ML Using R Section 38 x Fold Validation

Section 38 K Fold Validation

df <-  read.csv("G:\\RStudio\\udemy\\ml\\Machine Learning AZ\\Part 3 - Classification\\Section 17 - Kernel SVM\\Kernel_SVM\\Social_Network_Ads.csv")
head(df)

Select the fields that we will be working with

df <- df[,3:5]
head(df)

Split dataset into training and test set (300 training, 100 test)

library(caTools)
set.seed(1234)
split <- sample.split(df$Purchased, SplitRatio = 0.75)
training_set <- subset(df, split == TRUE)
test_set <- subset(df, split == FALSE)

For Classification,it is better to do feature scaling (normalization)

# Feature Scaling 1 age, 2 is salary
training_set[,1:2] <-  scale(training_set[,1:2])
test_set[,1:2] <-  scale(test_set[,1:2])

Fitting Classifier to the Training Set

# Create the classifier here
# install.packages("e1071")
# you can also use kernlab
library(e1071)
classifier <- svm(formula = Purchased ~ Age + EstimatedSalary,
                  data = training_set,
                  type = "C-classification",
                  kernel = "radial"
                  ) 
summary(classifier)

Call:
svm(formula = Purchased ~ Age + EstimatedSalary, data = training_set, type = "C-classification", 
    kernel = "radial")


Parameters:
   SVM-Type:  C-classification 
 SVM-Kernel:  radial 
       cost:  1 
      gamma:  0.5 

Number of Support Vectors:  80

 ( 38 42 )


Number of Classes:  2 

Levels: 
 0 1

Predicting the test set results

y_pred <-  predict(classifier, newdata=test_set[-3])
y_pred

  5  15  19  25  29  40  42  43  49  51  54  55  66  74  76  77  78  90  92 100 104 106 110 112 120 133 136 
  0   0   1   1   0   0   0   1   1   0   0   0   0   1   1   0   0   0   1   0   1   0   0   0   0   0   0 
137 141 142 143 144 145 153 157 159 164 166 172 174 179 181 183 184 195 197 202 203 216 218 221 223 228 229 
  0   0   0   0   0   0   0   1   0   0   0   1   0   0   0   1   0   0   0   1   1   1   0   0   1   1   0 
235 238 239 240 242 244 245 249 250 254 256 258 271 273 275 286 287 290 291 294 301 303 305 309 318 319 327 
  1   0   1   1   0   1   0   0   0   1   1   0   1   1   1   0   0   0   1   0   1   1   0   1   0   1   0 
330 332 333 338 341 343 351 353 354 357 360 361 363 368 369 373 386 387 394 
  1   1   0   0   1   0   1   0   0   1   0   1   1   1   0   0   1   1   1 
Levels: 0 1

Evaluate the prediction using confusion Matrix.

# Making the confusion matrix
# [3] refers to the outcome
cm <- table(test_set[,3], y_pred)
cm

   y_pred
     0  1
  0 55  9
  1  4 32

Applying K-fold cross validation

# Applying K-fold cross validation
# install.packages("caret")
library(caret)
folds = createFolds(training_set$Purchased, k = 10)
cv = lapply(folds, function(x){
  training_fold <-  training_set[-x, ]
  test_fold <-  training_set[x, ]
  classifier <- svm(formula = Purchased ~ Age + EstimatedSalary,
                  data = training_fold,
                  type = "C-classification",
                  kernel = "radial"
                  ) 
  y_pred <-  predict(classifier, newdata=test_fold[-3])
  cm <- table(test_fold[,3], y_pred)
  accuracy = (cm[1,1]+ cm[2,2]) / (cm[1,1]+ cm[2,2]+ cm[1,2]+ cm[2,1])
  return(accuracy)
  
})
accuracy <- mean(as.numeric(cv))
accuracy

[1] 0.9133333