python - Pandas:自定义类作为具有多索引的列标题

Question

我正在尝试将对象用作多索引中的列标题数据框，但我似乎无法让它工作。 __eq__, __hash__和 __str__ 只适用于简单的数据框。

这是一个小例子:

class Signal:

    def __init__(self, name):
        self.name = name


    def __eq__(self, other):
        try:
            return self.name == other or self.name == other.name
        except AttributeError as err:
            return False

    def __str__(self):
        return str(self.name)

    def __hash__(self):
        return hash(self.name)

if __name__ == '__main__':
    import pandas as pd
    import numpy as np
    a = Signal('name')
    b = Signal('name2')
    c = Signal('something')

    data = {
        ('A', a): np.arange(2),
        ('A', b): np.ones(2),
        ('B', c): np.zeros(2)
    }

    df = pd.DataFrame(data)

    print(df)
    print('-----------')
    print(df['A'])

我还尝试实现 __le__、__ge__ 和 __ne__。那没有做任何事。我真的不知道我还能做什么。有人有什么想法吗？

Answer 1

定义__lt__和__gt__后

class Signal:

    def __init__(self, name):
        self.name = name


    def __eq__(self, other):
        try:
            return self.name == other or self.name == other.name
        except AttributeError as err:
            return False

    def __lt__(self, other):
        return self.name < other.name

    def __gt__(self, other):
        return self.name > other.name

    def __str__(self):
        return str(self.name)

    def __hash__(self):
        return hash(self.name)

---

import pandas as pd
import numpy as np
a = Signal('name')
b = Signal('name2')
c = Signal('something')

data = {
    ('A', a): np.arange(2),
    ('A', b): np.ones(2),
    ('B', c): np.zeros(2)
}

df = pd.DataFrame(data)

print(df, df['A'], sep='\n\n')

     A               B
  name name2 something
0    0   1.0       0.0
1    1   1.0       0.0

   name  name2
0     0    1.0
1     1    1.0