compare actual values vs predicted values in decision tree

Question

How to compare the accuracy of actual values wrt predicted values in R after decision prediction?

Answer 1

You can compare test data using table() to get a confusion matrix.

1. Create your decision tree.

decision_tree = rpart(predicting value~.,train data)

2. Use the tree to predict for test data.

predicted_table = predict(decision_tree, test data, type = "class")

3. Now use table(predicting variable,predicted model). 

table(predicting variable, predicted_table)

The table gives a confusion matrix like below. It displays the number of records with a true positive, false positive. true negative, false negative count. The row and column can be Yes/No or True/False.

	Yes/True	No/False
Yes/True
No/False

4. Calculate accuracy as count in [Yes,Yes] + [No,No] / [count of all cells]).