"""
Komputerowa analiza danych
Zadanie 2
Michał Leśniak 195642
"""
from statistics import mean


def var(lst):
    x_mean = mean(lst)
    return sum((x-x_mean)**2 for x in lst)/len(lst)


def cov(lst_x, lst_y):
    assert len(lst_x) == len(lst_y)
    x_mean = mean(lst_x)
    y_mean = mean(lst_y)
    return sum((lst_x[i]-x_mean)*(lst_y[i]-y_mean) for i in range(len(lst_x)))/len(lst_x)


def load_data(*args):
    ret = ()
    for arg in args:
        with open(arg, 'r') as f:
            lines = f.read().splitlines()
        lst = []
        for line in lines:
            lst.append(tuple([float(x.strip()) for x in line.split(',')]))
        ret += lst,
    return ret


def model1(data):
    lst_x = [x for x, _ in data]
    lst_y = [y for _, y in data]

    a = cov(lst_x, lst_y)/var(lst_x)
    print(f'f(X) = {a} * X')


def model2(data):
    lst_x = [x for x, _ in data]
    lst_y = [y for _, y in data]

    a = cov(lst_x, lst_y)/var(lst_x)
    b = mean(lst_y) - a*mean(lst_x)
    print(f'f(X) = {a} * X + {b}')


def main():
    data1, data2, data3, data4 = load_data(
        'data1.csv', 'data2.csv', 'data3.csv', 'data4.csv')
    print(var([x for x, _ in data1]))
    print(cov([x for x, _ in data1], [y for _, y in data1]))
    # print(data2)
    # print(data3)
    # print(data4)
    model1(data1)
    model1(data2)
    model2(data1)
    model2(data2)
    x_mean = mean([x for x, _ in data1])
    y_mean = mean([y for _, y in data1])
    xy = sum([x*y for x, y in data1])
    x_2 = sum([x**2 for x, _ in data1])
    print(sum([2*x-2*x*y for x,y in data1])/len(data1))
    print(xy/x_2)


if __name__ == '__main__':
    main()