Table 1.
Training Set | Test Set | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|
LR | Score | r² | MAE | RMSE | RAE | RRSE | q² | MAE | RMSE | RAE | RRSE |
0.1 | 0.80 | 0.79 | 0.65 | 0.82 | 65 | 68 | 0.85 | 0.6 | 0.75 | 59 | 61 |
0.2 | 0.76 | 0.80 | 0.58 | 0.76 | 59 | 64 | 0.78 | 0.66 | 0.84 | 65 | 68 |
0.3 | 0.77 | 0.79 | 0.60 | 0.77 | 60 | 65 | 0.78 | 0.67 | 0.89 | 66 | 72 |
0.4 | 0.75 | 0.80 | 0.58 | 0.77 | 59 | 64 | 0.77 | 0.69 | 0.94 | 68 | 76 |
Note: LR = learning rate; r2 = correlation coefficient for the training set; q2 = correlation coefficient for the test set (r2pred); RMSE = root mean square error; MAE = mean absolute error; RAE = relative absolute error; RRSE = root relative squared error; score = (1 − |(r2 − q2)|) × q2.