Summary of 15_LightGBM_SelectedFeatures

<< Go back

LightGBM

• n_jobs: 6
• objective: multiclass
• num_leaves: 31
• learning_rate: 0.1
• feature_fraction: 0.5
• bagging_fraction: 1.0
• min_data_in_leaf: 10
• metric: custom
• custom_eval_metric_name: 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

28.1 seconds

Metric details

	0	1	2	3	4	5	accuracy	macro avg	weighted avg	logloss
precision	0.970167	0.970188	0.968973	0.990251	0.995616	0.99792	0.981826	0.982186	0.981921	0.0650685
recall	0.990658	0.958387	0.971939	0.992798	0.993439	0.977585	0.981826	0.980801	0.981826	0.0650685
f1-score	0.980305	0.964251	0.970453	0.991523	0.994527	0.987648	0.981826	0.981451	0.981828	0.0650685
support	2462	1562	1960	1944	1829	1963	0.981826	11720	11720	0.0650685

Confusion matrix

	Predicted as 0	Predicted as 1	Predicted as 2	Predicted as 3	Predicted as 4	Predicted as 5
Labeled as 0	2439	7	1	12	0	3
Labeled as 1	4	1497	58	1	2	0
Labeled as 2	12	39	1905	1	2	1
Labeled as 3	12	0	1	1930	1	0
Labeled as 4	7	0	1	4	1817	0
Labeled as 5	40	0	0	1	3	1919

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Precision Recall Curve

<< Go back