Measuring model performance with a confusion matrix

To measure the performance of a classification model, we can first generate a classification table based on our predicted label and actual label. We then use a confusion matrix to obtain performance measures such as precision, recall, specificity, and accuracy. In this recipe, we will demonstrate how to retrieve a confusion matrix using the caret package.

Getting ready

You need to have the previous recipes completed by generating a classification model, and assign the model to the variable fit.

How to do it…

Perform the following steps to generate classification measurement:

1. Predict labels using the fitted model, fit:

   > pred = predict(fit, testset[,! names(testset) %in% c("buy")], type="class")
   

2. Generate a classification table:

   > table(pred, testset[,c("buy")])
        
   pred  no yes
     no  11   1
     yes  0   8
   

3. Lastly, generate a confusion matrix using prediction results and actual labels from the testing dataset:

   > confusionMatrix(pred, testset...