U
|
¬ý°du` ã @ sâ d dl mZ d dlmZ d dlmZmZmZ d dlm Z m
|
Z
|
m Z er`d dl m Z mZ d dlmZ d dlmZ d dlmZmZmZ d d lmZmZmZmZm Z m Z m Z m Z m Z d d
|
l!m"Z"m#Z# G d d d e#Z$G d d de"e$Z%dS )é )Ú annotations)Údedent)Ú TYPE_CHECKINGÚAnyÚCallable)ÚAxisÚQuantileInterpolationÚWindowingRankType)Ú DataFrameÚSeries)ÚNDFrame)Údoc)Ú BaseIndexerÚExpandingIndexerÚGroupbyIndexer) Ú _shared_docsÚcreate_section_headerÚkwargs_numeric_onlyÚ numba_notesÚtemplate_headerÚtemplate_returnsÚtemplate_see_alsoÚwindow_agg_numba_parametersÚwindow_apply_parameters)ÚBaseWindowGroupbyÚRollingAndExpandingMixinc s\ e Zd ZU dZdddgZded< dd d d ddd fdd ZddddZee d e
|
de
|
dddd fd d Z e Z ee ed eed ed
|
d!
d"d#d$d%dd'd( fd)d* Zee ed+eed eed ed
|
d!
d"d,d-d%
|
dd.d'd/d0d1d2d3 fd4d5 Zee ed+ee ed eed eed6ed
|
d!
d"d7d7d% dd'd/d0d8 fd9d: Zee ed+ee ed eed eed6ed
|
d!
d"d;d<d% dd'd/d0d8 fd=d> Zee ed+ee ed eed eed6ed
|
d!
d"d?d@d% dd'd/d0d8 fdAdB Zee ed+ee ed eed eed6ed
|
d!
d"dCdCd% dd'd/d0d8 fdDdE Zee ed+ee ed eed eed6ed
|
d!
d"dFdFd% dd'd/d0d8 fdGdH Zee ed+e
|
dI dJdd¡eedKed eed dLeed6e
|
dM dJdd¡edNe
|
dO dJdd¡d"dPdQd%dd d'd/d0dR fdSdT Z ee ed+e
|
dI dJdd¡eedKed eed dUeed6e
|
dV dJdd¡edNe
|
dW dJdd¡d"dXdYd%dd d'd/d0dR fdZd[ Z ee ed+e
|
dI dJdd¡eed eed eed6d\edNe
|
d] dJdd¡d"d^d_d%dd d'd` fdadb Z ee ed+eed eed dceed6ddd"dedfd% dd'd( fdgdh Z ee ed+eed eed dieed6djedNe
|
dk dJdd¡d"dldmd%dd'd( fdndo Z!ee ed+e
|
dp dJdd¡eed eed ed
|
d!
d"dqdqd% ddsdtd'du fdvdw Z"ee dxed+e
|
dy dJdd¡eed eed eedNe
|
dz dJdd¡d"d{d{d%dd~d'd'd'd fdd Z#ee ed+e
|
d dJdd¡eed eed ed
|
d!
d"ddd% d d
dd d'd fdd Z$ee ed+e
|
d dJdd¡eed eed e
|
d dJdd¡eed6e
|
d dJdd¡d"ddd%d¡d
dd d'd fdd Z% Z&S )¢Ú Expandingaê
|
Provide expanding window calculations.
|
|
Parameters
|
----------
|
min_periods : int, default 1
|
Minimum number of observations in window required to have a value;
|
otherwise, result is ``np.nan``.
|
|
axis : int or str, default 0
|
If ``0`` or ``'index'``, roll across the rows.
|
|
If ``1`` or ``'columns'``, roll across the columns.
|
|
For `Series` this parameter is unused and defaults to 0.
|
|
method : str {'single', 'table'}, default 'single'
|
Execute the rolling operation per single column or row (``'single'``)
|
or over the entire object (``'table'``).
|
|
This argument is only implemented when specifying ``engine='numba'``
|
in the method call.
|
|
.. versionadded:: 1.3.0
|
|
Returns
|
-------
|
``Expanding`` subclass
|
|
See Also
|
--------
|
rolling : Provides rolling window calculations.
|
ewm : Provides exponential weighted functions.
|
|
Notes
|
-----
|
See :ref:`Windowing Operations <window.expanding>` for further usage details
|
and examples.
|
|
Examples
|
--------
|
>>> df = pd.DataFrame({"B": [0, 1, 2, np.nan, 4]})
|
>>> df
|
B
|
0 0.0
|
1 1.0
|
2 2.0
|
3 NaN
|
4 4.0
|
|
**min_periods**
|
|
Expanding sum with 1 vs 3 observations needed to calculate a value.
|
|
>>> df.expanding(1).sum()
|
B
|
0 0.0
|
1 1.0
|
2 3.0
|
3 3.0
|
4 7.0
|
>>> df.expanding(3).sum()
|
B
|
0 NaN
|
1 NaN
|
2 3.0
|
3 3.0
|
4 7.0
|
Ú min_periodsÚaxisÚmethodz list[str]Ú _attributesé r ÚsingleNr Úintr ÚstrÚNone)Úobjr r r Úreturnc s t j|||||d d S )N)r& r r r Ú selection)ÚsuperÚ__init__)Úselfr& r r r r( ©Ú __class__© úSd:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\pandas/core/window/expanding.pyr* u s ûzExpanding.__init__r ©r' c C s t S )z[
|
Return an indexer class that will compute the window start and end bounds
|
)r )r+ r. r. r/ Ú_get_window_indexer
s z Expanding._get_window_indexerÚ aggregatez£
|
See Also
|
--------
|
pandas.DataFrame.aggregate : Similar DataFrame method.
|
pandas.Series.aggregate : Similar Series method.
|
a
|
Examples
|
--------
|
>>> df = pd.DataFrame({"A": [1, 2, 3], "B": [4, 5, 6], "C": [7, 8, 9]})
|
>>> df
|
A B C
|
0 1 4 7
|
1 2 5 8
|
2 3 6 9
|
|
>>> df.ewm(alpha=0.5).mean()
|
A B C
|
0 1.000000 4.000000 7.000000
|
1 1.666667 4.666667 7.666667
|
2 2.428571 5.428571 8.428571
|
zSeries/DataframeÚ )Zsee_alsoZexamplesÚklassr c s t j|f||S )N)r) r2 )r+ ÚfuncÚargsÚkwargsr, r. r/ r2 s zExpanding.aggregateZReturnszSee AlsoéÿÿÿÿZ expandingz count of non NaN observationsÚcount)Z window_methodZaggregation_descriptionZ
|
agg_methodFÚbool©Ú numeric_onlyc s t j|dS ©Nr; )r) r9 ©r+ r< r, r. r/ r9 ¯ s zExpanding.countZ
|
Parameterszcustom aggregation functionÚapplyzCallable[..., Any]z
|
str | Nonezdict[str, bool] | Noneztuple[Any, ...] | Nonezdict[str, Any] | None)r5 ÚrawÚengineÚ engine_kwargsr6 r7 c s t j||||||dS )N)r@ rA rB r6 r7 )r) r? )r+ r5 r@ rA rB r6 r7 r, r. r/ r? ¼ s úzExpanding.applyZNotesÚsum©r< rA rB c s t j|||dS ©NrD )r) rC ©r+ r< rA rB r, r. r/ rC Ú s
|
ýz Expanding.sumÚmaximumÚmaxc s t j|||dS rE )r) rH rF r, r. r/ rH õ s
|
ýz Expanding.maxZminimumÚminc s t j|||dS rE )r) rI rF r, r. r/ rI s
|
ýz Expanding.minÚmeanc s t j|||dS rE )r) rJ rF r, r. r/ rJ + s
|
ýzExpanding.meanÚmedianc s t j|||dS rE )r) rK rF r, r. r/ rK F s
|
ýzExpanding.medianz¼
|
ddof : int, default 1
|
Delta Degrees of Freedom. The divisor used in calculations
|
is ``N - ddof``, where ``N`` represents the number of elements.
|
|
Ú
|
z1.4z/numpy.std : Equivalent method for NumPy array.
|
zÛ
|
The default ``ddof`` of 1 used in :meth:`Series.std` is different
|
than the default ``ddof`` of 0 in :func:`numpy.std`.
|
|
A minimum of one period is required for the rolling calculation.
|
|
ZExamplesa
|
>>> s = pd.Series([5, 5, 6, 7, 5, 5, 5])
|
|
>>> s.expanding(3).std()
|
0 NaN
|
1 NaN
|
2 0.577350
|
3 0.957427
|
4 0.894427
|
5 0.836660
|
6 0.786796
|
dtype: float64
|
zstandard deviationÚstd©Úddofr< rA rB c s t j||||dS ©NrN )r) rM ©r+ rO r< rA rB r, r. r/ rM a s 5üz Expanding.stdz/numpy.var : Equivalent method for NumPy array.
|
zÛ
|
The default ``ddof`` of 1 used in :meth:`Series.var` is different
|
than the default ``ddof`` of 0 in :func:`numpy.var`.
|
|
A minimum of one period is required for the rolling calculation.
|
|
a
|
>>> s = pd.Series([5, 5, 6, 7, 5, 5, 5])
|
|
>>> s.expanding(3).var()
|
0 NaN
|
1 NaN
|
2 0.333333
|
3 0.916667
|
4 0.800000
|
5 0.700000
|
6 0.619048
|
dtype: float64
|
ZvarianceÚvarc s t j||||dS rP )r) rR rQ r, r. r/ rR s 5üz Expanding.varz:A minimum of one period is required for the calculation.
|
|
zÁ
|
>>> s = pd.Series([0, 1, 2, 3])
|
|
>>> s.expanding().sem()
|
0 NaN
|
1 0.707107
|
2 0.707107
|
3 0.745356
|
dtype: float64
|
zstandard error of meanÚsem©rO r< c s t j||dS )NrT )r) rS )r+ rO r< r, r. r/ rS Ù s #z Expanding.semz:scipy.stats.skew : Third moment of a probability density.
|
zDA minimum of three periods is required for the rolling calculation.
|
zunbiased skewnessÚskewc s t j|dS r= )r) rU r> r, r. r/ rU þ s zExpanding.skewz/scipy.stats.kurtosis : Reference SciPy method.
|
z<A minimum of four periods is required for the calculation.
|
|
a[
|
The example below will show a rolling calculation with a window size of
|
four matching the equivalent function call using `scipy.stats`.
|
|
>>> arr = [1, 2, 3, 4, 999]
|
>>> import scipy.stats
|
>>> print(f"{{scipy.stats.kurtosis(arr[:-1], bias=False):.6f}}")
|
-1.200000
|
>>> print(f"{{scipy.stats.kurtosis(arr, bias=False):.6f}}")
|
4.999874
|
>>> s = pd.Series(arr)
|
>>> s.expanding(4).kurt()
|
0 NaN
|
1 NaN
|
2 NaN
|
3 -1.200000
|
4 4.999874
|
dtype: float64
|
z,Fisher's definition of kurtosis without biasÚkurtc s t j|dS r= )r) rV r> r, r. r/ rV s &zExpanding.kurta
|
quantile : float
|
Quantile to compute. 0 <= quantile <= 1.
|
interpolation : {{'linear', 'lower', 'higher', 'midpoint', 'nearest'}}
|
This optional parameter specifies the interpolation method to use,
|
when the desired quantile lies between two data points `i` and `j`:
|
|
* linear: `i + (j - i) * fraction`, where `fraction` is the
|
fractional part of the index surrounded by `i` and `j`.
|
* lower: `i`.
|
* higher: `j`.
|
* nearest: `i` or `j` whichever is nearest.
|
* midpoint: (`i` + `j`) / 2.
|
ÚquantileÚlinearÚfloatr ©rW Ú interpolationr< c s t j|||dS )NrZ )r) rW )r+ rW r[ r< r, r. r/ rW 8 s
|
"ýzExpanding.quantilez.. versionadded:: 1.4.0
|
|
a
|
method : {{'average', 'min', 'max'}}, default 'average'
|
How to rank the group of records that have the same value (i.e. ties):
|
|
* average: average rank of the group
|
* min: lowest rank in the group
|
* max: highest rank in the group
|
|
ascending : bool, default True
|
Whether or not the elements should be ranked in ascending order.
|
pct : bool, default False
|
Whether or not to display the returned rankings in percentile
|
form.
|
a+
|
>>> s = pd.Series([1, 4, 2, 3, 5, 3])
|
>>> s.expanding().rank()
|
0 1.0
|
1 2.0
|
2 2.0
|
3 3.0
|
4 5.0
|
5 3.5
|
dtype: float64
|
|
>>> s.expanding().rank(method="max")
|
0 1.0
|
1 2.0
|
2 2.0
|
3 3.0
|
4 5.0
|
5 4.0
|
dtype: float64
|
|
>>> s.expanding().rank(method="min")
|
0 1.0
|
1 2.0
|
2 2.0
|
3 3.0
|
4 5.0
|
5 3.0
|
dtype: float64
|
ÚrankÚaverageTr ©r Ú ascendingÚpctr< c s t j||||dS )Nr^ )r) r\ )r+ r r_ r` r< r, r. r/ r\ ` s DüzExpanding.ranka
|
other : Series or DataFrame, optional
|
If not supplied then will default to self and produce pairwise
|
output.
|
pairwise : bool, default None
|
If False then only matching columns between self and other will be
|
used and the output will be a DataFrame.
|
If True then all pairwise combinations will be calculated and the
|
output will be a MultiIndexed DataFrame in the case of DataFrame
|
inputs. In the case of missing elements, only complete pairwise
|
observations will be used.
|
ddof : int, default 1
|
Delta Degrees of Freedom. The divisor used in calculations
|
is ``N - ddof``, where ``N`` represents the number of elements.
|
zsample covarianceÚcovzDataFrame | Series | Nonez bool | None©ÚotherÚpairwiserO r< c s t j||||dS ©Nrb )r) ra ©r+ rc rd rO r< r, r. r/ ra « s $üz Expanding.covaN
|
other : Series or DataFrame, optional
|
If not supplied then will default to self and produce pairwise
|
output.
|
pairwise : bool, default None
|
If False then only matching columns between self and other will be
|
used and the output will be a DataFrame.
|
If True then all pairwise combinations will be calculated and the
|
output will be a MultiIndexed DataFrame in the case of DataFrame
|
inputs. In the case of missing elements, only complete pairwise
|
observations will be used.
|
z
|
cov : Similar method to calculate covariance.
|
numpy.corrcoef : NumPy Pearson's correlation calculation.
|
an
|
This function uses Pearson's definition of correlation
|
(https://en.wikipedia.org/wiki/Pearson_correlation_coefficient).
|
|
When `other` is not specified, the output will be self correlation (e.g.
|
all 1's), except for :class:`~pandas.DataFrame` inputs with `pairwise`
|
set to `True`.
|
|
Function will return ``NaN`` for correlations of equal valued sequences;
|
this is the result of a 0/0 division error.
|
|
When `pairwise` is set to `False`, only matching columns between `self` and
|
`other` will be used.
|
|
When `pairwise` is set to `True`, the output will be a MultiIndex DataFrame
|
with the original index on the first level, and the `other` DataFrame
|
columns on the second level.
|
|
In the case of missing elements, only complete pairwise observations
|
will be used.
|
Z correlationÚcorrc s t j||||dS re )r) rg rf r, r. r/ rg Ö s ?üzExpanding.corr)r! r r" N)F)FNNNN)FNN)FNN)FNN)FNN)FNN)r! FNN)r! FNN)r! F)F)F)rX F)r] TFF)NNr! F)NNr! F)'Ú__name__Ú
|
__module__Ú __qualname__Ú__doc__r Ú__annotations__r* r1 r r r r2 Zaggr r r r r9 r r? r r r rC rH rI rJ rK ÚreplacerM rR rS rU rV rW r\ ra rg Ú __classcell__r. r. r, r/ r , sB
|
F ú ÿÿã
|
ø
|
|
ö ù
|
ó ü
|
ó ü
|
ó ü
|
ó ü
|
ó ü ÿ úÿ ùÿ òÔ0 û ÿ úÿ ùÿ òÔ0 û ÿ úÿ õ à"óÿ ìÝ%ÿ ñ
|
æ ü ÿ ñÿ â Å? û ÿ ð
|
å û ÿ óÿ ûÿ êÊ: ûr c @ s* e Zd ZdZejej ZddddZdS )ÚExpandingGroupbyz5
|
Provide a expanding groupby implementation.
|
r r0 c C s t | jjtd}|S )z
|
Return an indexer class that will compute the window start and end bounds
|
|
Returns
|
-------
|
GroupbyIndexer
|
)Zgroupby_indicesÚwindow_indexer)r Ú_grouperÚindicesr )r+ rp r. r. r/ r1 $ s
|
þz$ExpandingGroupby._get_window_indexerN)rh ri rj rk r r r r1 r. r. r. r/ ro s ro N)&Ú
|
__future__r Útextwrapr Útypingr r r Zpandas._typingr r r Zpandasr
|
r Zpandas.core.genericr Zpandas.util._decoratorsr Z pandas.core.indexers.objectsr r r Zpandas.core.window.docr r r r r r r r r Zpandas.core.window.rollingr r r ro r. r. r. r/ Ú<module> s" , v
|
