def logistic_regression(X, y, eta=0.001, iter=100, alpha=0.5):
    """Logistic regression
Args:
    X - feature matrix
    y - target vector
    eta - learning rate
    iter - number of iterations
    alpha - regularization parameter
Returns:
    theta - weight estimates
    losses - historical loss data
    thetas - historical thetas data
"""
    _, n = X.shape
    theta = np.random.uniform(size=n)
    losses = np.zeros(iter)
    thetas = np.zeros(iter*3).reshape(iter, 3)
    #### your code (start)
    for i in range(iter):
        output = sigmoid(X @ theta)

        loss = binary_cross_entropy(output, y) + alpha / 2 * np.sum(theta[1:] ** 2)
        if i % 10 == 0:
            print(f'\r{loss}', end='')

        grad = (y - output) @ X
        grad[1:] += alpha * theta[1:] # regularization term

        theta += eta * grad

        losses[i] = loss
        thetas[i] = theta.copy()

    #### your code (end)
    return theta, losses, thetas