from models import create_model
from rank import calculate_mean_and_sort_list, get_ranks, calculate_mape
from data import load

from sklearn.model_selection import train_test_split


if __name__ == '__main__':
    X, y, names = load('WindData.csv')
    linear = create_model(X, y)
    ranks = get_ranks(linear, names)
    print("MEAN", calculate_mean_and_sort_list(ranks))
    for test_size in [0.001, 0.01, 0.05, 0.11]:
        X_train, X_test, Y_train, Y_test = train_test_split(X, y, test_size=test_size, random_state=100)
        mape = calculate_mape(X_train, X_test, Y_train, Y_test)
        print(f'MAPE for test_size={test_size} is {float("{:.3f}".format(mape))}')