Precision, Recall, F1

Problem

Compute precision, recall, and F1 score for binary classification.

A positive label is 1 by default. Return [precision, recall, f1].

precision = TP / (TP + FP) recall = TP / (TP + FN) F1 = 2 * precision * recall / (precision + recall)

Any undefined value (zero denominator) is 0.0.

Hint

TP = both true and pred are positive. FP = pred positive but true negative. FN = pred negative but true positive.

case 1

in: [[1,0,1,1,0],[1,0,0,1,0]]

expected: [1,0.6666666666666666,0.8]

case 2

in: [[1,1,0,0],[1,1,1,0]]

expected: [0.6666666666666666,1,0.8]

case 3

in: [[1,1,1],[0,0,0]]

expected: [0,0,0]

case 4

in: [[0,0,0],[1,1,1]]

expected: [0,0,0]

Starter codePython

def precision_recall_f1(y_true, y_pred, positive=1):
    # Returns [precision, recall, f1]
    # Your code here
    pass

4 test cases · run your code against them in the editor