https://blog.csdn.net/qq_41645987/article/details/109146503 博客代码:python画混淆矩阵图(里面有代码)
https://blog.csdn.net/li123_123_/article/details/91984838 混淆矩阵(confusion_matrix)的可视化
https://zhuanlan.zhihu.com/p/136140738 知乎:混淆矩阵及其可视化(里面有代码)
1,计算混淆矩阵
from sklearn.metrics import confusion_matrix #导入计算混淆矩阵的包
from sklearn.metrics import precision_score, recall_score, f1_score
from sklearn.metrics import accuracy_score
actual = data3['label'] #真实的类别标签(data3是个dataframe,label是其中的一列)
predicted = data3['Label'] #预测的类别标签
# 计算混淆矩阵
C=confusion_matrix(actual, predicted)
print(C)
'''
输出结果:
array([[1032, 1, 0, 0, 0],
[ 3, 965, 17, 0, 15],
[ 0, 10, 42, 0, 6],
[ 0, 11, 3, 0, 0],
[ 0, 98, 103, 0, 286]])
'''
2,用seaborn的热力图画混淆矩阵图
import seaborn as sns #导入包
df=pd.DataFrame(C)
sns.heatmap(df,fmt='g',annot=True,cmap='Blues')
# sns.heatmap(df,annot=True)
效果如下: