基本概念

precision：预测为对的当中，原本为对的比例（越大越好，1为理想状态）

recall：原本为对的当中，预测为对的比例（越大越好，1为理想状态）

F-measure：F度量是对准确率和召回率做一个权衡（越大越好，1为理想状态，此时precision为1，recall为1）

accuracy：预测对的（包括原本是对预测为对，原本是错的预测为错两种情形）占整个的比例（越大越好，1为理想状态）

fp rate：原本是错的预测为对的比例（越小越好，0为理想状态）

tp rate：原本是对的预测为对的比例（越大越好，1为理想状态）

ROC曲线通常在Y轴上具有真阳性率，在X轴上具有假阳性率。这意味着图的左上角是“理想”点 - 误报率为零，真正的正率为1。这不太现实，但它确实意味着曲线下面积（AUC）通常更好。

二分类问题：ROC曲线

from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport timestart_time = time.time()import matplotlib.pyplot as pltfrom sklearn.metrics import roc_curvefrom sklearn.metrics import aucimport numpy as npfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import recall_score,accuracy_scorefrom sklearn.metrics import precision_score,f1_scorefrom keras.optimizers import Adam,SGD,sgdfrom keras.models import load_modelprint('读取数据')X_train = np.load('x_train-rotate_2.npy')Y_train = np.load('y_train-rotate_2.npy')print(X_train.shape)print(Y_train.shape)print('获取测试数据和验证数据')X_train, X_valid, Y_train, Y_valid = train_test_split(X_train, Y_train, test_size=0.1, random_state=666)Y_train = np.asarray(Y_train,np.uint8)Y_valid = np.asarray(Y_valid,np.uint8)X_valid = np.array(X_valid, np.float32) / 255.print('获取模型')model = load_model('./model/InceptionV3_model.h5')opt = Adam(lr=1e-4)model.compile(optimizer=opt, loss='binary_crossentropy')print("Predicting")Y_pred = model.predict(X_valid)Y_pred = [np.argmax(y) for y in Y_pred] # 取出y中元素最大值所对应的索引Y_valid = [np.argmax(y) for y in Y_valid]# micro：多分类　　# weighted：不均衡数量的类来说，计算二分类metrics的平均# macro：计算二分类metrics的均值，为每个类给出相同权重的分值。precision = precision_score(Y_valid, Y_pred, average='weighted')recall = recall_score(Y_valid, Y_pred, average='weighted')f1_score = f1_score(Y_valid, Y_pred, average='weighted')accuracy_score = accuracy_score(Y_valid, Y_pred)print("Precision_score:",precision)print("Recall_score:",recall)print("F1_score:",f1_score)print("Accuracy_score:",accuracy_score)# 二分类　ＲＯＣ曲线# roc_curve:真正率（True Positive Rate , TPR）或灵敏度（sensitivity）# 横坐标：假正率（False Positive Rate , FPR）fpr, tpr, thresholds_keras = roc_curve(Y_valid, Y_pred)auc = auc(fpr, tpr)print("AUC : ", auc)plt.figure()plt.plot([0, 1], [0, 1], 'k--')plt.plot(fpr, tpr, label='Keras (area = {:.3f})'.format(auc))plt.xlabel('False positive rate')plt.ylabel('True positive rate')plt.title('ROC curve')plt.legend(loc='best')plt.savefig("../images/ROC/ROC_2分类.png")plt.show()print("--- %s seconds ---" % (time.time() - start_time))

ROC图如下所示：

多分类问题：ROC曲线

ROC曲线通常用于二分类以研究分类器的输出。为了将ROC曲线和ROC区域扩展到多类或多标签分类，有必要对输出进行二值化。⑴可以每个标签绘制一条ROC曲线。⑵也可以通过将标签指示符矩阵的每个元素视为二元预测（微平均）来绘制ROC曲线。⑶另一种用于多类别分类的评估方法是宏观平均，它对每个标签的分类给予相同的权重。

from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport timestart_time = time.time()import matplotlib.pyplot as pltfrom sklearn.metrics import roc_curvefrom sklearn.metrics import aucimport numpy as npfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import recall_score,accuracy_scorefrom sklearn.metrics import precision_score,f1_scorefrom keras.optimizers import Adam,SGD,sgdfrom keras.models import load_modelfrom itertools import cyclefrom scipy import interpfrom sklearn.preprocessing import label_binarizenb_classes = 5print('读取数据')X_train = np.load('x_train-resized_5.npy')Y_train = np.load('y_train-resized_5.npy')print(X_train.shape)print(Y_train.shape)print('获取测试数据和验证数据')X_train, X_valid, Y_train, Y_valid = train_test_split(X_train, Y_train, test_size=0.1, random_state=666)Y_train = np.asarray(Y_train,np.uint8)Y_valid = np.asarray(Y_valid,np.uint8)X_valid = np.asarray(X_valid, np.float32) / 255.print('获取模型')model = load_model('./model/SE-InceptionV3_model.h5')opt = Adam(lr=1e-4)model.compile(optimizer=opt, loss='categorical_crossentropy')print("Predicting")Y_pred = model.predict(X_valid)Y_pred = [np.argmax(y) for y in Y_pred] # 取出y中元素最大值所对应的索引Y_valid = [np.argmax(y) for y in Y_valid]# Binarize the outputY_valid = label_binarize(Y_valid, classes=[i for i in range(nb_classes)])Y_pred = label_binarize(Y_pred, classes=[i for i in range(nb_classes)])# micro：多分类　　# weighted：不均衡数量的类来说，计算二分类metrics的平均# macro：计算二分类metrics的均值，为每个类给出相同权重的分值。precision = precision_score(Y_valid, Y_pred, average='micro')recall = recall_score(Y_valid, Y_pred, average='micro')f1_score = f1_score(Y_valid, Y_pred, average='micro')accuracy_score = accuracy_score(Y_valid, Y_pred)print("Precision_score:",precision)print("Recall_score:",recall)print("F1_score:",f1_score)print("Accuracy_score:",accuracy_score)# roc_curve:真正率（True Positive Rate , TPR）或灵敏度（sensitivity）# 横坐标：假正率（False Positive Rate , FPR）# Compute ROC curve and ROC area for each classfpr = dict()tpr = dict()roc_auc = dict()for i in range(nb_classes): fpr[i], tpr[i], _ = roc_curve(Y_valid[:, i], Y_pred[:, i]) roc_auc[i] = auc(fpr[i], tpr[i])# Compute micro-average ROC curve and ROC areafpr["micro"], tpr["micro"], _ = roc_curve(Y_valid.ravel(), Y_pred.ravel())roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])# Compute macro-average ROC curve and ROC area# First aggregate all false positive ratesall_fpr = np.unique(np.concatenate([fpr[i] for i in range(nb_classes)]))# Then interpolate all ROC curves at this pointsmean_tpr = np.zeros_like(all_fpr)for i in range(nb_classes): mean_tpr += interp(all_fpr, fpr[i], tpr[i])# Finally average it and compute AUCmean_tpr /= nb_classesfpr["macro"] = all_fprtpr["macro"] = mean_tprroc_auc["macro"] = auc(fpr["macro"], tpr["macro"])# Plot all ROC curveslw = 2plt.figure()plt.plot(fpr["micro"], tpr["micro"], label='micro-average ROC curve (area = {0:0.2f})' ''.format(roc_auc["micro"]), color='deeppink', linestyle=':', linewidth=4)plt.plot(fpr["macro"], tpr["macro"], label='macro-average ROC curve (area = {0:0.2f})' ''.format(roc_auc["macro"]), color='navy', linestyle=':', linewidth=4)colors = cycle(['aqua', 'darkorange', 'cornflowerblue'])for i, color in zip(range(nb_classes), colors): plt.plot(fpr[i], tpr[i], color=color, lw=lw, label='ROC curve of class {0} (area = {1:0.2f})' ''.format(i, roc_auc[i]))plt.plot([0, 1], [0, 1], 'k--', lw=lw)plt.xlim([0.0, 1.0])plt.ylim([0.0, 1.05])plt.xlabel('False Positive Rate')plt.ylabel('True Positive Rate')plt.title('Some extension of Receiver operating characteristic to multi-class')plt.legend(loc="lower right")plt.savefig("../images/ROC/ROC_5分类.png")plt.show()print("--- %s seconds ---" % (time.time() - start_time))

ROC图如下所示：

以上这篇python实现二分类和多分类的ROC曲线教程就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。