import pandas as pd
import numpy as np
import math
df=pd.DataFrame({'Class': ['A1','A1','A1','A2','A3','A3'],
'Force': [50,150,100,120,140,160] },
columns=['Class', 'Force'])
print(df)
print('-'*30)
stats = df.groupby(['Class'])['Force'].agg(['mean', 'count', 'std'])
print(stats)
print('-'*30)
ci95_hi = []
ci95_lo = []
for i in stats.index:
m, c, s = stats.loc[i]
ci95_hi.append(m + 1.96*s/math.sqrt(c))
ci95_lo.append(m - 1.96*s/math.sqrt(c))
stats['ci95_hi'] = ci95_hi
stats['ci95_lo'] = ci95_lo
print(stats)
输出是
Class Force
0 A1 50
1 A1 150
2 A1 100
3 A2 120
4 A3 140
5 A3 160
------------------------------
mean count std
Class
A1 100 3 50.000000
A2 120 1 NaN
A3 150 2 14.142136
------------------------------
mean count std ci95_hi ci95_lo
Class
A1 100 3 50.000000 156.580326 43.419674
A2 120 1 NaN NaN NaN
A3 150 2 14.142136 169.600000 130.400000
602392714
清零编程群