k-邻居、决策树、朴素贝叶斯、神经网络、支持向量机分类算法(以iris为例)所需的安装包：/Pibrary(class ) #KNNLibrary ) ## 朴素波段支持向量机library KNN _ accfunctionknn _ ACC-function (train.data，test.data，k ) { pre _ KNN=KNN } trarain TNN k ) #completeACCACC_KNN=sum(diag ) table(pre_KNN，test.data[[ (，5 ) ) )/dim (test.data ) ) train.data ) pre_tree=predict ) tree，newdata=test.data 5) )/dim (test.data ([1] ) # naive Bayes _ ATA test.data train.data (pre _ naive Bayes=predict (naive Bayes 1， newdata=test.data ) ACC_naiveBayes=sum ) diag (table ) Prata 5) )/dim (test.data ([1] ) # neural net _ data test.data ) ) ) ) 65 train.data，hidden=2(pre _ neural net=compute (neural net 1，test.data(-5 ) ) $ which.max ) class=colnames ) pre_neuralnet ) idx ) ACC_neuralnet=sum 5) )/dim(test.data(1) } # SVM test.data ) SVM1=SVM gamma=0.1，cost=10(pre_SVM=predict(SVM1，test.data ) ACC _ SVM=sum (诊断(表) 代入iris数据比较5种算法的精度/pACC_all=c(for(Iin1:10 ) test.idx=seq(I，150，by=10 ) train.idx=setdiff ] # # # # predictspeciesbyknnfunctionacc _ KNN _ ACC (train.data，test .k=4) # # # predictspeciesbytrefytrefc test.data (# # # predictspeciesbynaivebayesfunctionacc _ naive Bayes=naive Bayes _ ACC (train.data， test.data ) # # # predictspeciesbyneuralnetfunctionacc _ neural net=neural net _ ACC (train.data )， test.data ) # # # predictspeciesbysvmfunctionacc _ SVM=SVM _ ACC (train.data，test.data ) # save ACC _ all ACC _ ACC ACC_svm ) (colnames(ACC_all )=c(KNN (，tree )，朴素贝叶斯)，neneer mean )输出结果：/ppdf (e 3360/r work/classss