ehlddlmZddlmZddlmZmZmZmZddl m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZddlmZmZerddlmZmZm Z dd l!m"Z"m#Z#dd l$m%Z%Gd d eZ&Gd dee&Z'y)) annotations)dedent) TYPE_CHECKINGAnyCallableLiteral)deprecate_kwargdoc) BaseIndexerExpandingIndexerGroupbyIndexer) _shared_docscreate_section_headerkwargs_numeric_only numba_notestemplate_headertemplate_returnstemplate_see_alsowindow_agg_numba_parameterswindow_apply_parameters)BaseWindowGroupbyRollingAndExpandingMixin)AxisQuantileInterpolationWindowingRankType) DataFrameSeries)NDFramec eZdZUdZgdZded< df dgfd ZdhdZee de d e d d d fdZ e Z ee edeedeede dddd didjfd Zee edeedeedeede dddd dk dlfd Zee edeeedeedeedeede dddd dm dnfd Zee edeeedeedeedeede d!dd"d# dm dnfd$ Zee edeeedeedeedeede d%dd&d' dm dnfd( Zee edeeedeedeedeede d)dd*d* dm dnfd+ Zee edeeedeedeedeede d,dd-d- dm dnfd. Zee ede d/j9d0d deed1edeedd2eede d3j9d0d dede d4j9d0d ddd5d6 do dpfd7 Zee ede d/j9d0d deed1edeedd8eede d9j9d0d dede d:j9d0d ddd;d< do dpfd= Zee ede d/j9d0d deedeedeedd>ede d?j9d0d ddd@dAdqdrfdB Zee edeedeeddCeeddDede dEddFdGdidjfdH Z ee edeedeeddIeeddJede dKj9d0d dddLdMdidjfdN Z!ee ede dOj9d0d deedeedeede dPddQdQ e"dQdRS ds dtfdT Z#ee dUede dVj9d0d deedeedeede dWj9d0d dddXdX du dvfdY Z$ee ede dZj9d0d deedeedeede d[dd\d] dw dxfd^ Z%ee ede d_j9d0d deedeede d`j9d0d deede daede dbddcdd dw dxfde Z&xZ'S)y Expandinga 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 ------- pandas.api.typing.Expanding See Also -------- rolling : Provides rolling window calculations. ewm : Provides exponential weighted functions. Notes ----- See :ref:`Windowing Operations ` 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 ) min_periodsaxismethodz list[str] _attributesc.t||||||y)N)objr!r"r# selection)super__init__)selfr'r!r"r#r( __class__s Z/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/pandas/core/window/expanding.pyr*zExpanding.__init__|s& #  ctS)z[ Return an indexer class that will compute the window start and end bounds )r )r+s r-_get_window_indexerzExpanding._get_window_indexers  !!r. 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/Dataframe)see_alsoexamplesklassr"c*t||g|i|S)N)r)r1)r+funcargskwargsr,s r-r1zExpanding.aggregates @w 7777r.ReturnszSee AlsoExamplesz >>> ser = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd']) >>> ser.expanding().count() a 1.0 b 2.0 c 3.0 d 4.0 dtype: float64 expandingzcount of non NaN observationscount) window_methodaggregation_description agg_methodc$t||SN) numeric_only)r)r=r+rCr,s r-r=zExpanding.counts.w},}77r. Parametersz >>> ser = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd']) >>> ser.expanding().apply(lambda s: s.max() - 2 * s.min()) a -1.0 b 0.0 c 1.0 d 2.0 dtype: float64 zcustom aggregation functionapplyc.t|||||||S)N)rawengine engine_kwargsr8r9)r)rF)r+r7rHrIrJr8r9r,s r-rFzExpanding.applys.Bw} '   r.Notesz >>> ser = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd']) >>> ser.expanding().sum() a 1.0 b 3.0 c 6.0 d 10.0 dtype: float64 sumc(t||||SN)rCrIrJ)r)rLr+rCrIrJr,s r-rLz Expanding.sum%Bw{%'  r.z >>> ser = pd.Series([3, 2, 1, 4], index=['a', 'b', 'c', 'd']) >>> ser.expanding().max() a 3.0 b 3.0 c 3.0 d 4.0 dtype: float64 maximummaxc(t||||SrN)r)rRrOs r-rRz Expanding.max rPr.z >>> ser = pd.Series([2, 3, 4, 1], index=['a', 'b', 'c', 'd']) >>> ser.expanding().min() a 2.0 b 2.0 c 2.0 d 1.0 dtype: float64 minimumminc(t||||SrN)r)rUrOs r-rUz Expanding.minGrPr.z >>> ser = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd']) >>> ser.expanding().mean() a 1.0 b 1.5 c 2.0 d 2.5 dtype: float64 meanc(t||||SrN)r)rWrOs r-rWzExpanding.meanns%Bw|%'  r.z >>> ser = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd']) >>> ser.expanding().median() a 1.0 b 1.5 c 2.0 d 2.5 dtype: float64 medianc(t||||SrN)r)rYrOs r-rYzExpanding.medians%Bw~%'  r.z ddof : int, default 1 Delta Degrees of Freedom. The divisor used in calculations is ``N - ddof``, where ``N`` represents the number of elements.  z1.4z/numpy.std : Equivalent method for NumPy array. z 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. a  >>> 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 deviationstdc*t|||||SN)ddofrCrIrJ)r)r\r+r_rCrIrJr,s r-r\z Expanding.std(jw{%'   r.z/numpy.var : Equivalent method for NumPy array. z 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 variancevarc*t|||||Sr^)r)rcr`s r-rcz Expanding.varrar.z:A minimum of one period is required for the calculation. z >>> 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 meansemc&t|||S)N)r_rC)r)re)r+r_rCr,s r-rez Expanding.sem4sFw{<{@@r.z:scipy.stats.skew : Third moment of a probability density. zEA minimum of three periods is required for the rolling calculation. a >>> ser = pd.Series([-1, 0, 2, -1, 2], index=['a', 'b', 'c', 'd', 'e']) >>> ser.expanding().skew() a NaN b NaN c 0.935220 d 1.414214 e 0.315356 dtype: float64 zunbiased skewnessskewc$t||SrB)r)rgrDs r-rgzExpanding.skewYs:w||66r.z/scipy.stats.kurtosis : Reference SciPy method. z>> arr = [1, 2, 3, 4, 999] >>> import scipy.stats >>> print(f"{{scipy.stats.kurtosis(arr[:-1], bias=False):.6f}}") -1.200000 >>> print(f"{{scipy.stats.kurtosis(arr, bias=False):.6f}}") 4.999874 >>> s = pd.Series(arr) >>> s.expanding(4).kurt() 0 NaN 1 NaN 2 NaN 3 -1.200000 4 4.999874 dtype: float64 z,Fisher's definition of kurtosis without biaskurtc$t||SrB)r)rirDs r-rizExpanding.kurtxsLw||66r.a quantile : float Quantile to compute. 0 <= quantile <= 1. .. deprecated:: 2.1.0 This will be renamed to 'q' in a future version. 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. a >>> ser = pd.Series([1, 2, 3, 4, 5, 6], index=['a', 'b', 'c', 'd', 'e', 'f']) >>> ser.expanding(min_periods=4).quantile(.25) a NaN b NaN c NaN d 1.75 e 2.00 f 2.25 dtype: float64 quantileq) old_arg_name new_arg_namec(t||||S)N)rl interpolationrC)r)rk)r+rlrprCr,s r-rkzExpanding.quantiles&hw'%   r.z.. 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 rankc*t|||||S)N)r# ascendingpctrC)r)rq)r+r#rsrtrCr,s r-rqzExpanding.ranks(Hw|%   r.a 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. a0 >>> ser1 = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd']) >>> ser2 = pd.Series([10, 11, 13, 16], index=['a', 'b', 'c', 'd']) >>> ser1.expanding().cov(ser2) a NaN b 0.500000 c 1.500000 d 3.333333 dtype: float64 zsample covariancecovc*t|||||SN)otherpairwiser_rC)r)rur+rxryr_rCr,s r-ruz Expanding.cov%s(bw{%   r.aN 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. ao 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. a1 >>> ser1 = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd']) >>> ser2 = pd.Series([10, 11, 13, 16], index=['a', 'b', 'c', 'd']) >>> ser1.expanding().corr(ser2) a NaN b 1.000000 c 0.981981 d 0.975900 dtype: float64 correlationcorrc*t|||||Srw)r)r|rzs r-r|zExpanding.corr]s(Xw|%   r.)r%rsingleN) r'rr!intr"rr#strreturnNone)rr )F)rCbool)FNNNN) r7zCallable[..., Any]rHrrI!Literal['cython', 'numba'] | NonerJdict[str, bool] | Noner8ztuple[Any, ...] | Noner9zdict[str, Any] | None)FNN)rCrrIrrJr)r%FNN)r_rrCrrIrrJr)r%F)r_rrCr)linearF)rlfloatrprrCr)averageTFF)r#rrsrrtrrCr)NNr%F)rxzDataFrame | Series | Noneryz bool | Noner_rrCr)(__name__ __module__ __qualname____doc__r$__annotations__r*r0r rrr1aggrrrrr=rrFrrrrLrRrUrWrYreplacer\rcrergrir rkrqrur| __classcell__)r,s@r-r r 3s DL?K>           "  [!    $! ;>8?>8 Ci(j)j)  " ?),8-,8 l+i(j)j)  " =-64804'+(,    2  .  %  & 10 $ l+#%i(j)g&j)  " %3:#4804    2  .  76   l+#%i(j)g&j)  " )3:#4804    2  .  76   l+#%i(j)g&j)  " )3:#4804    2  .  76   l+#%i(j)g&j)  " &3:#4804    2  .  76   l+#%i(j)g&j)  " (3:#4804    2  .  76   l+  '$A #E*i(j):g&   '$A j)   '$A ! 4Y-`"4804      2  .  ]-\   l+  '$A #E*i(j):g&   '$A j)   '$A ! *Y-`"4804      2  .  ]-\   l+  '$A i(j)g&Fj)   '$A ! 8A!DAE!DA l+i(j)Eg&Qj)  " 3587987 l+i(j):g&Hj)  ( '$A ! NG$J7K$J7 l+  $ '$A i(j)j)  " *W,Z*3?08"    -    @[,\   &l+   '$A i(j)j)  < '$A ! &w<~%."  !        {<z   l+  '$A i(j)j)  " 3Q)X,0 $"  (        U)T   l+   '$A i(j)  '$A g&  . j)  " -GDN,0 $"  (        KDJ  r.r cJeZdZdZej ej zZddZy)ExpandingGroupbyz5 Provide a expanding groupby implementation. cPt|jjt}|S)z Return an indexer class that will compute the window start and end bounds Returns ------- GroupbyIndexer )groupby_indiceswindow_indexer)r _grouperindicesr )r+rs r-r0z$ExpandingGroupby._get_window_indexers&( MM11+ r.N)rr )rrrrr r$rr0r.r-rrs%''*;*G*GGK r.rN)( __future__rtextwraprtypingrrrrpandas.util._decoratorsr r pandas.core.indexers.objectsr r r pandas.core.window.docrrrrrrrrrpandas.core.window.rollingrrpandas._typingrrrpandasrrpandas.core.genericrr rrr.r-rsp"      ,{  ({  |()r.