Lab 3: Code cleanup for assignment 3

lab3/Lab3Block1_2021_SVMs_St.R

@@ -7,43 +7,78 @@ set.seed(1234567890)
 
 data(spam)
 foo <- sample(nrow(spam))
-spam <- spam[foo,]
+spam <- spam[foo, ]
 tr <- spam[1:3000, ]
 va <- spam[3001:3800, ]
 trva <- spam[1:3800, ]
-te <- spam[3801:4601, ] 
+te <- spam[3801:4601, ]
 
 by <- 0.3
 err_va <- NULL
-for(i in seq(by,5,by)){
-  filter <- ksvm(type~.,data=tr,kernel="rbfdot",kpar=list(sigma=0.05),C=i,scaled=FALSE)
-  mailtype <- predict(filter,va[,-58])
-  t <- table(mailtype,va[,58])
-  err_va <-c(err_va,(t[1,2]+t[2,1])/sum(t))
+for (i in seq(by, 5, by)) {
+  filter <- ksvm(
+    type ~ .,
+    data = tr,
+    kernel = "rbfdot",
+    kpar = list(sigma = 0.05),
+    C = i,
+    scaled = FALSE
+  )
+  mailtype <- predict(filter, va[, -58])
+  t <- table(mailtype, va[, 58])
+  err_va <- c(err_va, (t[1, 2] + t[2, 1]) / sum(t))
 }
 
-filter0 <- ksvm(type~.,data=tr,kernel="rbfdot",kpar=list(sigma=0.05),C=which.min(err_va)*by,scaled=FALSE)
-mailtype <- predict(filter0,va[,-58])
-t <- table(mailtype,va[,58])
-err0 <- (t[1,2]+t[2,1])/sum(t)
+filter0 <- ksvm(
+  type ~ .,
+  data = tr,
+  kernel = "rbfdot",
+  kpar = list(sigma = 0.05),
+  C = which.min(err_va) * by,
+  scaled = FALSE
+)
+mailtype <- predict(filter0, va[, -58])
+t <- table(mailtype, va[, 58])
+err0 <- (t[1, 2] + t[2, 1]) / sum(t)
 err0
 
-filter1 <- ksvm(type~.,data=tr,kernel="rbfdot",kpar=list(sigma=0.05),C=which.min(err_va)*by,scaled=FALSE)
-mailtype <- predict(filter1,te[,-58])
-t <- table(mailtype,te[,58])
-err1 <- (t[1,2]+t[2,1])/sum(t)
+filter1 <- ksvm(
+  type ~ .,
+  data = tr,
+  kernel = "rbfdot",
+  kpar = list(sigma = 0.05),
+  C = which.min(err_va) * by,
+  scaled = FALSE
+)
+mailtype <- predict(filter1, te[, -58])
+t <- table(mailtype, te[, 58])
+err1 <- (t[1, 2] + t[2, 1]) / sum(t)
 err1
 
-filter2 <- ksvm(type~.,data=trva,kernel="rbfdot",kpar=list(sigma=0.05),C=which.min(err_va)*by,scaled=FALSE)
-mailtype <- predict(filter2,te[,-58])
-t <- table(mailtype,te[,58])
-err2 <- (t[1,2]+t[2,1])/sum(t)
+filter2 <- ksvm(
+  type ~ .,
+  data = trva,
+  kernel = "rbfdot",
+  kpar = list(sigma = 0.05),
+  C = which.min(err_va) * by,
+  scaled = FALSE
+)
+mailtype <- predict(filter2, te[, -58])
+t <- table(mailtype, te[, 58])
+err2 <- (t[1, 2] + t[2, 1]) / sum(t)
 err2
 
-filter3 <- ksvm(type~.,data=spam,kernel="rbfdot",kpar=list(sigma=0.05),C=which.min(err_va)*by,scaled=FALSE)
-mailtype <- predict(filter3,te[,-58])
-t <- table(mailtype,te[,58])
-err3 <- (t[1,2]+t[2,1])/sum(t)
+filter3 <- ksvm(
+  type ~ .,
+  data = spam,
+  kernel = "rbfdot",
+  kpar = list(sigma = 0.05),
+  C = which.min(err_va) * by,
+  scaled = FALSE
+)
+mailtype <- predict(filter3, te[, -58])
+t <- table(mailtype, te[, 58])
+err3 <- (t[1, 2] + t[2, 1]) / sum(t)
 err3
 
 # Questions
@@ -58,25 +93,30 @@ gaussian_kernel <- function(x_i, x_star, sigma) {
   return(exp(-sum((x_i - x_star)^2) / (2 * sigma^2)))
 }
 
-sv<-alphaindex(filter3)[[1]]
-co<-coef(filter3)[[1]]
-inte<- - b(filter3)
-k<-NULL
-for(i in 1:10){ # We produce predictions for just the first 10 points in the dataset.
-  k2<-0
-  test_point <- spam[i, -58]
-  for(j in 1:length(sv)){
-    
-    support_vector <- spam[sv[j], -58]
-    
-    kernel_value <- gaussian_kernel(support_vector, test_point, sigma = 0.05) 
 
+sv <- alphaindex(filter3)[[1]]
+co <- coef(filter3)[[1]]
+inte <- -b(filter3)
+k <- NULL
+for (i in 1:10) {
+  # We produce predictions for just the first 10 points in the dataset.
+  
+  k2 <- 0
+  data_point <- spam[i, -58]
+  
+  for (j in 1:length(sv)) {
+    support_vector <- spam[sv[j], -58]
+    kernel_value <- gaussian_kernel(support_vector, data_point, sigma = 0.05)
     k2 <- k2 + co[j] * kernel_value
     
   }
+  
   k2 <- k2 + inte
+  print(k2)
   k <- c(k, sign(k2))
   
 }
+
+# Only first correct, close to decision boundary (0.006292512).
 k
-predict(filter3,spam[1:10,-58], type = "decision")
+predict(filter3,spam[1:10,-58], type = "decision")
\ No newline at end of file