E glddlmZddlmZddlmZmZmZmZddl m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZddlmZmZerddlmZmZm Z dd l!m"Z"m#Z#dd l$m%Z%Gd d eZ&Gd dee&Z'dS)) annotations)dedent) TYPE_CHECKINGAnyCallableLiteral)deprecate_kwargdoc) BaseIndexerExpandingIndexerGroupbyIndexer) _shared_docscreate_section_headerkwargs_numeric_only numba_notestemplate_headertemplate_returnstemplate_see_alsowindow_agg_numba_parameterswindow_apply_parameters)BaseWindowGroupbyRollingAndExpandingMixin)AxisQuantileInterpolationWindowingRankType) DataFrameSeries)NDFrameceZdZUdZgdZded< ddfd ZddZee de de dddfdZ e Z ee edeedeede d d!d"d#$ ddfd( Zee ed)eedeedeede d*d!d+d,$ ddfd8 Zee ed)eeedeedeed9eede d:d!d;d;$ ddfd< Zee ed)eeedeedeed9eede d=d!d>d?$ ddfd@ Zee ed)eeedeedeed9eede dAd!dBdC$ ddfdD Zee ed)eeedeedeed9eede dEd!dFdF$ ddfdG Zee ed)eeedeedeed9eede dHd!dIdI$ ddfdJ Zee ed)e dKdLddeedMedeeddNeed9e dOdLddede dPdLddd!dQdR$ ddfdT Zee ed)e dKdLddeedMedeeddUeed9e dVdLddede dWdLddd!dXdY$ ddfdZ Zee ed)e dKdLddeedeedeed9d[ede d\dLddd!d]d^$ddfd_ Zee ed)eedeedd`eed9daede dbd!dcdd$ddfde Z ee ed)eedeeddfeed9dgede dhdLddd!didj$ddfdk Z!ee ed)e dldLddeedeedeede dmd!dndn$ e"dndop ddfdu Z#ee dved)e dwdLddeedeedeede dxdLddd!dydy$ ddfd Z$ee ed)e ddLddeedeedeede dd!dd$ ddfd Z%ee ed)e ddLddeedeede ddLddeed9e dede dd!dd$ ddfd Z&xZ'S) 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] _attributesrsingleNobjrr!intr"rr#strreturnNonecTt|||||dS)N)r'r!r"r# selection)super__init__)selfr'r!r"r#r- __class__s Q/var/www/sysmax/venv/lib/python3.11/site-packages/pandas/core/window/expanding.pyr/zExpanding.__init__|s? #      r ctS)z[ Return an indexer class that will compute the window start and end bounds )r )r0s r2_get_window_indexerzExpanding._get_window_indexers !!!r3 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>tj|g|Ri|S)N)r.r6)r0funcargskwargsr1s r2r6zExpanding.aggregates-@!uww 7777777r3ReturnszSee 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_methodF numeric_onlyboolcHt|SN)rF)r.rBr0rFr1s r2rBzExpanding.counts.ww}},}777r3 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 functionapplyr<Callable[..., Any]rawengine!Literal['cython', 'numba'] | None engine_kwargsdict[str, bool] | Noner=tuple[Any, ...] | Noner>dict[str, Any] | NonecRt||||||S)N)rNrOrQr=r>)r.rL)r0r<rNrOrQr=r>r1s r2rLzExpanding.applys7Bww}} '    r3Notesz >>> 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 sumcLt|||SN)rFrOrQ)r.rWr0rFrOrQr1s r2rWz Expanding.sum.Bww{{%'   r3z >>> 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 maximummaxcLt|||SrY)r.r]rZs r2r]z Expanding.max r[r3z >>> 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 minimummincLt|||SrY)r.r`rZs r2r`z Expanding.minGr[r3z >>> 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 meancLt|||SrY)r.rbrZs r2rbzExpanding.meanns.Bww||%'   r3z >>> 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 mediancLt|||SrY)r.rdrZs r2rdzExpanding.medians.Bww~~%'   r3z 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 deviationstdddofcNt||||SN)rhrFrOrQ)r.rgr0rhrFrOrQr1s r2rgz Expanding.std1jww{{%'    r3z/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 variancevarcNt||||Srj)r.rnrks r2rnz Expanding.varrlr3z: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 meansemcJt||S)N)rhrF)r.rp)r0rhrFr1s r2rpz Expanding.sem4s Fww{{<{@@@r3z: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 skewnessskewcHt|SrI)r.rrrJs r2rrzExpanding.skewYs:ww|||666r3z/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 biaskurtcHt|SrI)r.rtrJs r2rtzExpanding.kurtxsLww|||666r3a 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_namelinearfloat interpolationrcLt|||S)N)rwr|rF)r.rv)r0rwr|rFr1s r2rvzExpanding.quantiles0hww'%    r3z.. 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 rankaverageTr ascendingpctcNt||||S)N)r#rrrF)r.r~)r0r#rrrFr1s r2r~zExpanding.ranks1Hww||%    r3a 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 covariancecovotherDataFrame | Series | Nonepairwise bool | NonecNt||||SN)rrrhrF)r.rr0rrrhrFr1s r2rz Expanding.cov%s1bww{{%    r3aN 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 correlationcorrcNt||||Sr)r.rrs r2rzExpanding.corr]s1Xww||%    r3)r%rr&N) r'rr!r(r"rr#r)r*r+)r*r )F)rFrG)FNNNN) r<rMrNrGrOrPrQrRr=rSr>rT)FNN)rFrGrOrPrQrR)r%FNN)rhr(rFrGrOrPrQrR)r%F)rhr(rFrG)rzF)rwr{r|rrFrG)rTFF)r#rrrGrrGrFrG)NNr%F)rrrrrhr(rFrG)(__name__ __module__ __qualname____doc__r$__annotations__r/r5r rrr6aggrrrrrBrrLrrrrWr]r`rbrdreplacergrnrprrrtr rvr~rr __classcell__)r1s@r2r r 3s<DDL?>>K>>>>         """"  S[!      $! ;>8888?>8 CSi((j))j))  " ?),888888-,8 Sl++i((j))j))  " =-64804'+(,      10 $ Sl++##%%i((j))g&&j))  " %3:#4804       76   Sl++##%%i((j))g&&j))  " )3:#4804       76   Sl++##%%i((j))g&&j))  " )3:#4804       76   Sl++##%%i((j))g&&j))  " &3:#4804       76   Sl++##%%i((j))g&&j))  " (3:#4804       76   Sl++   '$A  ##E**i((j)):g&&    '$A  j))    '$A  ! 4Y---`"4804       ]--\   Sl++   '$A  ##E**i((j)):g&&    '$A  j))    '$A  ! *Y---`"4804       ]--\   Sl++   '$A  i((j))g&&Fj))   '$A  ! 8A!!!DAAAAAAE!!DA Sl++i((j))Eg&&Qj))  " 358777777987 Sl++i((j)):g&&Hj))   ( '$A  ! NG$$$J777777K$$J7 Sl++   $ '$A  i((j))j))  " *W,,,Z_*3???08"       @?[,,\   S&l++    '$A  i((j))j))   < '$A  ! &w<<<~%."       {<<z   Sl++   '$A  i((j))j))  " 3Q)))X,0 $"       U))T   Sl++   '$A  i((j))   '$A  g&&   . j))  " -GDDDN,0 $"       KDDJ      r3r c8eZdZdZejejzZddZdS)ExpandingGroupbyz5 Provide a expanding groupby implementation. r*r cFt|jjt}|S)z Return an indexer class that will compute the window start and end bounds Returns ------- GroupbyIndexer )groupby_indiceswindow_indexer)r _grouperindicesr )r0rs r2r5z$ExpandingGroupby._get_window_indexers+( M1+   r3N)r*r )rrrrr r$rr5r3r2rrsE'*;*GGK      r3rN)( __future__rtextwraprtypingrrrrpandas.util._decoratorsr r pandas.core.indexers.objectsr r r pandas.core.window.docrrrrrrrrrpandas.core.window.rollingrrpandas._typingrrrpandasrrpandas.core.genericrr rrr3r2rs8""""""                         , ,+++++{  {  {  {  {  ({  {  {  |()r3