Skip to content

Summary of 2_Xgboost_Stacked

<< Go back

Extreme Gradient Boosting (Xgboost)

  • n_jobs: -1
  • objective: multi:softprob
  • eta: 0.075
  • max_depth: 8
  • min_child_weight: 5
  • 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

18.1 seconds

Metric details

0 1 2 3 4 5 accuracy macro avg weighted avg logloss
precision 0.733815 0.76316 0.770978 0.958804 0.978763 0.976803 0.857186 0.863721 0.863721 0.69563
recall 0.917694 0.750378 0.705709 0.920578 0.957265 0.891489 0.857186 0.857186 0.857186 0.69563
f1-score 0.815518 0.756715 0.736901 0.939302 0.967895 0.932199 0.857186 0.858088 0.858088 0.69563
support 6296 6296 6296 6296 6296 6296 0.857186 37776 37776 0.69563

Confusion matrix

Predicted as 0 Predicted as 1 Predicted as 2 Predicted as 3 Predicted as 4 Predicted as 5
Labeled as 0 5777.8 102.863 161.088 118.39 44.6387 91.2182
Labeled as 1 438.148 4724.38 1095.37 19.0499 19.0499 0
Labeled as 2 446.173 1363.31 4443.14 30.9843 6.19685 6.19685
Labeled as 3 420.491 0 45.4585 5795.96 34.0939 0
Labeled as 4 161.436 0 17.9373 53.812 6026.94 35.8746
Labeled as 5 629.6 0 0 26.7915 26.7915 5612.82

Learning curves

Learning curves

Confusion Matrix

Confusion Matrix

Normalized Confusion Matrix

Normalized Confusion Matrix

ROC Curve

ROC Curve

Precision Recall Curve

Precision Recall Curve

<< Go back