传统的numpy与scipy甚至直接自行写python代码都是可以的（如果能忍受python循环的低效的话），另外还有专门进行统计计算的包statsmodels可供使用
import numpy as np
from scipy import stats
import statsmodels.api as sm
import math
def get_r2_numpy(x, y):
slope, intercept = np.polyfit(x, y, 1)
r_squared = 1 - (sum((y - (slope * x + intercept))**2) / ((len(y) - 1) * np.var(y, ddof=1)))
return r_squared
def get_r2_scipy(x, y):
_, _, r_value, _, _ = stats.linregress(x, y)
return r_value**2
def get_r2_statsmodels(x, y):
return sm.OLS(y, sm.add_constant(x)).fit().rsquared
def get_r2_python(x_list, y_list):
n = len(x)
x_bar = sum(x_list)/n
y_bar = sum(y_list)/n
x_std = math.sqrt(sum([(xi-x_bar)**2 for xi in x_list])/(n-1))
y_std = math.sqrt(sum([(yi-y_bar)**2 for yi in y_list])/(n-1))
zx = [(xi-x_bar)/x_std for xi in x_list]
zy = [(yi-y_bar)/y_std for yi in y_list]
r = sum(zxi*zyi for zxi, zyi in zip(zx, zy))/(n-1)
return r**2