a Ofl@sddlmZddlmZddlmZmZmZmZddl m Z m Z ddl m Z mZmZddlmZmZmZmZmZmZmZmZmZddlmZmZerddlmZmZm Z dd l!m"Z"m#Z#dd l$m%Z%Gd d d eZ&Gd ddee&Z'dS)) annotations)dedent) TYPE_CHECKINGAnyCallableLiteral)deprecate_kwargdoc) BaseIndexerExpandingIndexerGroupbyIndexer) _shared_docscreate_section_headerkwargs_numeric_only numba_notestemplate_headertemplate_returnstemplate_see_alsowindow_agg_numba_parameterswindow_apply_parameters)BaseWindowGroupbyRollingAndExpandingMixin)AxisQuantileInterpolationWindowingRankType) DataFrameSeries)NDFramecseZdZUdZgdZded<dd d d d d dfdd ZddddZee de de ddddfddZ e Z ee edeedeede d d!d"d#d$ dd&d'fd(d) Zee ed*eedeedeede d+d!d,d-d$ dd.d&d/d0d1d2d3fd4d5 Zee ed*eeedeedeed6eede d7d!d8d8d$dd&d/d0d9fd:d; Zee ed*eeedeedeed6eede d<d!d=d>d$dd&d/d0d9fd?d@ Zee ed*eeedeedeed6eede dAd!dBdCd$dd&d/d0d9fdDdE Zee ed*eeedeedeed6eede dFd!dGdGd$dd&d/d0d9fdHdI Zee ed*eeedeedeed6eede dJd!dKdKd$dd&d/d0d9fdLdM Zee ed*e dNdOddeedPedeeddQeed6e dRdOddede dSdOddd!dTdUd$dd d&d/d0dVfdWdX Zee ed*e dNdOddeedPedeeddYeed6e dZdOddede d[dOddd!d\d]d$dd d&d/d0dVfd^d_ Zee ed*e dNdOddeedeedeed6d`ede dadOddd!dbdcd$dd d&ddfdedf Zee ed*eedeeddgeed6dhede did!djdkd$dd&d'fdldm Z ee ed*eedeeddneed6doede dpdOddd!dqdrd$dd&d'fdsdt Z!ee ed*e dudOddeedeedeede dvd!dwdwd$ e"dwdxdydd{d|d&d}fd~d Z#ee ded*e ddOddeedeedeede ddOddd!ddd$ddd&d&d&dfdd Z$ee ed*e ddOddeedeedeede dd!ddd$ dddd d&dfdd Z%ee ed*e ddOddeedeede ddOddeed6e dede dd!ddd$dddd d&dfdd 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] _attributesrsingleNrintrstrNone)objrr r!returncstj|||||ddS)N)r(rr r! selection)super__init__)selfr(rr r!r* __class__U/var/www/ai-form-bot/venv/lib/python3.9/site-packages/pandas/core/window/expanding.pyr,|szExpanding.__init__r 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)Zsee_alsoZexamplesklassr cstj|g|Ri|S)N)r+r4)r-funcargskwargsr.r0r1r4s zExpanding.aggregateZReturnszSee AlsoZExamplesz >>> 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 Z expandingzcount of non NaN observationscount)Z window_methodZaggregation_descriptionZ agg_methodFbool numeric_onlycstj|dSNr<)r+r:r-r=r.r0r1r:szExpanding.countZ 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 functionapplyzCallable[..., Any]z!Literal['cython', 'numba'] | Nonezdict[str, bool] | Noneztuple[Any, ...] | Nonezdict[str, Any] | None)r7rawengine engine_kwargsr8r9cstj||||||dS)N)rArBrCr8r9)r+r@)r-r7rArBrCr8r9r.r0r1r@s!zExpanding.applyZNotesz >>> 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 sumr=rBrCcstj|||dSNrE)r+rDr-r=rBrCr.r0r1rDs !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 maximummaxcstj|||dSrF)r+rIrGr.r0r1rI s !z 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 minimummincstj|||dSrF)r+rKrGr.r0r1rKGs !z 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 meancstj|||dSrF)r+rLrGr.r0r1rLns !zExpanding.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 mediancstj|||dSrF)r+rMrGr.r0r1rMs !zExpanding.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 deviationstdddofr=rBrCcstj||||dSNrP)r+rOr-rQr=rBrCr.r0r1rOs 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 Zvariancevarcstj||||dSrR)r+rTrSr.r0r1rTs 5z 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 meansemrQr=cstj||dS)NrV)r+rU)r-rQr=r.r0r1rU4s#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 skewnessskewcstj|dSr>)r+rWr?r.r0r1rWYszExpanding.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 biaskurtcstj|dSr>)r+rXr?r.r0r1rXxs&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)Z old_arg_nameZ new_arg_namelinearfloatrrZ interpolationr=cstj|||dS)Nr])r+rY)r-rZr^r=r.r0r1rYs 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 rankaverageTrr! ascendingpctr=cstj||||dS)Nra)r+r_)r-r!rbrcr=r.r0r1r_s 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 covariancecovzDataFrame | Series | Nonez bool | NoneotherpairwiserQr=cstj||||dSNre)r+rdr-rfrgrQr=r.r0r1rd%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 Z correlationcorrcstj||||dSrh)r+rjrir.r0r1rj]s LzExpanding.corr)r#rr$N)F)FNNNN)FNN)FNN)FNN)FNN)FNN)r#FNN)r#FNN)r#F)F)F)r[F)r`TFF)NNr#F)NNr#F)(__name__ __module__ __qualname____doc__r"__annotations__r,r3r r rr4Zaggrrrrr:rr@rrrrDrIrKrLrMreplacerOrTrUrWrXrrYr_rdrj __classcell__r0r0r.r1r3sX F             00  " % -  ? ,  Grc@s*eZdZdZejejZddddZdS)ExpandingGroupbyz5 Provide a expanding groupby implementation. r r2cCst|jjtd}|S)z Return an indexer class that will compute the window start and end bounds Returns ------- GroupbyIndexer )Zgroupby_indiceswindow_indexer)r _grouperindicesr )r-rsr0r0r1r3s z$ExpandingGroupby._get_window_indexerN)rkrlrmrnrr"rr3r0r0r0r1rrs rrN)( __future__rtextwraprtypingrrrrZpandas.util._decoratorsrr Zpandas.core.indexers.objectsr r r Zpandas.core.window.docr rrrrrrrrZpandas.core.window.rollingrrZpandas._typingrrrZpandasrrZpandas.core.genericrrrrr0r0r0r1s&  ,