ArcLakeGroupSummary <- read_excel("~/Desktop/EPSRC Project /ArcLakeGroupSummary.xlsx")
dundeedata <- read_csv("~/Desktop/EPSRC Project /dundeedata.csv.xls")
colnames(dundeedata)[1]<-"GloboLakes_ID" # change the GloboLID column name to GloboLakes_ID to make the merge easier.
Data<-merge(ArcLakeGroupSummary, dundeedata, by = "GloboLakes_ID", all = TRUE )
Data<-subset(Data, Group!="NA") # The data set is back to the original 732 rows just with extra columns of information
Data$Group<-as.factor(Data$Group)In order to use each method, I first prepare a suitable data frame - splitting it into training and test sets and then splitting the training set into 5 folds.
Data1<-data.frame(Data[,c("Group","PC1","PC2")])
# Stratify the entire training set into training and test sets
set.seed(234)
library(caret)
train.index<-createDataPartition(Data1$Group, p=0.8, list = FALSE)
train.set<-Data1[train.index, ]
test.set<-Data1[-train.index, ]
# Stratify the training set into 5 folds
folds <- createFolds(y=factor(train.set$Group), k = 5, list = FALSE)
train.set$fold <- foldsThree main ways of choosing hyperparameters apart from selecting all possible combinations or just randomly performing a self selected sweep of what we think would perform well is to use a
#linear
svm_fit_bayes<-function(logCost){
CV.error<-NULL
for (i in 1:5) {
valid.data <- subset(train.set, fold == i)
train.data <- subset(train.set, fold != i)
svmfit<-svm(Group~PC1+PC2, data = train.data, kernel="linear",
cost=exp(logCost), scale= FALSE)
svm.y<-valid.data$Group
svm.predy<-predict(svmfit, valid.data)
ith.test.error<- mean(svm.y!=svm.predy)
CV.error<-c(CV.error,(nrow(valid.data)/nrow(train.set))*ith.test.error)
}
list(Score=-sum(CV.error), pred=0)
}
set.seed(234)
OPT_Res<- BayesianOptimization(svm_fit_bayes, bounds= list(logCost = c(-5, 20)),
init_grid_dt = NULL, init_points = 50,
n_iter = 20, acq = "ucb", kappa =2.576,
eps=0, verbose = TRUE)## elapsed = 6.48 Round = 1 logCost = 13.6405 Value = -0.0186
## elapsed = 11.07 Round = 2 logCost = 14.5428 Value = -0.0186
## elapsed = 0.13 Round = 3 logCost = -4.4991 Value = -0.0254
## elapsed = 8.99 Round = 4 logCost = 14.4021 Value = -0.0186
## elapsed = 0.05 Round = 5 logCost = -3.3272 Value = -0.0153
## elapsed = 2.84 Round = 6 logCost = 11.1199 Value = -0.0203
## elapsed = 7.57 Round = 7 logCost = 18.2346 Value = -0.1034
## elapsed = 5.17 Round = 8 logCost = 12.9411 Value = -0.0186
## elapsed = 7.59 Round = 9 logCost = 18.1934 Value = -0.1034
## elapsed = 0.06 Round = 10 logCost = 2.1058 Value = -0.0203
## elapsed = 0.52 Round = 11 logCost = 8.8931 Value = -0.0203
## elapsed = 0.48 Round = 12 logCost = 8.6925 Value = -0.0203
## elapsed = 2.18 Round = 13 logCost = 9.5712 Value = -0.0220
## elapsed = 2.01 Round = 14 logCost = 9.5747 Value = -0.0220
## elapsed = 0.23 Round = 15 logCost = -4.9700 Value = -0.0220
## elapsed = 1.05 Round = 16 logCost = 6.0279 Value = -0.0203
## elapsed = 0.18 Round = 17 logCost = 2.8288 Value = -0.0203
## elapsed = 10.93 Round = 18 logCost = 13.5004 Value = -0.0186
## elapsed = 0.06 Round = 19 logCost = -1.5418 Value = -0.0186
## elapsed = 7.64 Round = 20 logCost = 16.7944 Value = -0.1034
## elapsed = 0.48 Round = 21 logCost = 8.0767 Value = -0.0203
## elapsed = 1.67 Round = 22 logCost = 9.4776 Value = -0.0220
## elapsed = 7.16 Round = 23 logCost = 16.6300 Value = -0.1034
## elapsed = 1.98 Round = 24 logCost = 10.4356 Value = -0.0203
## elapsed = 0.53 Round = 25 logCost = 7.2445 Value = -0.0203
## elapsed = 0.10 Round = 26 logCost = 4.3700 Value = -0.0203
## elapsed = 5.47 Round = 27 logCost = 12.4167 Value = -0.0186
## elapsed = 0.07 Round = 28 logCost = -0.2072 Value = -0.0186
## elapsed = 7.40 Round = 29 logCost = 15.9732 Value = -0.0186
## elapsed = 7.90 Round = 30 logCost = 17.0627 Value = -0.1034
## elapsed = 2.31 Round = 31 logCost = 10.4807 Value = -0.0203
## elapsed = 0.07 Round = 32 logCost = 1.3078 Value = -0.0203
## elapsed = 0.05 Round = 33 logCost = -0.5958 Value = -0.0186
## elapsed = 6.10 Round = 34 logCost = 12.6207 Value = -0.0186
## elapsed = 0.51 Round = 35 logCost = 8.3371 Value = -0.0203
## elapsed = 4.96 Round = 36 logCost = 12.2033 Value = -0.0186
## elapsed = 5.27 Round = 37 logCost = 12.5207 Value = -0.0186
## elapsed = 0.05 Round = 38 logCost = -1.1632 Value = -0.0169
## elapsed = 0.42 Round = 39 logCost = 7.6583 Value = -0.0203
## elapsed = 0.08 Round = 40 logCost = 3.8680 Value = -0.0203
## elapsed = 1.67 Round = 41 logCost = 9.5338 Value = -0.0220
## elapsed = 7.47 Round = 42 logCost = 17.6858 Value = -0.1034
## elapsed = 7.78 Round = 43 logCost = 16.1313 Value = -0.0186
## elapsed = 0.07 Round = 44 logCost = 0.8071 Value = -0.0203
## elapsed = 3.43 Round = 45 logCost = 11.4682 Value = -0.0186
## elapsed = 7.72 Round = 46 logCost = 14.4283 Value = -0.0186
## elapsed = 0.05 Round = 47 logCost = 1.0083 Value = -0.0203
## elapsed = 3.30 Round = 48 logCost = 10.7092 Value = -0.0203
## elapsed = 1.27 Round = 49 logCost = 9.8284 Value = -0.0220
## elapsed = 0.05 Round = 50 logCost = -1.8423 Value = -0.0186
## elapsed = 2.17 Round = 51 logCost = 10.4467 Value = -0.0203
## elapsed = 3.98 Round = 52 logCost = 11.3556 Value = -0.0186
## elapsed = 6.27 Round = 53 logCost = 12.5493 Value = -0.0186
## elapsed = 0.07 Round = 54 logCost = -2.0199 Value = -0.0186
## elapsed = 3.90 Round = 55 logCost = 11.3426 Value = -0.0186
## elapsed = 3.64 Round = 56 logCost = 11.5541 Value = -0.0203
## elapsed = 8.13 Round = 57 logCost = 13.1535 Value = -0.0186
## elapsed = 0.08 Round = 58 logCost = -2.8344 Value = -0.0169
## elapsed = 0.09 Round = 59 logCost = -2.3143 Value = -0.0169
## elapsed = 4.93 Round = 60 logCost = 11.1460 Value = -0.0203
## elapsed = 4.78 Round = 61 logCost = 11.9674 Value = -0.0186
## elapsed = 0.07 Round = 62 logCost = -1.8601 Value = -0.0186
## elapsed = 2.83 Round = 63 logCost = 10.2196 Value = -0.0203
## elapsed = 4.10 Round = 64 logCost = 10.8603 Value = -0.0203
## elapsed = 4.88 Round = 65 logCost = 11.7292 Value = -0.0186
## elapsed = 3.88 Round = 66 logCost = 11.3742 Value = -0.0186
## elapsed = 0.08 Round = 67 logCost = -2.1433 Value = -0.0169
## elapsed = 0.08 Round = 68 logCost = -3.6650 Value = -0.0220
## elapsed = 0.34 Round = 69 logCost = -1.0259 Value = -0.0186
## elapsed = 5.86 Round = 70 logCost = 11.1258 Value = -0.0203
##
## Best Parameters Found:
## Round = 5 logCost = -3.3272 Value = -0.0153 OPT_Res$Best_Par## logCost
## -3.327248 as.numeric(exp(OPT_Res$Best_Par["logCost"]))## [1] 0.03589176 CV.error<-NULL
for (i in 1:5) {
valid.data <- subset(train.set, fold == i)
train.data <- subset(train.set, fold != i)
svmfit<-svm(Group~PC1+PC2, data = train.data, kernel="linear",
cost=exp(OPT_Res$Best_Par["logCost"]), scale = FALSE)
svm.y<-valid.data$Group
svm.predy<-predict(svmfit, valid.data)
ith.test.error<- mean(svm.y!=svm.predy)
CV.error<-c(CV.error,(nrow(valid.data)/nrow(train.set))*ith.test.error)
}
sum(CV.error)## [1] 0.01525424svm_fit_bayes<-function(logCost, logGamma, Degree){
CV.error<-NULL
for (i in 1:5) {
valid.data <- subset(train.set, fold == i)
train.data <- subset(train.set, fold != i)
svmfit<-svm(Group~PC1+PC2, data = train.data, kernel="polynomial",
cost=exp(logCost), gamma=exp(logGamma), degree=Degree)
svm.y<-valid.data$Group
svm.predy<-predict(svmfit, valid.data)
ith.test.error<- mean(svm.y!=svm.predy)
CV.error<-c(CV.error,(nrow(valid.data)/nrow(train.set))*ith.test.error)
}
list(Score=-sum(CV.error), pred=0)
}
set.seed(234)
OPT_Res<- BayesianOptimization(svm_fit_bayes, bounds= list(logCost = c(-5, 20),
logGamma = c(-9, 5),
Degree = c(1L, 5L)),
init_grid_dt = NULL, init_points = 50,
n_iter = 20, acq = "ucb", kappa =2.576,
eps=0, verbose = TRUE)## elapsed = 48.24 Round = 1 logCost = 13.6405 logGamma = -0.1100 Degree = 4.0000 Value = -0.1068
## elapsed = 0.14 Round = 2 logCost = 14.5428 logGamma = -3.6803 Degree = 4.0000 Value = -0.1203
## elapsed = 0.23 Round = 3 logCost = -4.4991 logGamma = -6.8452 Degree = 2.0000 Value = -0.6678
## elapsed = 6.50 Round = 4 logCost = 14.4021 logGamma = 2.3082 Degree = 3.0000 Value = -0.0203
## elapsed = 0.25 Round = 5 logCost = -3.3272 logGamma = -7.8940 Degree = 2.0000 Value = -0.6678
## elapsed = 0.22 Round = 6 logCost = 11.1199 logGamma = -6.9799 Degree = 5.0000 Value = -0.6678
## elapsed = 0.13 Round = 7 logCost = 18.2346 logGamma = -7.7917 Degree = 2.0000 Value = -0.0797
## elapsed = 0.81 Round = 8 logCost = 12.9411 logGamma = -2.5374 Degree = 2.0000 Value = -0.0780
## elapsed = 176.03 Round = 9 logCost = 18.1934 logGamma = 2.3218 Degree = 2.0000 Value = -0.1119
## elapsed = 0.15 Round = 10 logCost = 2.1058 logGamma = 0.5545 Degree = 3.0000 Value = -0.0305
## elapsed = 0.22 Round = 11 logCost = 8.8931 logGamma = -3.8455 Degree = 4.0000 Value = -0.4153
## elapsed = 0.17 Round = 12 logCost = 8.6925 logGamma = -2.1492 Degree = 2.0000 Value = -0.0780
## elapsed = 0.23 Round = 13 logCost = 9.5712 logGamma = -5.4319 Degree = 3.0000 Value = -0.4814
## elapsed = 4.80 Round = 14 logCost = 9.5747 logGamma = 3.1058 Degree = 3.0000 Value = -0.0203
## elapsed = 0.21 Round = 15 logCost = -4.9700 logGamma = -2.5619 Degree = 2.0000 Value = -0.6678
## elapsed = 0.10 Round = 16 logCost = 6.0279 logGamma = -3.4814 Degree = 1.0000 Value = -0.0288
## elapsed = 0.19 Round = 17 logCost = 2.8288 logGamma = 1.6296 Degree = 2.0000 Value = -0.0797
## elapsed = 1.79 Round = 18 logCost = 13.5004 logGamma = -1.9421 Degree = 2.0000 Value = -0.0797
## elapsed = 0.12 Round = 19 logCost = -1.5418 logGamma = 0.3706 Degree = 4.0000 Value = -0.1220
## elapsed = 1.14 Round = 20 logCost = 16.7944 logGamma = -0.5696 Degree = 3.0000 Value = -0.0186
## elapsed = 113.38 Round = 21 logCost = 8.0767 logGamma = 4.0595 Degree = 4.0000 Value = -0.1678
## elapsed = 0.18 Round = 22 logCost = 9.4776 logGamma = -4.1480 Degree = 3.0000 Value = -0.1610
## elapsed = 0.28 Round = 23 logCost = 16.6300 logGamma = -0.8016 Degree = 3.0000 Value = -0.0169
## elapsed = 0.14 Round = 24 logCost = 10.4356 logGamma = -4.6248 Degree = 3.0000 Value = -0.1864
## elapsed = 0.20 Round = 25 logCost = 7.2445 logGamma = -8.0562 Degree = 4.0000 Value = -0.6678
## elapsed = 0.16 Round = 26 logCost = 4.3700 logGamma = -3.6790 Degree = 2.0000 Value = -0.2322
## elapsed = 2.80 Round = 27 logCost = 12.4167 logGamma = -1.3037 Degree = 4.0000 Value = -0.0729
## elapsed = 0.36 Round = 28 logCost = -0.2072 logGamma = -3.5495 Degree = 4.0000 Value = -0.6678
## elapsed = 0.15 Round = 29 logCost = 15.9732 logGamma = -6.9054 Degree = 2.0000 Value = -0.0881
## elapsed = 0.15 Round = 30 logCost = 17.0627 logGamma = -7.2907 Degree = 2.0000 Value = -0.0831
## elapsed = 0.09 Round = 31 logCost = 10.4807 logGamma = -0.7788 Degree = 3.0000 Value = -0.0186
## elapsed = 0.17 Round = 32 logCost = 1.3078 logGamma = -1.4961 Degree = 2.0000 Value = -0.1712
## elapsed = 0.43 Round = 33 logCost = -0.5958 logGamma = -4.3707 Degree = 4.0000 Value = -0.6678
## elapsed = 18.16 Round = 34 logCost = 12.6207 logGamma = 2.8276 Degree = 5.0000 Value = -0.0678
## elapsed = 18.80 Round = 35 logCost = 8.3371 logGamma = 4.0253 Degree = 3.0000 Value = -0.0203
## elapsed = 1.09 Round = 36 logCost = 12.2033 logGamma = 0.0287 Degree = 5.0000 Value = -0.0305
## elapsed = 0.65 Round = 37 logCost = 12.5207 logGamma = -4.9540 Degree = 4.0000 Value = -0.4542
## elapsed = 1.25 Round = 38 logCost = -1.1632 logGamma = 4.3850 Degree = 2.0000 Value = -0.0780
## elapsed = 0.46 Round = 39 logCost = 7.6583 logGamma = -4.3597 Degree = 4.0000 Value = -0.6288
## elapsed = 3.64 Round = 40 logCost = 3.8680 logGamma = 2.5258 Degree = 2.0000 Value = -0.0780
## elapsed = 88.98 Round = 41 logCost = 9.5338 logGamma = 2.9501 Degree = 4.0000 Value = -0.1254
## elapsed = 17.24 Round = 42 logCost = 17.6858 logGamma = 2.9679 Degree = 5.0000 Value = -0.0695
## elapsed = 0.13 Round = 43 logCost = 16.1313 logGamma = -6.8699 Degree = 3.0000 Value = -0.2492
## elapsed = 0.20 Round = 44 logCost = 0.8071 logGamma = -6.9476 Degree = 4.0000 Value = -0.6678
## elapsed = 0.08 Round = 45 logCost = 11.4682 logGamma = -1.7771 Degree = 5.0000 Value = -0.0475
## elapsed = 12.42 Round = 46 logCost = 14.4283 logGamma = 4.9103 Degree = 5.0000 Value = -0.0678
## elapsed = 0.43 Round = 47 logCost = 1.0083 logGamma = -3.7983 Degree = 2.0000 Value = -0.6542
## elapsed = 0.14 Round = 48 logCost = 10.7092 logGamma = -3.7880 Degree = 2.0000 Value = -0.0746
## elapsed = 18.33 Round = 49 logCost = 9.8284 logGamma = 0.6458 Degree = 2.0000 Value = -0.0797
## elapsed = 0.20 Round = 50 logCost = -1.8423 logGamma = -1.8271 Degree = 3.0000 Value = -0.5169
## elapsed = 1.19 Round = 51 logCost = 10.0777 logGamma = 5.0000 Degree = 1.0000 Value = -0.0203
## elapsed = 15.66 Round = 52 logCost = 20.0000 logGamma = -4.1798 Degree = 2.0000 Value = -0.0763
## elapsed = 30.82 Round = 53 logCost = -5.0000 logGamma = 4.0627 Degree = 4.0000 Value = -0.0915
## elapsed = 13.18 Round = 54 logCost = 20.0000 logGamma = 5.0000 Degree = 3.0000 Value = -0.0729
## elapsed = 134.18 Round = 55 logCost = 13.5862 logGamma = 5.0000 Degree = 2.0000 Value = -0.1356
## elapsed = 0.08 Round = 56 logCost = 3.8687 logGamma = 5.0000 Degree = 1.0000 Value = -0.0203
## elapsed = 10.86 Round = 57 logCost = 20.0000 logGamma = -0.7478 Degree = 1.0000 Value = -0.0254
## elapsed = 0.10 Round = 58 logCost = -5.0000 logGamma = 1.8896 Degree = 3.0000 Value = -0.0492
## elapsed = 0.13 Round = 59 logCost = -5.0000 logGamma = 2.1669 Degree = 1.0000 Value = -0.2508
## elapsed = 0.37 Round = 60 logCost = 20.0000 logGamma = -1.3970 Degree = 5.0000 Value = -0.0305
## elapsed = 0.06 Round = 61 logCost = 14.2023 logGamma = -9.0000 Degree = 1.0000 Value = -0.0153
## elapsed = 0.14 Round = 62 logCost = 5.4855 logGamma = 0.2718 Degree = 5.0000 Value = -0.0373
## elapsed = 0.93 Round = 63 logCost = -0.0501 logGamma = 2.9051 Degree = 5.0000 Value = -0.0271
## elapsed = 0.10 Round = 64 logCost = -5.0000 logGamma = 1.7715 Degree = 5.0000 Value = -0.0407
## elapsed = 0.22 Round = 65 logCost = 20.0000 logGamma = -9.0000 Degree = 5.0000 Value = -0.6678
## elapsed = 0.21 Round = 66 logCost = 20.0000 logGamma = -9.0000 Degree = 1.0000 Value = -0.0203
## elapsed = 1.69 Round = 67 logCost = 1.4227 logGamma = 5.0000 Degree = 3.0000 Value = -0.0169
## elapsed = 0.21 Round = 68 logCost = -5.0000 logGamma = -9.0000 Degree = 5.0000 Value = -0.6678
## elapsed = 125.59 Round = 69 logCost = 20.0000 logGamma = 2.2255 Degree = 4.0000 Value = -0.1661
## elapsed = 0.07 Round = 70 logCost = 15.9883 logGamma = -4.0561 Degree = 3.0000 Value = -0.0271
##
## Best Parameters Found:
## Round = 61 logCost = 14.2023 logGamma = -9.0000 Degree = 1.0000 Value = -0.0153 OPT_Res$Best_Par## logCost logGamma Degree
## 14.20234 -9.00000 1.00000 as.numeric(exp(OPT_Res$Best_Par["logCost"]))## [1] 1472299 as.numeric(exp(OPT_Res$Best_Par["logGamma"]))## [1] 0.0001234098 CV.error<-NULL
for (i in 1:5) {
valid.data <- subset(train.set, fold == i)
train.data <- subset(train.set, fold != i)
svmfit<-svm(Group~PC1+PC2, data = train.data, kernel="polynomial",
cost=exp(OPT_Res$Best_Par["logCost"]),
gamma=exp(OPT_Res$Best_Par["logGamma"]),
degree=OPT_Res$Best_Par["Degree"])
svm.y<-valid.data$Group
svm.predy<-predict(svmfit, valid.data)
ith.test.error<- mean(svm.y!=svm.predy)
CV.error<-c(CV.error,(nrow(valid.data)/nrow(train.set))*ith.test.error)
}
sum(CV.error)## [1] 0.01525424svm_fit_bayes<-function(logCost, logGamma){
CV.error<-NULL
for (i in 1:5) {
valid.data <- subset(train.set, fold == i)
train.data <- subset(train.set, fold != i)
svmfit<-svm(Group~PC1+PC2, data = train.data, kernel="radial",
cost=exp(logCost), gamma=exp(logGamma))
svm.y<-valid.data$Group
svm.predy<-predict(svmfit, valid.data)
ith.test.error<- mean(svm.y!=svm.predy)
CV.error<-c(CV.error,(nrow(valid.data)/nrow(train.set))*ith.test.error)
}
list(Score=-sum(CV.error), pred=0)
}
set.seed(234)
OPT_Res<- BayesianOptimization(svm_fit_bayes, bounds= list(logCost = c(-5, 20),
logGamma = c(-9, 5)),
init_grid_dt = NULL, init_points = 50,
n_iter = 20, acq = "ucb", kappa =2.576,
eps=0, verbose = TRUE)## elapsed = 0.33 Round = 1 logCost = 13.6405 logGamma = -0.1100 Value = -0.0237
## elapsed = 0.19 Round = 2 logCost = 14.5428 logGamma = -3.6803 Value = -0.0186
## elapsed = 0.39 Round = 3 logCost = -4.4991 logGamma = -6.8452 Value = -0.6678
## elapsed = 0.23 Round = 4 logCost = 14.4021 logGamma = 2.3082 Value = -0.0390
## elapsed = 0.30 Round = 5 logCost = -3.3272 logGamma = -7.8940 Value = -0.6678
## elapsed = 0.07 Round = 6 logCost = 11.1199 logGamma = -6.9799 Value = -0.0203
## elapsed = 0.12 Round = 7 logCost = 18.2346 logGamma = -7.7917 Value = -0.0220
## elapsed = 0.15 Round = 8 logCost = 12.9411 logGamma = -2.5374 Value = -0.0203
## elapsed = 0.27 Round = 9 logCost = 18.1934 logGamma = 2.3218 Value = -0.0390
## elapsed = 0.12 Round = 10 logCost = 2.1058 logGamma = 0.5545 Value = -0.0339
## elapsed = 0.10 Round = 11 logCost = 8.8931 logGamma = -3.8455 Value = -0.0220
## elapsed = 0.08 Round = 12 logCost = 8.6925 logGamma = -2.1492 Value = -0.0220
## elapsed = 0.15 Round = 13 logCost = 9.5712 logGamma = -5.4319 Value = -0.0203
## elapsed = 0.26 Round = 14 logCost = 9.5747 logGamma = 3.1058 Value = -0.0441
## elapsed = 0.26 Round = 15 logCost = -4.9700 logGamma = -2.5619 Value = -0.6678
## elapsed = 0.11 Round = 16 logCost = 6.0279 logGamma = -3.4814 Value = -0.0322
## elapsed = 0.14 Round = 17 logCost = 2.8288 logGamma = 1.6296 Value = -0.0339
## elapsed = 0.16 Round = 18 logCost = 13.5004 logGamma = -1.9421 Value = -0.0203
## elapsed = 0.18 Round = 19 logCost = -1.5418 logGamma = 0.3706 Value = -0.0763
## elapsed = 1.27 Round = 20 logCost = 16.7944 logGamma = -0.5696 Value = -0.0271
## elapsed = 0.41 Round = 21 logCost = 8.0767 logGamma = 4.0595 Value = -0.0678
## elapsed = 0.17 Round = 22 logCost = 9.4776 logGamma = -4.1480 Value = -0.0186
## elapsed = 1.36 Round = 23 logCost = 16.6300 logGamma = -0.8016 Value = -0.0271
## elapsed = 0.18 Round = 24 logCost = 10.4356 logGamma = -4.6248 Value = -0.0186
## elapsed = 0.21 Round = 25 logCost = 7.2445 logGamma = -8.0562 Value = -0.0576
## elapsed = 0.20 Round = 26 logCost = 4.3700 logGamma = -3.6790 Value = -0.0424
## elapsed = 0.11 Round = 27 logCost = 12.4167 logGamma = -1.3037 Value = -0.0203
## elapsed = 0.34 Round = 28 logCost = -0.2072 logGamma = -3.5495 Value = -0.3000
## elapsed = 0.56 Round = 29 logCost = 15.9732 logGamma = -6.9054 Value = -0.0203
## elapsed = 0.36 Round = 30 logCost = 17.0627 logGamma = -7.2907 Value = -0.0153
## elapsed = 0.86 Round = 31 logCost = 10.4807 logGamma = -0.7788 Value = -0.0237
## elapsed = 0.13 Round = 32 logCost = 1.3078 logGamma = -1.4961 Value = -0.0576
## elapsed = 0.31 Round = 33 logCost = -0.5958 logGamma = -4.3707 Value = -0.4627
## elapsed = 0.23 Round = 34 logCost = 12.6207 logGamma = 2.8276 Value = -0.0390
## elapsed = 0.32 Round = 35 logCost = 8.3371 logGamma = 4.0253 Value = -0.0678
## elapsed = 0.17 Round = 36 logCost = 12.2033 logGamma = 0.0287 Value = -0.0271
## elapsed = 0.09 Round = 37 logCost = 12.5207 logGamma = -4.9540 Value = -0.0203
## elapsed = 0.40 Round = 38 logCost = -1.1632 logGamma = 4.3850 Value = -0.2254
## elapsed = 0.11 Round = 39 logCost = 7.6583 logGamma = -4.3597 Value = -0.0288
## elapsed = 0.20 Round = 40 logCost = 3.8680 logGamma = 2.5258 Value = -0.0373
## elapsed = 0.26 Round = 41 logCost = 9.5338 logGamma = 2.9501 Value = -0.0407
## elapsed = 0.26 Round = 42 logCost = 17.6858 logGamma = 2.9679 Value = -0.0390
## elapsed = 0.32 Round = 43 logCost = 16.1313 logGamma = -6.8699 Value = -0.0186
## elapsed = 0.35 Round = 44 logCost = 0.8071 logGamma = -6.9476 Value = -0.5593
## elapsed = 0.13 Round = 45 logCost = 11.4682 logGamma = -1.7771 Value = -0.0186
## elapsed = 0.43 Round = 46 logCost = 14.4283 logGamma = 4.9103 Value = -0.1136
## elapsed = 0.18 Round = 47 logCost = 1.0083 logGamma = -3.7983 Value = -0.1186
## elapsed = 0.15 Round = 48 logCost = 10.7092 logGamma = -3.7880 Value = -0.0203
## elapsed = 0.11 Round = 49 logCost = 9.8284 logGamma = 0.6458 Value = -0.0305
## elapsed = 0.26 Round = 50 logCost = -1.8423 logGamma = -1.8271 Value = -0.2932
## elapsed = 2.08 Round = 51 logCost = 20.0000 logGamma = -3.8279 Value = -0.0237
## elapsed = 0.40 Round = 52 logCost = 20.0000 logGamma = 5.0000 Value = -0.1271
## elapsed = 0.16 Round = 53 logCost = 5.5999 logGamma = 0.6218 Value = -0.0271
## elapsed = 0.44 Round = 54 logCost = -5.0000 logGamma = 5.0000 Value = -0.6678
## elapsed = 0.49 Round = 55 logCost = 2.1599 logGamma = 5.0000 Value = -0.1271
## elapsed = 0.36 Round = 56 logCost = 18.6350 logGamma = -5.2516 Value = -0.0203
## elapsed = 0.16 Round = 57 logCost = 0.5052 logGamma = 2.0277 Value = -0.0356
## elapsed = 6.62 Round = 58 logCost = 20.0000 logGamma = -0.7534 Value = -0.0288
## elapsed = 0.49 Round = 59 logCost = 5.0881 logGamma = -9.0000 Value = -0.3169
## elapsed = 0.16 Round = 60 logCost = 13.0671 logGamma = -9.0000 Value = -0.0220
## elapsed = 0.24 Round = 61 logCost = 20.0000 logGamma = -6.6654 Value = -0.0220
## elapsed = 0.30 Round = 62 logCost = 20.0000 logGamma = -9.0000 Value = -0.0220
## elapsed = 0.70 Round = 63 logCost = 7.1008 logGamma = 1.7864 Value = -0.0390
## elapsed = 1.03 Round = 64 logCost = 4.7301 logGamma = 5.0000 Value = -0.1271
## elapsed = 3.95 Round = 65 logCost = 18.6263 logGamma = -2.0736 Value = -0.0254
## elapsed = 0.10 Round = 66 logCost = 10.0748 logGamma = -9.0000 Value = -0.0407
## elapsed = 0.43 Round = 67 logCost = 17.6983 logGamma = 5.0000 Value = -0.1271
## elapsed = 0.08 Round = 68 logCost = 16.9965 logGamma = -9.0000 Value = -0.0186
## elapsed = 0.13 Round = 69 logCost = 3.7113 logGamma = -1.7333 Value = -0.0339
## elapsed = 0.12 Round = 70 logCost = 11.7444 logGamma = -9.0000 Value = -0.0288
##
## Best Parameters Found:
## Round = 30 logCost = 17.0627 logGamma = -7.2907 Value = -0.0153 OPT_Res$Best_Par## logCost logGamma
## 17.062727 -7.290688 as.numeric(exp(OPT_Res$Best_Par["logCost"]))## [1] 25718660 as.numeric(exp(OPT_Res$Best_Par["logGamma"]))## [1] 0.0006818588 CV.error<-NULL
for (i in 1:5) {
valid.data <- subset(train.set, fold == i)
train.data <- subset(train.set, fold != i)
svmfit<-svm(Group~PC1+PC2, data = train.data, kernel="radial",
cost=exp(OPT_Res$Best_Par["logCost"]),
gamma=exp(OPT_Res$Best_Par["logGamma"]))
svm.y<-valid.data$Group
svm.predy<-predict(svmfit, valid.data)
ith.test.error<- mean(svm.y!=svm.predy)
CV.error<-c(CV.error,(nrow(valid.data)/nrow(train.set))*ith.test.error)
}
sum(CV.error)## [1] 0.01525424