features = ['lead_time',

            'arrival_date_month',

            'stays_in_weekend_nights',

            'adults',

            'has_children',

            'has_babies',

            'meal',

            'country',

            'distribution_channel',

            'is_repeated_guest',

            'previous_cancellations',

            'previous_bookings_not_canceled',

            'reserved_room_type',

            'booking_changes',

            'days_in_waiting_list',

            'customer_type',

            'need_car_parking_space',

            'total_of_special_requests',

            'total_nights']

cat_features = ['arrival_date_month',

            'stays_in_weekend_nights',

            'meal',

            'country',

            'distribution_channel',

            'is_repeated_guest',

            'previous_cancellations',

            'previous_bookings_not_canceled',

            'reserved_room_type',

            'booking_changes',

            'customer_type',

            'need_car_parking_space',

            'total_of_special_requests',

            'total_nights']

target = 'is_canceled'

 

categorical_columns = df_train[features].select_dtypes(include='object').columns.to_list()

 

encoder = OneHotEncoder(handle_unknown='ignore')

encoder.fit(df_train[categorical_columns])

df_train_categorical = pd.DataFrame(encoder.transform(df_train[categorical_columns]).toarray())

df_test_categorical = pd.DataFrame(encoder.transform(df_test[categorical_columns]).toarray())

 

df_train_categorical.columns = encoder.get_feature_names_out()

df_test_categorical.columns = encoder.get_feature_names_out()

 

df_for_learn = pd.concat([df_train[features].select_dtypes(exclude='object').reset_index(drop=True), df_train_categorical.reset_index(drop=True)], axis=1)

df_for_test = pd.concat([df_test[features].select_dtypes(exclude='object').reset_index(drop=True), df_test_categorical.reset_index(drop=True)], axis=1)