如何计算最小二乘拟合以上的点数？

Question

我想计算最小二乘拟合上方的点数。

from sklearn.mixture import GaussianMixture
from sklearn import preprocessing
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from scipy import stats
from astropy.io import ascii
from scipy.stats import norm
from astropy.timeseries import LombScargle
from astropy import stats

data4= pd.read_csv('Standard Dev main pop.csv')
names4 = data4.columns
df3 = pd.DataFrame(data4, columns=names4)
df3.head()
#print(c)


data5= pd.read_csv('2 Sigma Main pop.csv')
names5 = data5.columns
df5 = pd.DataFrame(data5, columns=names5)
df5.head()


data6= pd.read_csv('3 Sigma main pop.csv')
names6 = data6.columns
df6 = pd.DataFrame(data6, columns=names6)
df6.head()

a=df5['Mean Mag']
b=df5['Std']

c=df6['Mean Mag']
d=df6['Std']

e=df3['Mean Mag']
f=df3['Std']

ax=plt.scatter(e,f, label=' All sources')
#ay=plt.scatter(c,d, label='3 Sigma from Median Std')

lstsq_coefs = np.polyfit(a, b, deg=2)
lstsq_preds = lstsq_coefs[0]*a**2 + lstsq_coefs[1]*a + lstsq_coefs[2]

plt.plot(a, lstsq_preds, linestyle="dashed", color="red", label="Least squares 2 sigma")


#ay=plt.scatter(c,d, label='3 Sigma from Median Std')

lstsq_coefs1 = np.polyfit(c ,d, deg=2)
lstsq_preds1 = lstsq_coefs1[0]*c**2 + lstsq_coefs1[1]*c + lstsq_coefs1[2]

plt.plot(c, lstsq_preds1, linestyle="dashed", color="black", label="Least squares 3 sigma")
plt.legend(loc='best',fontsize= 16)
plt.gcf().set_size_inches((12,10))
plt.ylim(0,0.1)
plt.show()

我想计算每个最小二乘拟合上方的点数。 我尝试了一些非常繁琐的方法，从长远来看是行不通的。

Answer 1

您可以使用numpy模块比较它们：

import numpy as np
f = np.array(f)
lstsq_preds = np.array(lstsq_preds)
lstsq_preds1 = np.array(lstsq_preds1)
print("Number above least squares #1:", len(f[f > lstsq_preds]))
print("Number above least squares #2:", len(f[f > lstsq_preds]))

请注意，我只是将 arrays 转换为 numpy 以确保它们是 numpy。可能没有必要使用这些转换线，因为您正在处理 pandas dataframe。