Skip to content

Summary of 1_Default_Xgboost_GoldenFeatures_Stacked

<< 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

14.1 seconds

Metric details

0 1 2 3 4 5 accuracy macro avg weighted avg logloss
precision 0.764518 0.742913 0.811988 0.949332 0.976795 0.968474 0.864058 0.869004 0.869004 0.876218
recall 0.899199 0.813918 0.668307 0.935018 0.957265 0.910638 0.864058 0.864058 0.864058 0.876218
f1-score 0.826407 0.776796 0.733175 0.942121 0.966932 0.938666 0.864058 0.864016 0.864016 0.876218
support 6296 6296 6296 6296 6296 6296 0.864058 37776 37776 0.876218

Confusion matrix

Predicted as 0 Predicted as 1 Predicted as 2 Predicted as 3 Predicted as 4 Predicted as 5
Labeled as 0 5661.35 112.567 207.667 157.206 48.5203 108.686
Labeled as 1 409.573 5124.43 723.897 9.52496 28.5749 0
Labeled as 2 371.811 1660.76 4207.66 30.9843 18.5906 6.19685
Labeled as 3 363.668 0 11.3646 5886.87 34.0939 0
Labeled as 4 89.6866 0 17.9373 89.6866 6026.94 71.7493
Labeled as 5 509.038 0 13.3957 26.7915 13.3957 5733.38

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