from sklearn.preprocessing import OneHotEncoder


columns = ["city", "plan"]
train = [
    ["Paris", "free"],
    ["Tokyo", "paid"],
    ["Paris", "paid"],
    ["London", "free"],
]
validation = [["Berlin", "paid"]]

encoder = OneHotEncoder(handle_unknown="ignore", sparse_output=False)
encoded_train = encoder.fit_transform(train).astype(int)
encoded_validation = encoder.transform(validation).astype(int)

feature_names = encoder.get_feature_names_out(columns)

print("Learned categories:")
for name, categories in zip(columns, encoder.categories_):
    print(f"- {name}: {', '.join(categories)}")

print()
print("Encoded feature names:")
print(", ".join(feature_names))

print()
print("Encoded training rows:")
print(encoded_train)

print()
print("Validation row with unseen city:")
print(encoded_validation)

print()
print(f"Encoded shape: {encoded_train.shape[0]} rows x {encoded_train.shape[1]} columns")