Summary of 18_Xgboost
Extreme Gradient Boosting (Xgboost)
- n_jobs: 6
- objective: multi:softprob
- eta: 0.1
- max_depth: 5
- min_child_weight: 1
- subsample: 1.0
- colsample_bytree: 1.0
- eval_metric: f1
- num_class: 6
- explain_level: 1
Validation
- validation_type: kfold
- k_folds: 5
- shuffle: True
- stratify: True
- random_seed: 42
Optimized metric
f1
Training time
36.4 seconds
Metric details
| 0 | 1 | 2 | 3 | 4 | 5 | accuracy | macro avg | weighted avg | logloss | |
|---|---|---|---|---|---|---|---|---|---|---|
| precision | 0.970424 | 0.964171 | 0.973347 | 0.98467 | 0.991238 | 0.996877 | 0.980034 | 0.980121 | 0.980121 | 0.067485 |
| recall | 0.98619 | 0.964789 | 0.968878 | 0.991255 | 0.989612 | 0.975548 | 0.980034 | 0.979378 | 0.980034 | 0.067485 |
| f1-score | 0.978243 | 0.96448 | 0.971107 | 0.987952 | 0.990424 | 0.986097 | 0.980034 | 0.979717 | 0.980042 | 0.067485 |
| support | 2462 | 1562 | 1960 | 1944 | 1829 | 1963 | 0.980034 | 11720 | 11720 | 0.067485 |
Confusion matrix
| Predicted as 0 | Predicted as 1 | Predicted as 2 | Predicted as 3 | Predicted as 4 | Predicted as 5 | |
|---|---|---|---|---|---|---|
| Labeled as 0 | 2428 | 7 | 5 | 19 | 0 | 3 |
| Labeled as 1 | 2 | 1507 | 46 | 1 | 6 | 0 |
| Labeled as 2 | 7 | 48 | 1899 | 1 | 4 | 1 |
| Labeled as 3 | 12 | 1 | 1 | 1927 | 3 | 0 |
| Labeled as 4 | 8 | 0 | 0 | 9 | 1810 | 2 |
| Labeled as 5 | 45 | 0 | 0 | 0 | 3 | 1915 |
Learning curves
Permutation-based Importance
Confusion Matrix
Normalized Confusion Matrix
ROC Curve
Precision Recall Curve
