R-Squared Score

Problem

Compute the coefficient of determination R^2 = 1 - SS_res / SS_tot, where SS_res = sum((y_i - pred_i)^2) and SS_tot = sum((y_i - mean_y)^2).

If SS_tot is 0, return 1.0 when SS_res is also 0 and 0.0 otherwise. Empty input returns 0.0.

Hint

Compare the residual sum of squares to the variance of y_true.

case 1

in: [[1,2,3],[1,2,3]]

expected: 1

case 2

in: [[1,2,3],[2,2,2]]

expected: 0

case 3

in: [[1,2,3],[3,2,1]]

expected: -3

case 4

in: [[5,5,5],[5,5,6]]

expected: 0

Starter codePython

def r2_score(y_true, y_pred):
    # Your code here
    pass

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