Confusion matrix error

[rczen]

Hello,

I am asking for the confusion matrix using the following line:

confusionMatrix(cart.model, test$meet_kpi, positive='No')

and get the following error:

Error in match.arg(norm, c("none", "overall", "average")) :
'arg' must be NULL or a character vector

I would like to find out what is the nature of this error, what is the complaint.

Thanks in advance,

Ronen

[rczen]

problem solved.

[jtorresec]

Hi, can you show how did you solve this problem? I have de same

[cramezan]

He was predicting on his model in the confusion matrix, rather than the prediction itself. I just ran into error this myself.

For my code which produced the error:

svm.model001 <- train(class_name~., data=Train001, method = "svmRadial",
tuneLength = 10,
preProcess = c("center", "scale"),
trControl = trainctrl,
metric="Kappa")

svm.predict001 <-predict(svm.model001, DelTest, verboseIter = TRUE)
confusionMatrix(svm.model001, as.factor(DelTest$class_name))

The issue is in the confusionMatrix line. It should read my stored prediction variable instead of the model variable.
confusionMatrix(svm.predict001, as.factor(DelTest$class_name))

[niharikakotaru]

He was predicting on his model in the confusion matrix, rather than the prediction itself. I just ran into error this myself.

For my code which produced the error:

svm.model001 <- train(class_name~., data=Train001, method = "svmRadial", tuneLength = 10, preProcess = c("center", "scale"), trControl = trainctrl, metric="Kappa")

svm.predict001 <-predict(svm.model001, DelTest, verboseIter = TRUE) confusionMatrix(svm.model001, as.factor(DelTest$class_name))

The issue is in the confusionMatrix line. It should read my stored prediction variable instead of the model variable. confusionMatrix(svm.predict001, as.factor(DelTest$class_name))

Thank you so much! it worked