import pandas as pd import numpy as np # 读取Excel文件 path = r'F:\BM2023\BM20230531\冠幅\all.xlsx' df = pd.read_excel(path) # 从数据框中提取两列数据，并转换为numpy数组 x = df["wp"].values y = df["w"].values # 进行直线拟合，并计算拟合误差的均方根 coefficients = np.polyfit(x, y, 1) y_fit = np.polyval(coefficients, x) rmse = np.sqrt(np.mean((y - y_fit) ** 2)) print("拟合误差的均方根为：", rmse)增加计算R2的代码

要计算R2，需要先计算总离差平方和（TSS）和残差平方和（RSS），然后用1减去RSS/TSS即可得到R2的值。以下是增加计算R2的代码：

import pandas as pd
import numpy as np
from sklearn.metrics import r2_score # 导入r2_score函数

# 读取Excel文件
path = r'F:\BM2023\BM20230531\冠幅\all.xlsx'
df = pd.read_excel(path)

# 从数据框中提取两列数据，并转换为numpy数组
x = df["wp"].values
y = df["w"].values

# 进行直线拟合，并计算拟合误差的均方根
coefficients = np.polyfit(x, y, 1)
y_fit = np.polyval(coefficients, x)
rmse = np.sqrt(np.mean((y - y_fit) ** 2))

# 计算R2
y_mean = np.mean(y)
tss = np.sum((y - y_mean) ** 2)
rss = np.sum((y - y_fit) ** 2)
r2 = 1 - rss / tss

print("拟合误差的均方根为：", rmse)
print("R2为：", r2)