#MEMBUKA FILE DATA
dataDirectory <- "D:/SVM/Golongan B/"
data <- read.csv(paste(dataDirectory,'Golongan B Train.txt', sep=""),header = TRUE)
plot(data, pch=16)
#Install Package
install.packages("e1071")
#Load Library
library(e1071)
#Create svm model
model <- svm( y ~ x , data)
#Make a prediction for each x
predictedY <- predict(model, data)
points(data$x, predictedY, col = "red",pch=4)
#perform a grid search
tuneResult <- tune(svm, y ~ x, data = data,kernel="radial",ranges = list(epsilon = seq(0,1,0.1), cost = 2^(-5:10), gamma = 2^(-6:3)))
print(tuneResult)
summary(tuneResult)
getOption("max.print")
options(max.print = 99999999)
out <- capture.output(summary(tuneResult))
cat("My title", out, file="summary_of_tune_Result_Data_Training_Gol_B.txt", sep="n", append=TRUE)
tunedModel <- tuneResult$best.model
tunedModelY <- predict(tunedModel, data)
points(data$x,tunedModelY,col = "green",pch=4)
print(tunedModelY)
dataDirectory <- "D:/SVM/Golongan B/"
data <- read.csv(paste(dataDirectory,'Golongan B Test.txt', sep=""),header = TRUE)
plot(data, pch=16)
model <- svm(y ~ x, data = data , kernel="radial" , epsilon = 0.2 , cost = 16 , gamma = 0.5)
predictedY <- predict(model, data)
points(data$x, predictedY, col = "red",pch=4)
print(model)
tunedModeltest <- tuneResult$best.model
tunedModeltesting <- predict(tunedModeltest, data)
points(data$x,tunedModeltesting,col = "green",pch=4)
print(tunedModeltesting)
#Load Library
library(e1071)
x <- c(1:12)
y <- c(18.2, 17.1, 17.1, 16.5, 17.5, 16.2, 18.2, 17.3, 16.5, 18.1, 18.1, 16.7)
DF <- data.frame(x = x, y = y)
nextvalues <- c(13:18)
model <- svm(y ~ x, kernel = "radial", epsilon= 0.2, gamma = 16, cost = 0.5)
predict (model , newdata = data.frame(x =nextvalues))
#MEMBUKA FILE DATA
dataDirectory <- "D:/SVM/Golongan AB/"
data <- read.csv(paste(dataDirectory,'Golongan AB Train.txt', sep=""),header = TRUE)
plot(data, pch=16)
#Install Package
install.packages("e1071")
#Load Library
library(e1071)
#Create svm model
model <- svm( y ~ x , data)
#Make a prediction for each x
predictedY <- predict(model, data)
points(data$x, predictedY, col = "red",pch=4)
#perform a grid search
tuneResult <- tune(svm, y ~ x, data = data,kernel="radial",ranges = list(epsilon = seq(0,1,0.1), cost = 2^(-5:10), gamma = 2^(-6:3)))
print(tuneResult)
summary(tuneResult)
getOption("max.print")
options(max.print = 99999999)
out <- capture.output(summary(tuneResult))
cat("My title", out, file="summary_of_tune_Result_Data_Training_Gol_AB.txt", sep="n", append=TRUE)
tunedModel <- tuneResult$best.model
tunedModelY <- predict(tunedModel, data)
points(data$x,tunedModelY,col = "green",pch=4)
print(tunedModelY)
dataDirectory <- "D:/SVM/Golongan AB/"
data <- read.csv(paste(dataDirectory,'Golongan AB Test.txt', sep=""),header = TRUE)
plot(data, pch=16)
model <- svm(y ~ x, data = data , kernel="radial" , epsilon = 1 , cost = 4 , gamma = 0.25)
predictedY <- predict(model, data)
points(data$x, predictedY, col = "red",pch=4)
print(model)
tunedModeltest <- tuneResult$best.model
tunedModeltesting <- predict(tunedModeltest, data)
points(data$x,tunedModeltesting,col = "green",pch=4)
print(tunedModeltesting)
#Load Library
library(e1071)
x <- c(1:12)
y <- c(8.9, 6, 7, 8.1, 6.2, 8.1, 8.1, 6.2, 7.6, 9.6, 6.9, 6.7)
DF <- data.frame(x = x, y = y)
nextvalues <- c(13:18)
model <- svm(y ~ x, kernel = "radial", epsilon= 1, gamma = 0.25, cost = 4)
predict (model , newdata = data.frame(x =nextvalues))
