Przeczytaj kod uważnie

from sklearn.metrics import roc_auc_score

# labels:  [0,   0,   1,   1  ]   (two negatives, two positives)
# scores:  [0.1, 0.2, 0.7, 0.9]
#
# AUC = P(score of random positive > score of random negative)
#
# Count the positive-negative score pairs and how many are correctly
# ordered. Divide.

print(roc_auc_score([0, 0, 1, 1], [0.1, 0.2, 0.7, 0.9]))

# What does this print? Type your prediction.

Co wypisze program? Napisz tutaj: