Confusion matrix for a logistic glm model in R. Helpful for comparing glm to randomForests.

gistfile1.r

confusion.glm <- function(data, model) {
  prediction <- ifelse(predict(model, data, type='response') > 0.5, TRUE, FALSE)
  confusion  <- table(prediction, as.logical(model$y))
  confusion  <- cbind(confusion, c(1 - confusion[1,1]/(confusion[1,1]+confusion[2,1]), 1 - confusion[2,2]/(confusion[2,2]+confusion[1,2])))
  confusion  <- as.data.frame(confusion)
  names(confusion) <- c('FALSE', 'TRUE', 'class.error')
  confusion
}

In the case of a prediction vector of all True or all False [Class-Error 100%] this throws an error which is fixed by changing to
confusion <- table(factor(prediction, levels = c(FALSE, TRUE)), as.logical(model$y))

Great! Thank