from sklearn.linear_model import LogisticRegressionCV
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split

# Load sample data
X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create LogisticRegressionCV model
# Cs is a list of regularization strengths to try
# cv is the number of folds in cross-validation
logistic_cv = LogisticRegressionCV(
    Cs=10,           # Try 10 different C values (default is 10)
    cv=5,            # 5-fold cross-validation
    penalty='l2',    # Ridge regularization (can also use 'l1')
    solver='liblinear',
    random_state=42
)

# Fit the model (cross-validation happens during fitting)
logistic_cv.fit(X_train, y_train)

# Access the best regularization parameter found
print(f"Best C parameter: {logistic_cv.C_}")

# Evaluate on test set
score = logistic_cv.score(X_test, y_test)
print(f"Test accuracy: {score:.4f}")