DataFrame子类的属性设置器

Question

我正在尝试设置pd.DataFrame的子类，该子类在初始化（group和timestamp_col）时有两个必需的参数。我想对这些参数group和timestamp_col运行验证，因此我对每个属性都有一个setter方法。在我尝试set_index()并获得TypeError: 'NoneType' object is not iterable之前，这些都是有效的。在test_set_index和test_assignment_with_indexed_obj中，似乎没有参数被传递给我的setter函数。如果我将if g == None: return添加到setter函数中，我可以通过测试用例，但我认为这不是正确的解决方案

我应该如何实现这些必需参数的属性验证

下面是我的班级：

import pandas as pd
import numpy as np


class HistDollarGains(pd.DataFrame):
    @property
    def _constructor(self):
        return HistDollarGains._internal_ctor

    _metadata = ["group", "timestamp_col", "_group", "_timestamp_col"]

    @classmethod
    def _internal_ctor(cls, *args, **kwargs):
        kwargs["group"] = None
        kwargs["timestamp_col"] = None
        return cls(*args, **kwargs)

    def __init__(
        self,
        data,
        group,
        timestamp_col,
        index=None,
        columns=None,
        dtype=None,
        copy=True,
    ):
        super(HistDollarGains, self).__init__(
            data=data, index=index, columns=columns, dtype=dtype, copy=copy
        )

        self.group = group
        self.timestamp_col = timestamp_col

    @property
    def group(self):
        return self._group

    @group.setter
    def group(self, g):
        if g == None:
            return

        if isinstance(g, str):
            group_list = [g]
        else:
            group_list = g

        if not set(group_list).issubset(self.columns):
            raise ValueError("Data does not contain " + '[' + ', '.join(group_list) + ']')
        self._group = group_list

    @property
    def timestamp_col(self):
        return self._timestamp_col

    @timestamp_col.setter
    def timestamp_col(self, t):
        if t == None:
            return
        if not t in self.columns:
            raise ValueError("Data does not contain " + '[' + t + ']')
        self._timestamp_col = t

以下是我的测试用例：

import pytest

import pandas as pd
import numpy as np

from myclass import *


@pytest.fixture(scope="module")
def sample():
    samp = pd.DataFrame(
        [
            {"timestamp": "2020-01-01", "group": "a", "dollar_gains": 100},
            {"timestamp": "2020-01-01", "group": "b", "dollar_gains": 100},
            {"timestamp": "2020-01-01", "group": "c", "dollar_gains": 110},
            {"timestamp": "2020-01-01", "group": "a", "dollar_gains": 110},
            {"timestamp": "2020-01-01", "group": "b", "dollar_gains": 90},
            {"timestamp": "2020-01-01", "group": "d", "dollar_gains": 100},
        ]
    )

    return samp

@pytest.fixture(scope="module")
def sample_obj(sample):
    return HistDollarGains(sample, "group", "timestamp")

def test_constructor_without_args(sample):
    with pytest.raises(TypeError):
        HistDollarGains(sample)


def test_constructor_with_string_group(sample):
    hist_dg = HistDollarGains(sample, "group", "timestamp")
    assert hist_dg.group == ["group"]
    assert hist_dg.timestamp_col == "timestamp"


def test_constructor_with_list_group(sample):
    hist_dg = HistDollarGains(sample, ["group", "timestamp"], "timestamp")

def test_constructor_with_invalid_group(sample):
    with pytest.raises(ValueError):
        HistDollarGains(sample, "invalid_group", np.random.choice(sample.columns))

def test_constructor_with_invalid_timestamp(sample):
    with pytest.raises(ValueError):
        HistDollarGains(sample, np.random.choice(sample.columns), "invalid_timestamp")

def test_assignment_with_indexed_obj(sample_obj):
    b = sample_obj.set_index(sample_obj.group + [sample_obj.timestamp_col])

def test_set_index(sample_obj):
    # print(isinstance(a, pd.DataFrame))
    assert sample_obj.set_index(sample_obj.group + [sample_obj.timestamp_col]).index.names == ['group', 'timestamp']

Answer 1

set_index()方法将在内部调用self.copy()来创建DataFrame对象的副本（请参阅源代码here），在其中使用自定义构造函数方法_internal_ctor()来创建新对象（source）。请注意self._constructor()与self._internal_ctor()相同，这是几乎所有pandas类在深度复制或切片等操作期间创建新实例的常用内部方法。您的问题实际上源于此功能：

class HistDollarGains(pd.DataFrame):
    ...
    @classmethod
    def _internal_ctor(cls, *args, **kwargs):
        kwargs["group"]         = None
        kwargs["timestamp_col"] = None
        return cls(*args, **kwargs) # this is equivalent to calling
                                    # HistDollarGains(data, group=None, timestamp_col=None)

我猜你是从the github issue复制了这段代码。 行kwargs["**"] = None显式地告诉构造函数将None设置为group和timestamp_col。最后，setter/validator获取None作为新值并引发错误

因此，应该将可接受的值设置为group和timestamp_col

    @classmethod
    def _internal_ctor(cls, *args, **kwargs):
        kwargs["group"]         = []
        kwargs["timestamp_col"] = 'timestamp' # or whatever name that makes your validator happy
        return cls(*args, **kwargs)

然后可以删除验证器中的if g == None: return行