import sklearn.metrics
import numpy

def matthews_corrcoef(y_true, y_predicted):
    conf_matrix = sklearn.metrics.confusion_matrix(y_true, y_predicted)
    true_pos = conf_matrix[1,1]
    false_pos = conf_matrix[1,0]
    false_neg = conf_matrix[0,1]
    n_points = conf_matrix.sum()*1.0
    pos_rate = (true_pos + false_neg) / n_points
    activity = (true_pos + false_pos) / n_points
    mcc_numerator = true_pos / n_points - pos_rate * activity
    mcc_denominator = activity * pos_rate * (1 - activity) * (1 - pos_rate)
    return mcc_numerator / numpy.sqrt(mcc_denominator)

def random_ys(n_points):
    x_true = numpy.random.sample(n_points)
    x_pred = x_true + 0.2 * (numpy.random.sample(n_points) - 0.5)
    y_true = (x_true > 0.5) * 1.0
    y_pred = (x_pred > 0.5) * 1.0
    return y_true, y_pred

for n_points in [10, 100, 1000]:
    y_true, y_pred = random_ys(n_points)
    mcc_safe = matthews_corrcoef(y_true, y_pred)
    mcc_unsafe = sklearn.metrics.matthews_corrcoef(y_true, y_pred)
    try:
        assert(abs(mcc_safe - mcc_unsafe) < 1e-8)
    except AssertionError:
        print('Error: mcc_safe=%s, mcc_unsafe=%s, n_points=%s' % (
            mcc_safe, mcc_unsafe, n_points))