Summary of 2_Default_Xgboost_GoldenFeatures

<< Go back

Extreme Gradient Boosting (Xgboost)

• n_jobs: 6
• 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

40.3 seconds

Metric details

	0	1	2	3	4	5	accuracy	macro avg	weighted avg	logloss
precision	0.966521	0.964789	0.972848	0.981623	0.992869	0.998433	0.979181	0.979514	0.97931	0.0676023
recall	0.984972	0.964789	0.968878	0.989198	0.989612	0.974019	0.979181	0.978578	0.979181	0.0676023
f1-score	0.975659	0.964789	0.970859	0.985396	0.991238	0.986075	0.979181	0.979003	0.979198	0.0676023
support	2462	1562	1960	1944	1829	1963	0.979181	11720	11720	0.0676023

Confusion matrix

	Predicted as 0	Predicted as 1	Predicted as 2	Predicted as 3	Predicted as 4	Predicted as 5
Labeled as 0	2425	6	6	23	0	2
Labeled as 1	2	1507	46	2	5	0
Labeled as 2	8	47	1899	2	4	0
Labeled as 3	17	2	0	1923	2	0
Labeled as 4	9	0	1	8	1810	1
Labeled as 5	48	0	0	1	2	1912

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Precision Recall Curve

<< Go back