多类别混淆矩阵中各个类别的误报率(FPR)

时间:2020-05-05 00:42:51

标签: python machine-learning scikit-learn confusion-matrix multiclass-classification

我使用高斯NB分类器获得了分类报告和混淆矩阵。

from sklearn.naive_bayes import GaussianNB
import pandas as pd

gnb = GaussianNB()
y_pred = gnb.fit(train_x, train_Y).predict(test_x)
results_nm = confusion_matrix(test_Y,y_pred)
print(classification_report(test_Y,y_pred))
print(results_nm)

Ouput

enter image description here

如何找到各个类别(良性,dos,探针,r2l,u2r)的假阳性率(FPR)?

0 个答案:

没有答案