random_classifier_auroc_aupr.py

import numpy as np
from sklearn.metrics import roc_auc_score

n_class_0 = 50000
n_class_1 = 100

def main():
    # Suppose imblanced classification dataset
    labels = n_class_0 * [False] + n_class_1 * [True]
    y_true = n_class_0 * [0] + n_class_1 * [1]
    # Suppose totally random classifier
    y_scores = np.random.uniform(size=n_class_0 + n_class_1)

    result = []
    for i in range(n_class_0 + n_class_1):
        result.append((labels[i], y_scores[i]))
    y_scores = [x[1] for x in result]

    try:
        auc = roc_auc_score(y_true, y_scores)
    except:
        auc = 0
    print("AUC ", auc)

    # normal class
    X1 = [x[1] for x in result if x[0]]
    # abnormal class
    Y1 = [x[1] for x in result if not x[0]]
    minP = min([x[1] for x in result]) - 1
    maxP = max([x[1] for x in result]) + 1

    ##################################################################
    # AUPR IN
    ##################################################################
    auprin = 0.0
    recallTemp = 1.0
    for e in np.arange(minP, maxP, 0.2):
        tp = np.sum(np.greater_equal(X1, e))
        fp = np.sum(np.greater_equal(Y1, e))
        if tp + fp == 0:
            continue
        precision = tp / (tp + fp)
        recall = tp / np.float(len(X1))
        auprin += (recallTemp - recall) * precision
        recallTemp = recall
    auprin += recall * precision
    print("auprin: ", auprin)

    ##################################################################
    # AUPR OUT
    ##################################################################
    minp, maxP = -maxP, -minP
    X1 = [-x for x in X1]
    Y1 = [-x for x in Y1]
    auprout = 0.0
    recallTemp = 1.0
    for e in np.arange(minP, maxP, 0.2):
        tp = np.sum(np.greater_equal(Y1, e))
        fp = np.sum(np.greater_equal(X1, e))
        if tp + fp == 0:
            continue
        precision = tp / (tp + fp)
        recall = tp / np.float(len(Y1))
        auprout += (recallTemp - recall) * precision
        recallTemp = recall
    auprout += recall * precision
    print("auprout: ", auprout)


if __name__ == '__main__':
    main()
    """
    AUC  0.5059258
    auprin:  0.00226314447686
    auprout:  0.997870047959
    """