Pandas统计重复的列里面的值 Pandas统计重复的列里面的值方法

import pandas as pd
import numpy as np

salaries = pd.DataFrame({
 'name': ['BOSS', 'Lilei', 'Lilei', 'Han', 'BOSS', 'BOSS', 'Han', 'BOSS'],
 'Year': [2016, 2016, 2016, 2016, 2017, 2017, 2017, 2017],
 'Salary': [1, 2, 3, 4, 5, 6, 7, 8],
 'Bonus': [2, 2, 2, 2, 3, 4, 5, 6]
})
print(salaries)
print(salaries['Bonus'].duplicated(keep='first'))
print(salaries[salaries['Bonus'].duplicated(keep='first')].index)
print(salaries[salaries['Bonus'].duplicated(keep='first')])
print(salaries['Bonus'].duplicated(keep='last'))
print(salaries[salaries['Bonus'].duplicated(keep='last')].index)
print(salaries[salaries['Bonus'].duplicated(keep='last')])

 Bonus Salary Year name
0  2  1 2016 BOSS
1  2  2 2016 Lilei
2  2  3 2016 Lilei
3  2  4 2016 Han
4  3  5 2017 BOSS
5  4  6 2017 BOSS
6  5  7 2017 Han
7  6  8 2017 BOSS
0 False
1  True
2  True
3  True
4 False
5 False
6 False
7 False
Name: Bonus, dtype: bool
Int64Index([1, 2, 3], dtype='int64')
 Bonus Salary Year name
1  2  2 2016 Lilei
2  2  3 2016 Lilei
3  2  4 2016 Han
0  True
1  True
2  True
3 False
4 False
5 False
6 False
7 False
Name: Bonus, dtype: bool
Int64Index([0, 1, 2], dtype='int64')
 Bonus Salary Year name
0  2  1 2016 BOSS
1  2  2 2016 Lilei
2  2  3 2016 Lilei

方法1

m = np.zeros_like(a, dtype=bool)
m[np.unique(a, return_index=True)[1]] = True
a[~m]

方法2

a[~np.in1d(np.arange(len(a)), np.unique(a, return_index=True)[1], assume_unique=True)]

方法3

np.setxor1d(a, np.unique(a), assume_unique=True)

方法4

u, i = np.unique(a, return_inverse=True)
u[np.bincount(i) > 1]

方法5

s = np.sort(a, axis=None)
s[:-1][s[1:] == s[:-1]]