机器学习2——如何评价模型的好坏_如何进行模型评估训练好坏-优快云博客

本文链接：https://blog.youkuaiyun.com/Aries_yang/article/details/103080957

本文探讨了机器学习中评价模型性能的关键指标，包括精度、查准率/精准率、查全率/召回率、F1度量、MCC马修斯相关系数、平均绝对误差、均方误差和R得分，通过理论讲解与代码实现，帮助理解如何有效评估模型好坏。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

理论部分：

from sklearn.model_selection import train_test_split

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=666)

from sklearn.metrics import accuracy_score
accuracy_score(y_test_binarized,predictions_binarized)

from sklearn.metrics import precision_score
precision_score(y_test_binarized,predictions_binarized)

from sklearn.metrics import recall_score
recall_score(y_test_binarized,predictions_binarized)

from sklearn.metrics import f1_score
f1_score(y_test_binarized,predictions_binarized)

from sklearn.metrics import matthews_corrcoef
matthews_corrcoef(y_test_binarized,predictions_binarized)

注：一个函数共同生成精准率/召回率/F1得分

from sklearn.metrics import classification_report
classification_report(y_test_binarized,predictions_binarized)

from sklearn.metrics import mean_absolute_error
mean_absolute_error(y_test,predictions)

from sklearn.metrics import mean_squared_error
mean_squared_error(y_test,predictions)

from sklearn.metrics import r2_error
r2_error(y_test,predictions)