import sklearn
from sklearn.datasets import load_breast_cancer
from sklearn.metrics import accuracy_score
from sklearn.model_selection import GridSearchCV, StratifiedKFold, train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC


X, y = load_breast_cancer(return_X_y=True)

X_train, X_test, y_train, y_test = train_test_split(
    X,
    y,
    test_size=0.25,
    stratify=y,
    random_state=42,
)

model = make_pipeline(
    StandardScaler(),
    SVC(),
)

param_grid = {
    "svc__C": [0.1, 1, 10],
    "svc__gamma": ["scale", 0.01],
    "svc__kernel": ["rbf"],
}

cv = StratifiedKFold(
    n_splits=5,
    shuffle=True,
    random_state=42,
)

search = GridSearchCV(
    model,
    param_grid=param_grid,
    scoring="accuracy",
    cv=cv,
    refit=True,
)
search.fit(X_train, y_train)

candidate_count = len(search.cv_results_["params"])
test_predictions = search.predict(X_test)
held_out_accuracy = accuracy_score(y_test, test_predictions)

print(f"scikit-learn {sklearn.__version__}")
print(f"scoring: {search.scoring}")
print(f"cross-validation folds: {search.n_splits_}")
print(f"evaluated candidates: {candidate_count}")
print(f"total fits: {candidate_count * search.n_splits_}")
print(f"best parameters: {search.best_params_}")
print(f"best mean CV accuracy: {search.best_score_:.3f}")
print(f"held-out accuracy: {held_out_accuracy:.3f}")
print("top candidates:")

ranked_candidates = sorted(
    zip(
        search.cv_results_["rank_test_score"],
        search.cv_results_["mean_test_score"],
        search.cv_results_["params"],
    ),
    key=lambda item: item[0],
)

for rank, mean_score, params in ranked_candidates[:3]:
    print(f"  rank {rank}: mean={mean_score:.3f}, params={params}")