python sklearn PR曲线 AUPR值

最新推荐文章于 2025-08-06 11:10:43 发布

原创最新推荐文章于 2025-08-06 11:10:43 发布 · 6.4k 阅读

CC 4.0 BY-SA版权

本文深入探讨了Python机器学习库sklearn中的PR曲线和AUPR(Area Under the Precision-Recall curve)。通过引用三个链接资源，文章提供了关于如何计算和理解这两个概念的详细说明，包括代码示例和实际应用。

一、来自链接：http://www.voidcn.com/article/p-qkxqxmdl-but.html

import matplotlib.pyplot as plt
import numpy
from sklearn.datasets import make_blobs
from sklearn.metrics import precision_recall_curve, auc
from sklearn.model_selection import KFold
from sklearn.svm import SVC

FOLDS = 5

X, y = make_blobs(n_samples=1000, n_features=2, centers=2, cluster_std=10.0,
    random_state=12345)

f, axes = plt.subplots(1, 2, figsize=(10, 5))

axes[0].scatter(X[y==0,0], X[y==0,1], color='blue', s=2, label='y=0')
axes[0].scatter(X[y!=0,0], X[y!=0,1], color='red', s=2, label='y=1')
axes[0].set_xlabel('X[:,0]')
axes[0].set_ylabel('X[:,1]')
axes[0].legend(loc='lower left', fontsize='small')

k_fold = KFold(n_splits=FOLDS, shuffle=True, random_state=12345)
predictor = SVC(kernel='linear', C=1.0, probability=True, random_state=12345)

y_real = []
y_proba = []
for i, (train_index, test_index) in enumerate(k_fold.split(X)):
    Xtrain, Xtest = X[train_index], X[test_index]
    ytrain, ytest = y[train_index], y[test_index]
    predictor.fit(Xtrain, ytrain)
    pred_proba = predictor.predict_proba(Xtest)
    precision, recall, _ = precision_recall_curve(ytest, pred_proba[:,1])
    lab = 'Fold %d AUC=%.4f' % (i+1, auc(recall, precision))
    axes[1].step(recall, precision, label=lab)
    y_real.append(ytest)
    y_proba.append(pred_proba[:,1])

y_real = numpy.concatenate(y_real)
y_proba = numpy.concatenate(y_proba)
precision, recall, _ = precision_recall_curve(y_real, y_proba)
lab = 'Overall AUC=%.4f' % (auc(recall, precision))
axes[1].step(recall, precision, label=lab, lw=2, color='black')
axes[1].set_xlabel('Recall')
axes[1].set_ylabel('Precision')
axes[1].legend(loc='lower left', fontsize='small')

f.tight_layout()
f.savefig('result.png')

二、来自链接：https://www.programcreek.com/python/example/89259/sklearn.metrics.precision_recall_curve

def precision_recall_auc(loss_file,reverse,smoothing):
    if not os.path.isdir(loss_file):
        loss_file_list = [loss_file]
    else:
        loss_file_list = os.listdir(loss_file)
        loss_file_list = [os.path.join(loss_file, sub_loss_file) for sub_loss_file in loss_file_list]

    optimal_results = RecordResult()
    for sub_loss_file in loss_file_list:
        dataset, scores, labels = get_scores_labels(sub_loss_file,reverse,smoothing)
        precision, recall, thresholds = metrics.precision_recall_curve(labels, scores, pos_label=0)
        auc = metrics.auc(recall, precision)

        results = RecordResult(recall, precision, auc, dataset, sub_loss_file)

        if optimal_results < results:
            optimal_results = results

        if os.path.isdir(loss_file):
            print(results)
    print('##### optimal result and model PR-AUC = {}'.format(optimal_results))
    return optimal_results

三、来自链接：https://github.com/9468305/python-script/tree/master/auc_pr_roc/

'''使用real.csv和result.csv列数据，计算PR曲线的AUC值'''
precision, recall, _thresholds = metrics.precision_recall_curve(label, prob)
area = metrics.auc(recall, precision)
return area