Table 2.
Performance achieved by scikit ML on the composition of the diatom.
| Methods (Parameters) | Main Dataset | Validation Dataset | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Sen | Spc | Acc | MCC | AUC | Sen | Spc | Acc | MCC | AUC | |
| RF (n_estimators = 100) | 73.61 | 74.03 | 73.82 | 0.48 | 0.83 | 78.46 | 74.36 | 76.41 | 0.53 | 0.86 |
| KNN (n_neighbors = 10,algorithm = ‘ball_tree',weights = ‘uniform') |
72.32 | 61.59 | 66.95 | 0.34 | 0.81 | 73.5 | 72.65 | 73.08 | 0.46 | 0.84 |
| Ridge (alpha = 1) | 57.51 | 57.51 | 57.51 | 0.15 | 0.72 | 55.56 | 63.25 | 59.4 | 0.19 | 0.75 |
| Extratree (n_estimators = 200) | 75.54 | 73.18 | 74.36 | 0.49 | 0.87 | 77.78 | 74.19 | 75.98 | 0.52 | 0.88 |