import pandas as pd
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn import datasets
iris=datasets.load_iris()
print(iris.data)
print(iris.target)
Xtrain,Xtest,ytrain,ytest=train_test_split(iris.data,iris.target,random_state=12)
clf=GaussianNB()
clf.fit(Xtrain,ytrain)
print("类别:\n",clf.predict(Xtest))
print("概率:\n",clf.predict_proba(Xtest))
print("准确率:\n",accuracy_score(ytest,clf.predict(Xtest)))
import numpy as np
import pandas as pd
import random
dataSet=pd.read_csv('../MLinAction_source/iris.txt',header=None)
print(dataSet.head())
def randSplit(dataSet,rate):
l=list(dataSet.index)
random.shuffle(l)
dataSet.index=l
n=dataSet.shape[0]
m=int(n*rate)
train=dataSet.loc[range(m),:]
test=dataSet.loc[range(m,n),:]
dataSet.index=range(dataSet.shape[0])
test.index=range(test.shape[0])
return train,test
train,test=randSplit(dataSet,0.8)
def gnb_classify(train,test):
labels=train.iloc[:,-1].value_counts().index
mean=[]
std=[]
result=[]
for i in labels:
item=train.loc[train.iloc[:,-1]==i,:]
m=item.iloc[:,:-1].mean()
s=np.sum((item.iloc[:,:-1]-m)**2)/(item.shape[0])
mean.append(m)
std.append(s)
means=pd.DataFrame(mean,index=labels)
stds=pd.DataFrame(std,index=labels)
for j in range(test.shape[0]):
iset=test.iloc[j,:-1].tolist()
iprob=np.exp(-1*(iset-means)**2/(stds*2))/(np.sqrt(2*np.pi*stds))
prob=1
for k in range(test.shape[1]-1):
prob*=iprob[k]
cla=prob.index[np.argmax(prob.values)]
result.append(cla)
test['predict']=result
acc=(test.iloc[:,-1]==test.iloc[:,-2]).mean()
print(f'模型的准确率为{acc}')
return test
gnb_classify(train,test)
'''
返回: dataSet 切分好的样本词条
classVec:类标签向量
'''
def loadDataSet():
dataSet = [['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]
return dataSet,classVec
dataSet,classVec=loadDataSet()
'''
参数: dataSet:切分好的样本词条
返回: vocabList:不重复的词汇表
'''
def createVocabLitst(dataSet):
vocabSet=set()
for doc in dataSet:
vocabSet=vocabSet|set(doc)
vocabList=list(vocabSet)
return vocabList
vocabList=createVocabLitst(dataSet)
print("词汇表:\n",vocabList)
'''
根据vocabList词汇表,将inputSet向量化,向量的每个元素为1或0
参数:
vocabList:词汇表
inputSet:切分好的词条列表中的一条
返回:
returnVec:文档向量,词集模型
'''
def setOfwords2vec(vocabList,inputSet):
returnVec=[0]*len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)]=1
else:
print(f"{word} is not in my vocabulary!")
return returnVec
'''
生成训练集向量列表
参数: dataSet:切分好的样本词条
返回: trainMat:所有的词条向量组成的列表
'''
def get_trainMat(dataSet):
trainMat=[]
vocabList=createVocabLitst(dataSet)
for inputSet in dataSet:
returnVec=setOfwords2vec(vocabList,inputSet)
trainMat.append(returnVec)
return trainMat
trainMat=get_trainMat(dataSet)
print("trainMat:\n",trainMat)
'''
功能: 朴素贝叶斯分类器训练函数
参数说明:
trainMat:训练文档矩阵
classVec:训练类标签向量
返回值:
p0v:非侮辱类的条件概率数组
p1v:侮辱类的条件概率数组
pab:文档属于侮辱类的概率
'''
def trainNB(trainMat,classVec):
n=len(trainMat)
m=len(trainMat[0])
pAb=sum(classVec)/n
p0Num=np.ones(m)
p1Num=np.ones(m)
p0Denom=2
p1Denom=2
for i in range(n):
if classVec[i]==1:
p1Num+=trainMat[i]
p1Denom+=sum(trainMat[i])
else:
p0Num+=trainMat[i]
p0Denom+=sum(trainMat[i])
p1v=np.log(p1Num/p1Denom)
p0v=np.log(p0Num/p0Denom)
return p0v,p1v,pAb
p0V,p1V,pAb=trainNB(trainMat,classVec)
print(p0V)
from functools import reduce
'''
函数功能: 朴素贝叶斯分类器分类函数
参数:
vec2classify:待分类的词条数组
p0v:非侮辱类的条件概率数组
p1v:侮辱类的条件概率数组
pAb:文档输入侮辱类的概率
返回:
0:属于非侮辱类
1:属于侮辱类
'''
def classifyNB(vec2Classify,p0v,p1v,pAb):
p1=sum(vec2Classify*p1v)+np.log(pAb)
p0=sum(vec2Classify*p0v)+np.log(1-pAb)
print('p0:',p0)
print('p1:',p1)
if p1>p0:
return 1
else:
return 0
'''
参数:testVec:测试样本
返回:测试样本的类别
'''
def testingNB(testVec):
dataSet,classVec=loadDataSet()
vocabList=createVocabLitst(dataSet)
trainMat=get_trainMat(dataSet)
p0v,p1v,pAb=trainNB(trainMat,classVec)
thisone=setOfwords2vec(vocabList,testVec)
if classifyNB(thisone,p0v,p1v,pAb)==1:
print(testVec,'属于侮辱类')
else:
print(testVec,'属于非侮辱类')
testVec1=['love','my','dalmation']
testingNB(testVec1)
testVec2=['stupid','garbage']
testingNB(testVec2)
iris.txt:
5.1,3.5,1.4,0.2,Iris-setosa
4.9,3.0,1.4,0.2,Iris-setosa
4.7,3.2,1.3,0.2,Iris-setosa
4.6,3.1,1.5,0.2,Iris-setosa
5.0,3.6,1.4,0.2,Iris-setosa
5.4,3.9,1.7,0.4,Iris-setosa
4.6,3.4,1.4,0.3,Iris-setosa
5.0,3.4,1.5,0.2,Iris-setosa
4.4,2.9,1.4,0.2,Iris-setosa
4.9,3.1,1.5,0.1,Iris-setosa
5.4,3.7,1.5,0.2,Iris-setosa
4.8,3.4,1.6,0.2,Iris-setosa
4.8,3.0,1.4,0.1,Iris-setosa
4.3,3.0,1.1,0.1,Iris-setosa
5.8,4.0,1.2,0.2,Iris-setosa
5.7,4.4,1.5,0.4,Iris-setosa
5.4,3.9,1.3,0.4,Iris-setosa
5.1,3.5,1.4,0.3,Iris-setosa
5.7,3.8,1.7,0.3,Iris-setosa
5.1,3.8,1.5,0.3,Iris-setosa
5.4,3.4,1.7,0.2,Iris-setosa
5.1,3.7,1.5,0.4,Iris-setosa
4.6,3.6,1.0,0.2,Iris-setosa
5.1,3.3,1.7,0.5,Iris-setosa
4.8,3.4,1.9,0.2,Iris-setosa
5.0,3.0,1.6,0.2,Iris-setosa
5.0,3.4,1.6,0.4,Iris-setosa
5.2,3.5,1.5,0.2,Iris-setosa
5.2,3.4,1.4,0.2,Iris-setosa
4.7,3.2,1.6,0.2,Iris-setosa
4.8,3.1,1.6,0.2,Iris-setosa
5.4,3.4,1.5,0.4,Iris-setosa
5.2,4.1,1.5,0.1,Iris-setosa
5.5,4.2,1.4,0.2,Iris-setosa
4.9,3.1,1.5,0.1,Iris-setosa
5.0,3.2,1.2,0.2,Iris-setosa
5.5,3.5,1.3,0.2,Iris-setosa
4.9,3.1,1.5,0.1,Iris-setosa
4.4,3.0,1.3,0.2,Iris-setosa
5.1,3.4,1.5,0.2,Iris-setosa
5.0,3.5,1.3,0.3,Iris-setosa
4.5,2.3,1.3,0.3,Iris-setosa
4.4,3.2,1.3,0.2,Iris-setosa
5.0,3.5,1.6,0.6,Iris-setosa
5.1,3.8,1.9,0.4,Iris-setosa
4.8,3.0,1.4,0.3,Iris-setosa
5.1,3.8,1.6,0.2,Iris-setosa
4.6,3.2,1.4,0.2,Iris-setosa
5.3,3.7,1.5,0.2,Iris-setosa
5.0,3.3,1.4,0.2,Iris-setosa
7.0,3.2,4.7,1.4,Iris-versicolor
6.4,3.2,4.5,1.5,Iris-versicolor
6.9,3.1,4.9,1.5,Iris-versicolor
5.5,2.3,4.0,1.3,Iris-versicolor
6.5,2.8,4.6,1.5,Iris-versicolor
5.7,2.8,4.5,1.3,Iris-versicolor
6.3,3.3,4.7,1.6,Iris-versicolor
4.9,2.4,3.3,1.0,Iris-versicolor
6.6,2.9,4.6,1.3,Iris-versicolor
5.2,2.7,3.9,1.4,Iris-versicolor
5.0,2.0,3.5,1.0,Iris-versicolor
5.9,3.0,4.2,1.5,Iris-versicolor
6.0,2.2,4.0,1.0,Iris-versicolor
6.1,2.9,4.7,1.4,Iris-versicolor
5.6,2.9,3.6,1.3,Iris-versicolor
6.7,3.1,4.4,1.4,Iris-versicolor
5.6,3.0,4.5,1.5,Iris-versicolor
5.8,2.7,4.1,1.0,Iris-versicolor
6.2,2.2,4.5,1.5,Iris-versicolor
5.6,2.5,3.9,1.1,Iris-versicolor
5.9,3.2,4.8,1.8,Iris-versicolor
6.1,2.8,4.0,1.3,Iris-versicolor
6.3,2.5,4.9,1.5,Iris-versicolor
6.1,2.8,4.7,1.2,Iris-versicolor
6.4,2.9,4.3,1.3,Iris-versicolor
6.6,3.0,4.4,1.4,Iris-versicolor
6.8,2.8,4.8,1.4,Iris-versicolor
6.7,3.0,5.0,1.7,Iris-versicolor
6.0,2.9,4.5,1.5,Iris-versicolor
5.7,2.6,3.5,1.0,Iris-versicolor
5.5,2.4,3.8,1.1,Iris-versicolor
5.5,2.4,3.7,1.0,Iris-versicolor
5.8,2.7,3.9,1.2,Iris-versicolor
6.0,2.7,5.1,1.6,Iris-versicolor
5.4,3.0,4.5,1.5,Iris-versicolor
6.0,3.4,4.5,1.6,Iris-versicolor
6.7,3.1,4.7,1.5,Iris-versicolor
6.3,2.3,4.4,1.3,Iris-versicolor
5.6,3.0,4.1,1.3,Iris-versicolor
5.5,2.5,4.0,1.3,Iris-versicolor
5.5,2.6,4.4,1.2,Iris-versicolor
6.1,3.0,4.6,1.4,Iris-versicolor
5.8,2.6,4.0,1.2,Iris-versicolor
5.0,2.3,3.3,1.0,Iris-versicolor
5.6,2.7,4.2,1.3,Iris-versicolor
5.7,3.0,4.2,1.2,Iris-versicolor
5.7,2.9,4.2,1.3,Iris-versicolor
6.2,2.9,4.3,1.3,Iris-versicolor
5.1,2.5,3.0,1.1,Iris-versicolor
5.7,2.8,4.1,1.3,Iris-versicolor
6.3,3.3,6.0,2.5,Iris-virginica
5.8,2.7,5.1,1.9,Iris-virginica
7.1,3.0,5.9,2.1,Iris-virginica
6.3,2.9,5.6,1.8,Iris-virginica
6.5,3.0,5.8,2.2,Iris-virginica
7.6,3.0,6.6,2.1,Iris-virginica
4.9,2.5,4.5,1.7,Iris-virginica
7.3,2.9,6.3,1.8,Iris-virginica
6.7,2.5,5.8,1.8,Iris-virginica
7.2,3.6,6.1,2.5,Iris-virginica
6.5,3.2,5.1,2.0,Iris-virginica
6.4,2.7,5.3,1.9,Iris-virginica
6.8,3.0,5.5,2.1,Iris-virginica
5.7,2.5,5.0,2.0,Iris-virginica
5.8,2.8,5.1,2.4,Iris-virginica
6.4,3.2,5.3,2.3,Iris-virginica
6.5,3.0,5.5,1.8,Iris-virginica
7.7,3.8,6.7,2.2,Iris-virginica
7.7,2.6,6.9,2.3,Iris-virginica
6.0,2.2,5.0,1.5,Iris-virginica
6.9,3.2,5.7,2.3,Iris-virginica
5.6,2.8,4.9,2.0,Iris-virginica
7.7,2.8,6.7,2.0,Iris-virginica
6.3,2.7,4.9,1.8,Iris-virginica
6.7,3.3,5.7,2.1,Iris-virginica
7.2,3.2,6.0,1.8,Iris-virginica
6.2,2.8,4.8,1.8,Iris-virginica
6.1,3.0,4.9,1.8,Iris-virginica
6.4,2.8,5.6,2.1,Iris-virginica
7.2,3.0,5.8,1.6,Iris-virginica
7.4,2.8,6.1,1.9,Iris-virginica
7.9,3.8,6.4,2.0,Iris-virginica
6.4,2.8,5.6,2.2,Iris-virginica
6.3,2.8,5.1,1.5,Iris-virginica
6.1,2.6,5.6,1.4,Iris-virginica
7.7,3.0,6.1,2.3,Iris-virginica
6.3,3.4,5.6,2.4,Iris-virginica
6.4,3.1,5.5,1.8,Iris-virginica
6.0,3.0,4.8,1.8,Iris-virginica
6.9,3.1,5.4,2.1,Iris-virginica
6.7,3.1,5.6,2.4,Iris-virginica
6.9,3.1,5.1,2.3,Iris-virginica
5.8,2.7,5.1,1.9,Iris-virginica
6.8,3.2,5.9,2.3,Iris-virginica
6.7,3.3,5.7,2.5,Iris-virginica
6.7,3.0,5.2,2.3,Iris-virginica
6.3,2.5,5.0,1.9,Iris-virginica
6.5,3.0,5.2,2.0,Iris-virginica
6.2,3.4,5.4,2.3,Iris-virginica
5.9,3.0,5.1,1.8,Iris-virginica