Skip to content

Summary of 1_Default_Xgboost_RandomFeature

<< Go back

Extreme Gradient Boosting (Xgboost)

  • n_jobs: -1
  • objective: multi:softprob
  • eta: 0.075
  • max_depth: 6
  • 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

19.1 seconds

Metric details

0 1 2 3 4 5 accuracy macro avg weighted avg logloss
precision 0.752502 0.771945 0.771988 0.957716 0.978546 0.988859 0.864249 0.870259 0.870259 0.327912
recall 0.923551 0.771558 0.712598 0.936823 0.960114 0.880851 0.864249 0.864249 0.864249 0.327912
f1-score 0.829298 0.771751 0.741105 0.947154 0.969242 0.931736 0.864249 0.865048 0.865048 0.327912
support 6296 6296 6296 6296 6296 6296 0.864249 37776 37776 0.327912

Confusion matrix

Predicted as 0 Predicted as 1 Predicted as 2 Predicted as 3 Predicted as 4 Predicted as 5
Labeled as 0 5814.68 71.8101 190.2 110.626 52.402 56.2836
Labeled as 1 323.849 4857.73 1076.32 9.52496 28.5749 0
Labeled as 2 402.795 1363.31 4486.52 37.1811 0 6.19685
Labeled as 3 363.668 0 22.7292 5898.24 11.3646 0
Labeled as 4 125.561 0 35.8746 89.6866 6044.88 0
Labeled as 5 696.579 0 0 13.3957 40.1872 5545.84

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