R-squared is a statistical measure that represents the goodness of fit. The R-squared score for a perfect fit of a regression model is 1. i.e, the model is fitted well as the r-squared value is close to 1.
note: The best possible score is 1.0
Mathematical Formula for R² score:
R² = 1- SS(res) / SS(tot)
SS(res) is the sum squared of residual errors.
SS(tot) is the total sum of errors.
For example, we have values of y and ŷ as,
y = 12, 18 , 15
ŷ = 11, 19, 15
here, y is the actual value and ŷ is the predicted value.
now, SS(res) = 2 , SS(tot) = 18
thus, R² = 1 – (2 / 18)
R² = 0.88
from sklearn.metrics import r2_scorey_true = [3, 4.3, 2, 9]
y_pred = [3.4, 3.9, 1.8, 8.2]r2_score(y_true, y_pred)
I hope this might have helped you. If you ❤️ my content do follow.