R Data Analysis Cookbook - Second Edition

How to do it...

To classify using SVM, follow these steps:

1. Load the e1071 and caret packages:

> library(e1071) 
> library(caret)

2. Read the data:

> bn <- read.csv("banknote-authentication.csv") 

3. Convert the outcome variable class to a factor:

> bn$class <- factor(bn$class) 

4. Partition the data:

> set.seed(1000) 
> t.idx <- createDataPartition(bn$class, p=0.7, list=FALSE) 

5. Build the model:

> mod <- svm(class ~ ., data = bn[t.idx,]) 

6. Check model performance on training data by generating an error/classification confusion matrix:

> table(bn[t.idx,"class"], fitted(mod), dnn = c("Actual", "Predicted")) 
      Predicted 
Actual   0   1 
     0 534   0 
     1   0 427 

7. Check model performance on the validation partition:

> pred <- predict(mod, bn[-t.idx,]) > table(bn[-t.idx, ...