from scipy.stats import loguniform
import sklearn
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score
from sklearn.model_selection import RandomizedSearchCV, StratifiedKFold, train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC


iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    iris.data,
    iris.target,
    test_size=0.25,
    stratify=iris.target,
    random_state=42,
)

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

param_distributions = {
    "svc__C": loguniform(1e-2, 1e2),
    "svc__gamma": loguniform(1e-4, 1e0),
    "svc__kernel": ["rbf"],
}

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

search = RandomizedSearchCV(
    estimator=model,
    param_distributions=param_distributions,
    n_iter=8,
    scoring="accuracy",
    cv=cv,
    random_state=42,
    refit=True,
)
search.fit(X_train, y_train)

best_params = search.best_params_
best_params_display = {
    "svc__C": round(float(best_params["svc__C"]), 4),
    "svc__gamma": round(float(best_params["svc__gamma"]), 4),
    "svc__kernel": best_params["svc__kernel"],
}

test_predictions = search.predict(X_test)
test_accuracy = accuracy_score(y_test, test_predictions)

print(f"scikit-learn {sklearn.__version__}")
print(f"candidate settings tried: {len(search.cv_results_['params'])}")
print(f"cross-validation folds: {search.n_splits_}")
print(f"best params: {best_params_display}")
print(f"best CV accuracy: {search.best_score_:.3f}")
print(f"held-out accuracy: {test_accuracy:.3f}")