A classification model on a 95% negative / 5% positive dataset predicts 'negative' for every observation. What is the F1 score for the positive class?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — if your model always predicts negative, it never catches a positive case, so positive-class recall is zero. With no true positives, the positive-class F1 score comes out to 0.00.
Full Explanation
The 0.00 option is right because always predicting negative yields zero true positives for the positive class, so positive recall is 0; precision is undefined and treated as 0, giving F1 = 0. The 0.95 option is majority-class accuracy, not F1. The 0.50 option has no basis. The 0.05 option is class proportion, not F1.