我尝试从 https://en.wikipedia.org/wiki/Coefficient_of_determination#Definitions 实现公式,但结果不同。为什么会这样?
y_true = np.array([1, 1, 0])
y_pred = np.array([1, 0, 1])
r2 = r2_score(y_true, y_pred)
print(r2)
y_true_mean = statistics.mean(y_true)
r2 = 1 - np.sum((y_true - y_pred) ** 2) / np.sum((y_true - y_true_mean) ** 2)
print(r2)
-1.9999999999999996
0.0
回答1
不确定您使用什么 statistics 包,但似乎不同的结果源自那里。尝试使用 np.mean
代替。这给出了与 sklearn 相同的 R2:
import numpy as np
y_true = np.array([1, 1, 0])
y_pred = np.array([1, 0, 1])
y_true_mean = np.mean(y_true)
r2 = 1 - np.sum((y_true - y_pred) ** 2) / np.sum((y_true - y_true_mean) ** 2)
print(r2)