Extracting and Normalizing Feature Importance from LightGBM Models

The code uses the LightGBM library to extract feature importance from a trained model. It also uses NumPy for numerical operations.

Technology Stack : The code uses the LightGBM library for machine learning, and NumPy for numerical computations.

Code Type : The type of code

Code Difficulty :

                
                    
def random_feature_importance(lgbm_model):
    """
    This function extracts and returns the feature importance from a trained LightGBM model.
    """
    import lightgbm as lgbm
    import numpy as np
    
    def get_feature_importance(model):
        # Extract feature importance from the model
        importance = model.feature_importances_
        # Normalize the feature importance
        importance = (importance - np.min(importance)) / (np.max(importance) - np.min(importance))
        # Sort the feature importance in descending order
        sorted_idx = np.argsort(importance)[::-1]
        return sorted_idx, importance[sorted_idx]
    
    # Check if the input is a trained LightGBM model
    if not isinstance(lgbm_model, lgbm.Booster):
        raise ValueError("The input must be a trained LightGBM model.")
    
    # Get the feature importance
    sorted_idx, importance = get_feature_importance(lgbm_model)
    
    return sorted_idx, importance