Skip to content

Summary of 6_LightGBM_SelectedFeatures

<< Go back

LightGBM

  • n_jobs: 6
  • objective: multiclass
  • num_leaves: 63
  • learning_rate: 0.2
  • 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

32.5 seconds

Metric details

0 1 2 3 4 5 accuracy macro avg weighted avg logloss
precision 0.97483 0.966581 0.971487 0.99075 0.997806 0.997925 0.983191 0.98323 0.983266 0.0588952
recall 0.991064 0.962868 0.973469 0.99177 0.994533 0.980132 0.983191 0.982306 0.983191 0.0588952
f1-score 0.98288 0.964721 0.972477 0.99126 0.996166 0.988949 0.983191 0.982742 0.9832 0.0588952
support 2462 1562 1960 1944 1829 1963 0.983191 11720 11720 0.0588952

Confusion matrix

Predicted as 0 Predicted as 1 Predicted as 2 Predicted as 3 Predicted as 4 Predicted as 5
Labeled as 0 2440 8 2 10 0 2
Labeled as 1 2 1504 53 2 1 0
Labeled as 2 7 43 1908 2 0 0
Labeled as 3 13 1 0 1928 1 1
Labeled as 4 5 0 1 3 1819 1
Labeled as 5 36 0 0 1 2 1924

Learning curves

Learning curves

Permutation-based Importance

Permutation-based Importance

Confusion Matrix

Confusion Matrix

Normalized Confusion Matrix

Normalized Confusion Matrix

ROC Curve

ROC Curve

Precision Recall Curve

Precision Recall Curve

<< Go back