permutation_importance.png

def fig_permutation_importance(model, X_test: pd.DataFrame,
                               y_test: pd.Series) -> None:
    """Horizontal bar chart of permutation importance with error bars."""
    result = permutation_importance(
        model, X_test, y_test,
        n_repeats=10, random_state=SEED, scoring="roc_auc", n_jobs=1,
    )
    means = result.importances_mean
    stds = result.importances_std

    # Sort ascending so the most important feature appears at the top.
    order = np.argsort(means)
    sorted_names = [FEATURES[i] for i in order]
    sorted_means = means[order]
    sorted_stds = stds[order]

    # German-friendly feature label mapping.
    label_map = {
        "alter": "Alter (Jahre)",
        "sofa_score": "SOFA-Score",
        "crp_mg_l": "CRP (mg/l)",
        "bmi": "BMI",
        "leukozyten_g_l": "Leukozyten (G/l)",
        "kreatinin_mg_dl": "Kreatinin (mg/dl)",
        "laktat_mmol_l": "Laktat (mmol/l)",
        "aufnahmegrund": "Aufnahmegrund",
        "raucherstatus": "Raucherstatus",
        "diabetes": "Diabetes",
        "hypertonie": "Hypertonie",
    }
    display_names = [label_map.get(n, n) for n in sorted_names]

    colors = [EVENT if m > 0.005 else SECONDARY for m in sorted_means]

    fig, ax = plt.subplots(figsize=(7, 5))
    y_pos = np.arange(len(sorted_names))
    ax.barh(y_pos, sorted_means, xerr=sorted_stds,
            color=colors, height=0.6, error_kw={"linewidth": 0.8, "capsize": 3})
    ax.axvline(0, color="#CCCCCC", lw=0.8)
    ax.set_yticks(y_pos)
    ax.set_yticklabels(display_names, fontsize=10)
    ax.set_xlabel("Mittlerer AUC-Abfall (Permutation Importance)")
    ax.set_title("Permutation Importance auf dem Testset\n(positiv = Modell verlässt sich darauf)")
    ax.grid(axis="x")
    save(fig, ASSETS / "permutation_importance.png")