Hi all!
I am having problems with using SVM in R
I have a data frame `trainData` which contains 198 rows and looks like
Matchup Win HomeID AwayID A_TWPCT A_WST6 A_SEED B_TWPCT B_WST6
B_SEED2010_1115_1457 1 1115 1457 0.531 5 16 0.567 4
16
2010_1124_1358 1 1124 1358 0.774 5 3 0.75 5 14
...
The testData is similar.
In order to use SVM, I have to change the response variable Win to a factor. I
tried the below:
trainDataSVM <- trainData
trainDataSVM$Win <- factor(trainDataSVM$Win)
svmfit =svm (Win ~ A_WST6 + A_SEED + B_WST6 + B_SEED , data = trainDataSVM
, kernel ="linear", cost =10,scale =FALSE, probability=TRUE )
testDataSVM<-testData
testDataSVM$Win <-factor(testDataSVM$Win)
predictions_SVM <- predict(bestmod, testDataSVM, type =
"response",probability=TRUE)
However, I get the message
Error in matrix(ret$prob, nrow = nrow(newdata), byrow = TRUE, dimnames =
list(rowns, :
length of 'dimnames' [2] not equal to array extent
If I re-run the code except not changing trainDataSVM$Win and testDataSVM$Win
to factors, if I print out predictions_SVM, I get the message named numeric(0)
How do I fix this?
Thanks!
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
