各种AUC的计算方式python实现

auc计算方式：

参考：

https://blog.csdn.net/lieyingkub99/article/details/81266664?utm_medium=distribute.pc_relevant.none-task-blog-title-1&spm=1001.2101.3001.4242

import numpy as np
from sklearn.metrics import roc_auc_score
y_true = [1,1,0,0,1,1,0]
y_pred = [0.8,0.7,0.5,0.5,0.5,0.5,0.3]
print(roc_auc_score(y_true, y_pred))
# 下面实现的是方法1
# https://blog.csdn.net/lieyingkub99/article/details/81266664?utm_medium=distribute.pc_relevant.none-task-blog-title-1&spm=1001.2101.3001.4242
def cal_auc1(y_true, y_pred):
    n_bins = 10
    postive_len = sum(y_true)  # M正样本个数
    negative_len = len(y_true) - postive_len  # N负样本个数
    total_case = postive_len * negative_len  # M * N样本对数
    pos_histogram = [0 for _ in range(n_bins)]  # 保存每一个概率值下的正样本个数
    neg_histogram = [0 for _ in range(n_bins)]  # 保存每一个概率值下的负样本个数
    bin_width = 1.0 / n_bins
    for i in range(len(y_true)):
        nth_bin = int(y_pred[i] / bin_width)  # 概率值转化为整数下标
        if y_true[i] == 1:
            pos_histogram[nth_bin] += 1
        else:
            neg_histogram[nth_bin] += 1
    print(pos_histogram)
    print(neg_histogram)
    accumulated_neg = 0
    satisfied_pair = 0
    for i in range(n_bins):
        satisfied_pair += (pos_histogram[i] * accumulated_neg + pos_histogram[i] * neg_histogram[i] * 0.5)
        print(pos_histogram[i], neg_histogram[i], accumulated_neg, satisfied_pair)
        accumulated_neg += neg_histogram[i]

    return satisfied_pair / float(total_case)
print(cal_auc1(y_true, y_pred))
# 下面实现的是方法2
# https://blog.csdn.net/lieyingkub99/article/details/81266664?utm_medium=distribute.pc_relevant.none-task-blog-title-1&spm=1001.2101.3001.4242
def cal_auc2(y_true, y_pred):
    n_bins = 10
    postive_len = sum(y_true)  # M正样本个数
    negative_len = len(y_true) - postive_len  # N负样本个数
    total_case = postive_len * negative_len  # M * N样本对数
    prob_rank = [0 for _ in range(n_bins)]  # 保存每一个概率值的rank
    prob_num = [0 for _ in range(n_bins)]  # 保存每一个概率值出现的次数
    bin_width = 1.0 / n_bins
    raw_arr = []
    for i in range(len(y_true)):
        raw_arr.append([y_pred[i], y_true[i]])
    arr = sorted(raw_arr, key=lambda d: d[0]) # 按概率由低到高排序
    for i in range(len(arr)):
        nth_bin = int(arr[i][0] / bin_width)  # 概率值转化为整数下标
        prob_rank[nth_bin] = prob_rank[nth_bin] + i + 1
        prob_num[nth_bin] = prob_num[nth_bin] + 1
    satisfied_pair = 0
    for i in range(len(arr)):
        if arr[i][1] == 1:
            nth_bin = int(arr[i][0] / bin_width)  # 概率值转化为整数下标
            satisfied_pair = satisfied_pair + prob_rank[nth_bin] / prob_num[nth_bin]
    return (satisfied_pair - postive_len * (postive_len + 1) / 2 ) / total_case



print(cal_auc2(y_true, y_pred))

# 根据roc曲线,找不同点算下面积, 需要点足够多
def cal_auc3(y_true, y_pred):
    """Summary
    Args:
        raw_arr (TYPE): Description
    Returns:
        TYPE: Description
    """
    raw_arr = []
    for i in range(len(y_true)):
        raw_arr.append([y_pred[i], y_true[i]])
    print(raw_arr)
    arr = sorted(raw_arr, key=lambda d:d[0], reverse=True)
    pos, neg = 0., 0.
    for record in arr:
        if record[1] == 1.:
            pos += 1
        else:
            neg += 1

    fp, tp = 0., 0.
    xy_arr = []
    for record in arr:
        if record[1] == 1.:
            tp += 1
        else:
            fp += 1
        xy_arr.append([fp/neg, tp/pos])
    print(xy_arr)
    auc = 0.
    prev_x = 0.
    prev_y = 0.
    for x, y in xy_arr:
        if x != prev_x:
            auc += ((x - prev_x) * (y + prev_y) / 2.)
            prev_x = x
            prev_y = y
        print(auc)
    import numpy as np
    from sklearn.metrics import roc_auc_score
    y_true = [1, 1, 0, 0, 1, 1, 0]
    y_pred = [0.8, 0.7, 0.5, 0.5, 0.5, 0.5, 0.3]
    print(roc_auc_score(y_true, y_pred))

    # 下面实现的是方法1
    # https://blog.csdn.net/lieyingkub99/article/details/81266664?utm_medium=distribute.pc_relevant.none-task-blog-title-1&spm=1001.2101.3001.4242
    def cal_auc1(y_true, y_pred):
        n_bins = 10
        postive_len = sum(y_true)  # M正样本个数
        negative_len = len(y_true) - postive_len  # N负样本个数
        total_case = postive_len * negative_len  # M * N样本对数
        pos_histogram = [0 for _ in range(n_bins)]  # 保存每一个概率值下的正样本个数
        neg_histogram = [0 for _ in range(n_bins)]  # 保存每一个概率值下的负样本个数
        bin_width = 1.0 / n_bins
        for i in range(len(y_true)):
            nth_bin = int(y_pred[i] / bin_width)  # 概率值转化为整数下标
            if y_true[i] == 1:
                pos_histogram[nth_bin] += 1
            else:
                neg_histogram[nth_bin] += 1
        print(pos_histogram)
        print(neg_histogram)
        accumulated_neg = 0
        satisfied_pair = 0
        for i in range(n_bins):
            satisfied_pair += (pos_histogram[i] * accumulated_neg + pos_histogram[i] * neg_histogram[i] * 0.5)
            print(pos_histogram[i], neg_histogram[i], accumulated_neg, satisfied_pair)
            accumulated_neg += neg_histogram[i]

        return satisfied_pair / float(total_case)

    print(cal_auc1(y_true, y_pred))

    # 下面实现的是方法2
    # https://blog.csdn.net/lieyingkub99/article/details/81266664?utm_medium=distribute.pc_relevant.none-task-blog-title-1&spm=1001.2101.3001.4242
    def cal_auc2(y_true, y_pred):
        n_bins = 10
        postive_len = sum(y_true)  # M正样本个数
        negative_len = len(y_true) - postive_len  # N负样本个数
        total_case = postive_len * negative_len  # M * N样本对数
        prob_rank = [0 for _ in range(n_bins)]  # 保存每一个概率值的rank
        prob_num = [0 for _ in range(n_bins)]  # 保存每一个概率值出现的次数
        bin_width = 1.0 / n_bins
        raw_arr = []
        for i in range(len(y_true)):
            raw_arr.append([y_pred[i], y_true[i]])
        arr = sorted(raw_arr, key=lambda d: d[0])  # 按概率由低到高排序
        for i in range(len(arr)):
            nth_bin = int(arr[i][0] / bin_width)  # 概率值转化为整数下标
            prob_rank[nth_bin] = prob_rank[nth_bin] + i + 1
            prob_num[nth_bin] = prob_num[nth_bin] + 1
        satisfied_pair = 0
        for i in range(len(arr)):
            if arr[i][1] == 1:
                nth_bin = int(arr[i][0] / bin_width)  # 概率值转化为整数下标
                satisfied_pair = satisfied_pair + prob_rank[nth_bin] / prob_num[nth_bin]
        return (satisfied_pair - postive_len * (postive_len + 1) / 2) / total_case

    print(cal_auc2(y_true, y_pred))

    # 根据roc曲线,找不同点算下面积, 需要点足够多
    def cal_auc3(y_true, y_pred):
        """Summary
        Args:
            raw_arr (TYPE): Description
        Returns:
            TYPE: Description
        """
        raw_arr = []
        for i in range(len(y_true)):
            raw_arr.append([y_pred[i], y_true[i]])
        print(raw_arr)
        arr = sorted(raw_arr, key=lambda d: d[0], reverse=True)
        pos, neg = 0., 0.
        for record in arr:
            if record[1] == 1.:
                pos += 1
            else:
                neg += 1

        fp, tp = 0., 0.
        xy_arr = []
        for record in arr:
            if record[1] == 1.:
                tp += 1
            else:
                fp += 1
            xy_arr.append([fp / neg, tp / pos])
        print(xy_arr)
        auc = 0.
        prev_x = 0.
        prev_y = 0.
        for x, y in xy_arr:
            if x != prev_x:
                auc += ((x - prev_x) * (y + prev_y) / 2.)
                prev_x = x
                prev_y = y
            print(auc)

        return auc

    print(cal_auc3(y_true, y_pred))
    return auc
print(cal_auc3(y_true, y_pred))