进行朴素贝叶斯算法分类
    bayes = MultinomialNB(alpha=1.0)
    bayes.fit(x_train,y_train)
    y_predict = bayes.predict(x_test)
    print("测试集的预测结果为：",y_predict)
    print("模型的预测准确率为：",bayes.score(x_test,y_test))

if __name__ == '__main__':
    naive_bayes()3、基础

https://www.cnblogs.com/MrLJC/p/4102737.html

#coding=utf-8
from numpy import *
def loadDataSet():
    postingList=[['my', 'dog', 'has', 'flea', 'problems', '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]    #1 is abusive, 0 not
    return postingList,classVec

#创建一个带有所有单词的列表
def createVocabList(dataSet):
    vocabSet = set([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    return list(vocabSet)

def setOfWords2Vec(vocabList, inputSet):
    retVocabList = [0] * len(vocabList)
    for word in inputSet:
        if word in vocabList:
            retVocabList[vocabList.index(word)] = 1
        else:
            print 'word ',word ,'not in dict'
    return retVocabList

#另一种模型
def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec

def trainNB0(trainMatrix,trainCatergory):
    numTrainDoc = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCatergory)/float(numTrainDoc)
    #防止多个概率的成绩当中的一个为0
    p0Num = ones(numWords)
    p1Num = ones(numWords)
    p0Denom = 2.0
    p1Denom = 2.0
    for i in range(numTrainDoc):
        if trainCatergory[i] == 1:
            p1Num +=trainMatrix[i]
            p1Denom += sum(trainMatrix[i])
        else:
            p0Num +=trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    p1Vect = log(p1Num/p1Denom)#处于精度的考虑，否则很可能到限归零
    p0Vect = log(p0Num/p0Denom)
    return p0Vect,p1Vect,pAbusive

def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)    #element-wise mult
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else:
        return 0

def testingNB():
    listOPosts,listClasses = loadDataSet()
    myVocabList = createVocabList(listOPosts)
    trainMat=[]
    for postinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    p0V,p1V,pAb = trainNB0(array(trainMat),array(listClasses))
    testEntry = ['love', 'my', 'dalmation']
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb)
    testEntry = ['stupid', 'garbage']
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb)

def main():
    testingNB()

if __name__ == '__main__':
    main()