一.二分类的正确率 or 预测正确的样本个数,混淆矩阵
from sklearn import metrics
y_pred=my_model.predict(x_test)
metrics.accuracy_score(y_test,y_pred)
metrics.confusion_matrix(y_true, y_pred, labels=None, sample_weight=None)
tn, fp, fn, tp =metrics.confusion_matrix(y_true, y_pred, labels=None, sample_weight=None).ravel()
metrics.confusion_matrix(y_test,ypred_lr,labels=[0,1])
metrics.confusion_matrix(y_test,ypred_lr)
二.ROC曲线 ,AUC
roc_auc_score(y_true, y_score, average='macro', sample_weight=None, max_fpr=None)
metric.roc_auc_score(y_test,y_pred)
roc_curve(y_true, y_score, pos_label=None, sample_weight=None, drop_intermediate=True)
fpr, tpr, thresholds=metrics.roc_curve(y_test,ypred_lr)
三.分类模型的评价指标
classification_report(y_true, y_pred, labels=None, target_names=None, sample_weight=None, digits=2, output_dict=False)
metrics.classification_report(y_test,ypred_rf)