R版本：3.6.1

setwd('G:\\R语言\\大三下半年\\数据挖掘：R语言实战\\')

> library("e1071", lib.loc="H:/Program Files/R/R-3.6.1/library") Warning message: 程辑包‘e1071’是用R版本3.6.2 来建造的 

 #############模拟线性可分下的SVM > set.seed(12345) > x y x[y==1,] data_train x y x[y==1,] data_test plot(data_train[,2:1],col=as.integer(as.vector(data_train[,3]))+2,pch=8,cex=0.7,main="训练样本集-1和+1类散点图") > SvmFit summary(SvmFit)

Call: svm(formula = Fy ~ ., data = data_train, type = "C-classification",      kernel = "linear", cost = 10, scale = FALSE)

Parameters:    SVM-Type:  C-classification   SVM-Kernel:  linear         cost:  10 

Number of Support Vectors:  16

 ( 8 8 )

Number of Classes:  2 

Levels:   -1 1

> SvmFit$index  [1]  1  6  7 10 11 16 17 20 22 24 28 31 33 35 36 37 > plot(x=SvmFit,data=data_train,formula=Fx1~Fx2,svSymbol="#",dataSymbol="*",grid=100)

> SvmFit summary(SvmFit)

Call: svm(formula = Fy ~ ., data = data_train, type = "C-classification",      kernel = "linear", cost = 0.1, scale = FALSE)

Parameters:    SVM-Type:  C-classification   SVM-Kernel:  linear         cost:  0.1 

Number of Support Vectors:  25

 ( 12 13 )

Number of Classes:  2 

Levels:   -1 1

##############10折交叉验证选取损失惩罚参数C > set.seed(12345) > tObj summary(tObj)

Parameter tuning of ‘svm’:

- sampling method: 10-fold cross validation 

- best parameters:  cost     5

- best performance: 0.175 

- Detailed performance results:    cost error dispersion 1 1e-03 0.675  0.3129164 2 1e-02 0.375  0.3584302 3 1e-01 0.225  0.2486072 4 1e+00 0.200  0.2297341 5 5e+00 0.175  0.2371708 6 1e+01 0.175  0.2371708 7 1e+02 0.175  0.2371708 8 1e+03 0.175  0.2371708

> BestSvm summary(BestSvm)

Call: best.svm(x = Fy ~ ., data = data_train, cost = c(0.001, 0.01,      0.1, 1, 5, 10, 100, 1000), type = "C-classification", kernel = "linear",      scale = FALSE)

Parameters:    SVM-Type:  C-classification   SVM-Kernel:  linear         cost:  5 

Number of Support Vectors:  16

 ( 8 8 )

Number of Classes:  2 

Levels:   -1 1

> yPred (ConfM (Err ##############模拟线性不可分下的SVM > set.seed(12345) > x x[1:100,] x[101:150,] y data flag data_train data_test plot(data_train[,2:1],col=as.integer(as.vector(data_train[,3])),pch=8,cex=0.7,main="训练样本集散点图")

> set.seed(12345) > tObj plot(tObj,xlab=expression(gamma),ylab="损失惩罚参数C", +   main="不同参数组合下的预测错误率",nlevels=10,color.palette=terrain.colors)

> BestSvm summary(BestSvm)

Call: best.svm(x = Fy ~ ., data = data_train, gamma = c(0.5, 1, 2,      3, 4), cost = c(0.001, 0.01, 0.1, 1, 5, 10, 100, 1000),      type = "C-classification", kernel = "radial", scale = FALSE)

Parameters:    SVM-Type:  C-classification   SVM-Kernel:  radial         cost:  1 

Number of Support Vectors:  40

 ( 23 17 )

Number of Classes:  2 

Levels:   1 2

> plot(x=BestSvm,data=data_train,formula=Fx1~Fx2,svSymbol="#",dataSymbol="*",grid=100)

> yPred (ConfM (Err ##############模拟多类别的SVM > set.seed(12345) > x x[1:100,] x[101:150,] x y y x[y==0,2] data plot(data[,2:1],col=as.integer(as.vector(data[,3]))+1,pch=8,cex=0.7,main="训练样本集散点图")

> set.seed(12345) > tObj BestSvm summary(BestSvm)

Call: best.svm(x = Fy ~ ., data = data, gamma = c(0.5, 1, 2, 3, 4),      cost = c(0.001, 0.01, 0.1, 1, 5, 10, 100, 1000), type = "C-classification",      kernel = "radial", scale = FALSE)

Parameters:    SVM-Type:  C-classification   SVM-Kernel:  radial         cost:  5 

Number of Support Vectors:  133

 ( 70 31 32 )

Number of Classes:  3 

Levels:   0 1 2

> plot(x=BestSvm,data=data,formula=Fx1~Fx2,svSymbol="#",dataSymbol="*",grid=100)

> SvmFit head(SvmFit$decision.values)        1/2       1/0         2/0 1 1.033036 1.2345269 -0.61225558 2 1.600637 1.2219439  0.76098974 3 1.068253 1.0112116  0.59276079 4 1.047869 0.9999145  0.05666298 5 2.146043 1.4892178  1.23321397 6 1.031256 1.2279855 -1.10302134 > yPred (ConfM (Err ################天猫数据SVM > Tmall_train Tmall_train$BuyOrNot set.seed(12345) > tObj plot(tObj,xlab=expression(gamma),ylab="损失惩罚参数C", +   main="不同参数组合下的预测错误率",nlevels=10,color.palette=terrain.colors)

> BestSvm summary(BestSvm)

Call: best.svm(x = BuyOrNot ~ ., data = Tmall_train, gamma = 10^(-6:-3),      cost = 10^(-3:2), type = "C-classification", kernel = "radial")

Parameters:    SVM-Type:  C-classification   SVM-Kernel:  radial         cost:  100 

Number of Support Vectors:  79

 ( 40 39 )

Number of Classes:  2 

Levels:   0 1

> Tmall_test Tmall_test$BuyOrNot yPred (ConfM (Err