1

I don't know how to interpret the svm summary outputs in R. I show you the reproducible code below. data <- read.csv(file.choose (), header = TRUE, sep=';') set.seed(1234) splitIndex <- createDataPartition( dati[,outcomeName], p = .75, list = FALSE, times = 1) trainDF <- dati[ splitIndex,]

 testDF  <- dati[-splitIndex,]

 model_svm <- svm(Y~.,data = trainDF) 

> model_svm_test <- svm(Y~.,data = testDF)

> summary(model_svm)


THESE ARE THE TWO SUMMARY OUTPUTS. THE FIRST ONE FOR TRAIN AND THE SECOND ONE FOR TEST
Call:
svm(formula = Y ~ ., data = trainDF)


Parameters:
   SVM-Type:  eps-regression 
 SVM-Kernel:  radial 
       cost:  1 
      gamma:  0.0625 
    epsilon:  0.1 


Number of Support Vectors:  1886





> summary(model_svm_test)

Call:
svm(formula = Y ~ ., data = testDF)


Parameters:
   SVM-Type:  eps-regression 
 SVM-Kernel:  radial 
       cost:  1 
      gamma:  0.0625 
    epsilon:  0.1 


Number of Support Vectors:  799
Ferdi
  • 4,882
  • 7
  • 42
  • 62
Dalila
  • 13
  • 1
  • 1
  • 7
  • What do you *not* understand here, after you've reviewed the documentation? – John M. Apr 07 '17 at 22:54
  • Regarding SVM type you can read this question: https://stats.stackexchange.com/questions/237382/difference-between-the-types-of-svm – Ferdi Dec 15 '17 at 12:24

0 Answers0