o hl@sddlmZddlmZddlmZmZmZmZddl m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZddlmZmZerbddlmZmZm Z dd l!m"Z"m#Z#dd l$m%Z%Gd d d eZ&Gd ddee&Z'dS)) annotations)dedent) TYPE_CHECKINGAnyCallableLiteral)deprecate_kwargdoc) BaseIndexerExpandingIndexerGroupbyIndexer) _shared_docscreate_section_headerkwargs_numeric_only numba_notestemplate_headertemplate_returnstemplate_see_alsowindow_agg_numba_parameterswindow_apply_parameters)BaseWindowGroupbyRollingAndExpandingMixin)AxisQuantileInterpolationWindowingRankType) DataFrameSeries)NDFramecsbeZdZUdZgdZded<    ddfdd ZdddZee de de ddddfddZ e Z ee ed eed!eed"e d#d$d%d&d' ddfd+d, Zee ed-eed eed!eed"e d.d$d/d0d' (    ddfdeed"e d?d$d@d@d' (  ddfdAdB Zee ed-eeed eed!eed>eed"e dCd$dDdEd' (  ddfdFdG Zee ed-eeed eed!eed>eed"e dHd$dIdJd' (  ddfdKdL Zee ed-eeed eed!eed>eed"e dMd$dNdNd' (  ddfdOdP Zee ed-eeed eed!eed>eed"e dQd$dRdRd' (  ddfdSdT Zee ed-e dUdVddeedWed eed!dXeed>e dYdVdded"e dZdVddd$d[d\d'  (  ddfd^d_ Zee ed-e dUdVddeedWed eed!d`eed>e dadVdded"e dbdVddd$dcddd'  (  ddfdedf Zee ed-e dUdVddeed eed!eed>dged"e dhdVddd$didjd'ddfdkdl Zee ed-eed eed!dmeed>dned"e dod$dpdqd'ddfdrds Z ee ed-eed eed!dteed>dued"e dvdVddd$dwdxd'ddfdydz Z!ee ed-e d{dVddeed eed!eed"e d|d$d}d}d' e"d}d~d (ddfdd Z#ee ded-e ddVddeed eed!eed"e ddVddd$ddd' ( (ddfdd Z$ee ed-e ddVddeed eed!eed"e dd$ddd'    (ddfdd Z%ee ed-e ddVddeed eed!e ddVddeed>e ded"e dd$ddd'    (ddfdd Z&Z'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] _attributesrsingleNobjrrintr rr!strreturnNonecstj|||||ddS)N)r%rr r! selection)super__init__)selfr%rr r!r* __class__N/var/www/html/env/lib/python3.10/site-packages/pandas/core/window/expanding.pyr,|s zExpanding.__init__r cCstS)z[ Return an indexer class that will compute the window start and end bounds )r )r-r0r0r1_get_window_indexerszExpanding._get_window_indexer 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 cstj|g|Ri|S)N)r+r3)r-funcargskwargsr.r0r1r3s zExpanding.aggregateReturnszSee 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_onlyboolctj|dSN)rB)r+r>r-rBr.r0r1r>szExpanding.count 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 functionapplyr8Callable[..., Any]rawengine!Literal['cython', 'numba'] | None engine_kwargsdict[str, bool] | Noner9tuple[Any, ...] | Noner:dict[str, Any] | Nonecstj||||||dS)N)rJrKrMr9r:)r+rH)r-r8rJrKrMr9r:r.r0r1rHs!zExpanding.applyNotesz >>> 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 sumctj|||dSN)rBrKrM)r+rRr-rBrKrMr.r0r1rR !z Expanding.sumz >>> 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 maximummaxcrSrT)r+rXrUr.r0r1rX rVz Expanding.maxz >>> 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 minimummincrSrT)r+rZrUr.r0r1rZGrVz Expanding.minz >>> 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 meancrSrT)r+r[rUr.r0r1r[nrVzExpanding.meanz >>> 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 mediancrSrT)r+r\rUr.r0r1r\rVzExpanding.medianz 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 deviationstdddofctj||||dSN)r_rBrKrM)r+r^r-r_rBrKrMr.r0r1r^ 5z Expanding.stdz/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 variancevarcr`ra)r+rerbr.r0r1rercz Expanding.varz: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 meansemcstj||dS)N)r_rB)r+rf)r-r_rBr.r0r1rf4s#z Expanding.semz: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 skewnessskewcrDrE)r+rgrFr.r0r1rgYszExpanding.skewz/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 biaskurtcrDrE)r+rhrFr.r0r1rhxs&zExpanding.kurta 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 interpolationrcrS)N)rjrorB)r+ri)r-rjrorBr.r0r1ris 4zExpanding.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 rankaverageTr ascendingpctcr`)N)r!rrrsrB)r+rp)r-r!rrrsrBr.r0r1rps DzExpanding.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. 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 | Nonecr`N)rurwr_rB)r+rtr-rurwr_rBr.r0r1rt%s 1z 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. 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 correlationcorrcr`ry)r+r|rzr.r0r1r|]s LzExpanding.corr)r#rr$N) r%rrr&r rr!r'r(r))r(r )F)rBrC)FNNNN) r8rIrJrCrKrLrMrNr9rOr:rP)FNN)rBrCrKrLrMrN)r#FNN)r_r&rBrCrKrLrMrN)r#F)r_r&rBrC)rmF)rjrnrorrBrC)rqTFF)r!rrrrCrsrCrBrC)NNr#F)rurvrwrxr_r&rBrC)(__name__ __module__ __qualname____doc__r"__annotations__r,r2r r rr3aggrrrrr>rrHrrrrRrXrZr[r\replacer^rerfrgrhrrirprtr| __classcell__r0r0r.r1r3s< F                0   0  "  %   -   ?  ,   Grc@s&eZdZdZejejZdddZdS)ExpandingGroupbyz5 Provide a expanding groupby implementation. r(r cCst|jjtd}|S)z Return an indexer class that will compute the window start and end bounds Returns ------- GroupbyIndexer )groupby_indiceswindow_indexer)r _grouperindicesr )r-rr0r0r1r2s z$ExpandingGroupby._get_window_indexerN)r(r )r}r~rrrr"rr2r0r0r0r1rs rN)( __future__rtextwraprtypingrrrrpandas.util._decoratorsrr pandas.core.indexers.objectsr r r pandas.core.window.docr rrrrrrrrpandas.core.window.rollingrrpandas._typingrrrpandasrrpandas.core.genericrrrr0r0r0r1s( ,