from sklearn.datasets import load_diabetes
from sklearn.inspection import (
    permutation_importance,
)
from sklearn.linear_model import Ridge
from sklearn.model_selection import (
    train_test_split,
)


diabetes = load_diabetes()
split = train_test_split(
    diabetes.data,
    diabetes.target,
    test_size=0.25,
    random_state=0,
)
X_train, X_val, y_train, y_val = split

model = Ridge(alpha=1e-2)
model.fit(X_train, y_train)

score = model.score(X_val, y_val)
result = permutation_importance(
    model,
    X_val,
    y_val,
    n_repeats=30,
    random_state=0,
    scoring="r2",
)

print(f"validation r2: {score:.3f}")
print("feature  mean_drop  std")

ranked = result.importances_mean.argsort()[::-1]
for index in ranked[:5]:
    name = diabetes.feature_names[index]
    mean = result.importances_mean[index]
    std = result.importances_std[index]
    print(
        f"{name:<7} {mean:>9.3f}  "
        f"{std:.3f}"
    )

top_index = result.importances_mean.argmax()
top_name = diabetes.feature_names[top_index]
print(f"top feature: {top_name}")