我想在Pandas DataFrame上应用分组操作,而不进行任何聚合。相反,我只想让分层结构在MultiIndex中得到体现。
import pandas as pd
def multi_index_group_by(df, columns):
# TODO: How to write this? (Hard-coded to give the desired result for the example.)
if columns == ["b"]:
df.index = pd.MultiIndex(levels=[[0,1],[0,1,2]], labels=[[0,1,0,1,0],[0,0,1,1,2]])
return df
if columns == ["c"]:
df.index = pd.MultiIndex(levels=[[0,1],[0,1],[0,1]], labels=[[0,1,0,1,0],[0,0,0,1,1],[0,0,1,0,0]])
return df
if __name__ == '__main__':
df = pd.DataFrame({
"a": [0,1,2,3,4],
"b": ["b0","b1","b0","b1","b0"],
"c": ["c0","c0","c0","c1","c1"],
})
print(df.index.values) # [0,1,2,3,4]
# Add level of grouping
df = multi_index_group_by(df, ["b"])
print(df.index.values) # [(0, 0) (1, 0) (0, 1) (1, 1) (0, 2)]
# Examples
print(df.loc[0]) # Group 0
print(df.loc[1,1]) # Group 1, Item 1
# Add level of grouping
df = multi_index_group_by(df, ["c"])
print(df.index.values) # [(0, 0, 0) (1, 0, 0) (0, 0, 1) (1, 1, 0) (0, 1, 0)]
# Examples
print(df.loc[0]) # Group 0
print(df.loc[0,0]) # Group 0, Sub-Group 0
print(df.loc[0,0,1]) # Group 0, Sub-Group 0, Item 1
如何最好地实现multi_index_group_by
?以下方法几乎可以完成,但生成的索引不是数字:
index_columns = []
# Add level of grouping
index_columns += ["b"]
print(df.set_index(index_columns, drop=False))
# Add level of grouping
index_columns += ["c"]
print(df.set_index(index_columns, drop=False))
编辑: 为了澄清,在这个例子中,最终的索引应该等同于:
[
[ #b0
[ #c0
{"a": 0, "b": "b0", "c": "c0"},
{"a": 2, "b": "b0", "c": "c0"},
],
[ #c1
{"a": 4, "b": "b0", "c": "c1"},
]
],
[ #b1
[ #c0
{"a": 1, "b": "b1", "c": "c0"},
],
[ #c1
{"a": 3, "b": "b1", "c": "c1"},
]
]
]
编辑:这是我到目前为止最好的翻译:
def autoincrement(value=0):
def _autoincrement(*args, **kwargs):
nonlocal value
result = value
value += 1
return result
return _autoincrement
def swap_levels(df, i, j):
order = list(range(len(df.index.levels)))
order[i], order[j] = order[j], order[i]
return df.reorder_levels(order)
def multi_index_group_by(df, columns):
new_index = df.groupby(columns)[columns[0]].aggregate(autoincrement())
result = df.join(new_index.rename("_new_index"), on=columns)
result.set_index('_new_index', append=True, drop=True, inplace=True)
result.index.name = None
result = swap_levels(result, -2, -1)
return result
除了最后一个级别没有改变,它给出了正确的结果。仍然觉得有很大的改进空间。
b
的MultiIndex正确吗?最后一个元组中的2
代表哪个子组? - desiato