import shap

def generate_shap_plots(ranker, X_train, feature_names, N=3):
    """
    Generates SHAP plots for a pre-trained LightGBM model.

    Parameters:
        ranker (lightgbm.Booster): A trained LightGBM model
        X_train (np.ndarray): The training data used to fit the model
        feature_names (List): list of feature names
        N (int): The number of plots to generate

    Returns:
        None
    """
    explainer = shap.Explainer(ranker, X_train, feature_names=feature_names)
    shap_values = explainer(X_train.iloc[:N])

    # Create a figure with 2 subplots
    # fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(15,5))

    # Plot the summary plot on the first subplot
    plt.subplot(1, 2, 1)
    shap.summary_plot(shap_values, feature_names=feature_names, plot_type='bar')

    # Plot the feature importance plot on the second subplot
    plt.subplot(1, 2, 2)
    shap.summary_plot(shap_values, feature_names=feature_names, plot_type='dot')

    plt.show()

generate_shap_plots(model,xtrain,features,N=10000)