r2与NSE的差异
difference between Nash-Sutcliffe efficiency and coefficient of determination
相当于r2在进行计算的时候会先进行一个线性变化
为什么我用python的两种方式计算的R方结果不一样?
方法一:from scipy.stats import pearsonr 方法二: from sklearn.metrics import r2_score
r2_score只有在是线性满足线性模型时才是r2,否则是nse
应该是,所以r2_score计算的其实是NSE,真正需要计算corr的时候最好使用pearson r
https://math.stackexchange.com/questions/4107786/why-square-of-pearson-correlation-does-not-match-with-r2-score