U
|
¬ý°d9& ã @ s° d dl mZ d dlmZmZmZmZ d dlZd dl m
|
Z
|
d dl m Z m Z d dlmZmZ erxd dlmZmZ d dlmZ G d d
|
d
|
Ze ejG d d d ZG d d dZdS )é )Ú annotations)Ú TYPE_CHECKINGÚIterableÚLiteralÚcastN)ÚPositionalIndexer)Úcache_readonlyÚdoc)Ú
|
is_integerÚ is_list_like)Ú DataFrameÚSeries)Úgroupbyc @ s e Zd ZdZeddddZdddd d
|
Zd ddd d ZdddddZdddddZ dddddZ
|
eddddZ edddd Z d S ) ÚGroupByIndexingMixinz<
|
Mixin for adding ._positional_selector to GroupBy.
|
ÚGroupByPositionalSelector)Úreturnc C s t rttj| }n| }t|S )aÌ
|
|
Return positional selection for each group.
|
|
``groupby._positional_selector[i:j]`` is similar to
|
``groupby.apply(lambda x: x.iloc[i:j])``
|
but much faster and preserves the original index and order.
|
|
``_positional_selector[]`` is compatible with and extends :meth:`~GroupBy.head`
|
and :meth:`~GroupBy.tail`. For example:
|
|
- ``head(5)``
|
- ``_positional_selector[5:-5]``
|
- ``tail(5)``
|
|
together return all the rows.
|
|
Allowed inputs for the index are:
|
|
- An integer valued iterable, e.g. ``range(2, 4)``.
|
- A comma separated list of integers and slices, e.g. ``5``, ``2, 4``, ``2:4``.
|
|
The output format is the same as :meth:`~GroupBy.head` and
|
:meth:`~GroupBy.tail`, namely
|
a subset of the ``DataFrame`` or ``Series`` with the index and order preserved.
|
|
Returns
|
-------
|
Series
|
The filtered subset of the original Series.
|
DataFrame
|
The filtered subset of the original DataFrame.
|
|
See Also
|
--------
|
DataFrame.iloc : Purely integer-location based indexing for selection by
|
position.
|
GroupBy.head : Return first n rows of each group.
|
GroupBy.tail : Return last n rows of each group.
|
GroupBy.nth : Take the nth row from each group if n is an int, or a
|
subset of rows, if n is a list of ints.
|
|
Notes
|
-----
|
- The slice step cannot be negative.
|
- If the index specification results in overlaps, the item is not duplicated.
|
- If the index specification changes the order of items, then
|
they are returned in their original order.
|
By contrast, ``DataFrame.iloc`` can change the row order.
|
- ``groupby()`` parameters such as as_index and dropna are ignored.
|
|
The differences between ``_positional_selector[]`` and :meth:`~GroupBy.nth`
|
with ``as_index=False`` are:
|
|
- Input to ``_positional_selector`` can include
|
one or more slices whereas ``nth``
|
just handles an integer or a list of integers.
|
- ``_positional_selector`` can accept a slice relative to the
|
last row of each group.
|
- ``_positional_selector`` does not have an equivalent to the
|
``nth()`` ``dropna`` parameter.
|
|
Examples
|
--------
|
>>> df = pd.DataFrame([["a", 1], ["a", 2], ["a", 3], ["b", 4], ["b", 5]],
|
... columns=["A", "B"])
|
>>> df.groupby("A")._positional_selector[1:2]
|
A B
|
1 a 2
|
4 b 5
|
|
>>> df.groupby("A")._positional_selector[1, -1]
|
A B
|
1 a 2
|
2 a 3
|
4 b 5
|
)r r r ÚGroupByr ©ÚselfZ groupby_self© r úSd:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\pandas/core/groupby/indexing.pyÚ_positional_selector$ s Nz)GroupByIndexingMixin._positional_selectorúPositionalIndexer | tuplez
|
np.ndarray©Úargr c C s¼ t |rHtdd tt|D r6| ttt |¡}q| tt|¡}nDt|t r^|
|
|¡}n.t |rx| tt|¡}nt dt| dt|tr°|r¦| jdk}n
|
| jdk }ttj|S )Nc s s | ]}t |V qd S ©N)r
|
)Ú.0Úir r r Ú <genexpr> s zJGroupByIndexingMixin._make_mask_from_positional_indexer.<locals>.<genexpr>zInvalid index zE. Must be integer, list-like, slice or a tuple of integers and slicesr )r Úallr r Ú_make_mask_from_listÚintÚ_make_mask_from_tupleÚtupleÚ
|
isinstanceÚsliceÚ_make_mask_from_slicer
|
Ú_make_mask_from_intÚ TypeErrorÚtypeÚboolÚ_ascending_countÚnpZndarray©r r Úmaskr r r Ú"_make_mask_from_positional_indexerz s
|
ÿ
|
|
z7GroupByIndexingMixin._make_mask_from_positional_indexerr! c C s& |dkr| j |kS | j| d kS d S )Nr é )r+ Ú_descending_count)r r r r r r' s
|
z(GroupByIndexingMixin._make_mask_from_intz Iterable[int]zbool | np.ndarray)Úargsr c C sP dd |D }dd |D }d}|r6|t | j|¡O }|rL|t | j|¡O }|S )Nc S s g | ]}|d kr|qS )r r ©r r r r r Ú
|
<listcomp> s z=GroupByIndexingMixin._make_mask_from_list.<locals>.<listcomp>c S s g | ]}|d k r| d qS )r r0 r r3 r r r r4 s F)r, Úisinr+ r1 )r r2 ZpositiveÚnegativer. r r r r s z)GroupByIndexingMixin._make_mask_from_listr# c C s^ d}|D ]P}t |r*|| tt|¡O }qt|trD|| |¡O }qtdt| dq|S )NFzInvalid argument z. Should be int or slice.) r
|
r' r r! r$ r% r& Ú
|
ValueErrorr) )r r2 r. r r r r r" « s
|
ÿz*GroupByIndexingMixin._make_mask_from_tupler% c C s* |j }|j}|j}|d k r2|dk r2td| dd}|d krBd}|d krf|dkrò|| j| dkM }n|dkr|| j|kM }|dkrò|| j| | dkM }nV|| j| k M }| j| d }| j| j |d dk }t || j|¡}||| dkM }|d k r&|dkr|| j|k M }n|| j| kM }|S )Nr z Invalid step z. Must be non-negativeTr0 )ÚstartÚstopÚstepr7 r+ r1 r, Úwhere)r r r8 r9 r: r. Z offset_arrayZ limit_arrayr r r r& º s6 þ
|
|
z*GroupByIndexingMixin._make_mask_from_slicec C s t rttj| }n| }| ¡ S r ©r r r r Z_cumcount_arrayr r r r r+ ä s z%GroupByIndexingMixin._ascending_countc C s" t rttj| }n| }|jddS )NF)Z ascendingr< r r r r r1 í s z&GroupByIndexingMixin._descending_countN) Ú__name__Ú
|
__module__Ú __qualname__Ú__doc__r r r/ r' r r" r& r+ r1 r r r r r s U *r c @ s, e Zd ZdddddZdddd d
|
Zd S ) r úgroupby.GroupByÚNone©Úgroupby_objectr c C s
|
|| _ d S r ©rD ©r rD r r r Ú__init__ù s z"GroupByPositionalSelector.__init__r úDataFrame | Seriesr c C s | j |¡}| j |¡S )a
|
Select by positional index per group.
|
|
Implements GroupBy._positional_selector
|
|
Parameters
|
----------
|
arg : PositionalIndexer | tuple
|
Allowed values are:
|
- int
|
- int valued iterable such as list or range
|
- slice with step either None or positive
|
- tuple of integers and slices
|
|
Returns
|
-------
|
Series
|
The filtered subset of the original groupby Series.
|
DataFrame
|
The filtered subset of the original groupby DataFrame.
|
|
See Also
|
--------
|
DataFrame.iloc : Integer-location based indexing for selection by position.
|
GroupBy.head : Return first n rows of each group.
|
GroupBy.tail : Return last n rows of each group.
|
GroupBy._positional_selector : Return positional selection for each group.
|
GroupBy.nth : Take the nth row from each group if n is an int, or a
|
subset of rows, if n is a list of ints.
|
)rD r/ Z_mask_selected_objr- r r r Ú __getitem__ü s z%GroupByPositionalSelector.__getitem__N)r= r> r? rG rI r r r r r ÷ s r c @ sD e Zd ZdZdddddZddd d
|
d d d Zdd
|
dddZdS )ÚGroupByNthSelectorzO
|
Dynamically substituted for GroupBy.nth to enable both call and index
|
rA rB rC c C s
|
|| _ d S r rE rF r r r rG $ s zGroupByNthSelector.__init__Nr z Literal[('any', 'all', None)]rH )ÚnÚdropnar c C s | j ||¡S r ©rD Z_nth)r rK rL r r r Ú__call__' s zGroupByNthSelector.__call__)rK r c C s | j |¡S r rM )r rK r r r rI . s z GroupByNthSelector.__getitem__)N)r= r> r? r@ rG rN rI r r r r rJ s
|
ýrJ )Ú
|
__future__r Útypingr r r r Únumpyr, Zpandas._typingr Zpandas.util._decoratorsr r Zpandas.core.dtypes.commonr
|
r Zpandasr r Zpandas.core.groupbyr r r r rJ r r r r Ú<module> s Y'
|
