The Receiver Operating Characteristic (ROC) curve is created by plotting the True Positive Rate (TPR) against the False Positive Rate (FPR) at various threshold settings. The Area Under the Curve (AUC) for the ROC curve is equal to the probability that a classifier will rank a randomly chosen similar pair (images of same people) higher than a randomly chosen dissimilar one (images from two different people) (assuming 'similar' ranks higher than 'dissimilar' in terms of similarity scores).
As mentioned in the part 2 handout, the utils.py utility is:
from sklearn.metrics import roc_auc_score
import sys
import pandas as pd

def get_auc(y_true, y_score):
    auc = roc_auc_score(y_true, y_score)
    return auc

if __name__ == '__main__':
    args = sys.argv[1:]
    if len(args)  "
        exit()
    score_csv = args[0]
    label_csv = args[1]
    y_score = pd.read_csv(score_csv).score.values
    y_true = pd.read_csv(label_csv).score.values
    auc = get_auc(y_true, y_score)
    print ("AUC: ", auc)