U MZfE]@sddlmZddlmZddlmZmZmZddlm Z m Z m Z er`ddl m Z mZddlmZddlmZddlmZmZmZdd lmZmZmZmZmZmZmZmZm Z dd l!m"Z"m#Z#Gd d d e#Z$Gd dde"e$Z%dS)) annotations)dedent) TYPE_CHECKINGAnyCallable)AxisQuantileInterpolationWindowingRankType) DataFrameSeries)NDFrame)doc) BaseIndexerExpandingIndexerGroupbyIndexer) _shared_docscreate_section_headerkwargs_numeric_only numba_notestemplate_headertemplate_returnstemplate_see_alsowindow_agg_numba_parameterswindow_apply_parameters)BaseWindowGroupbyRollingAndExpandingMixincs\eZdZUdZdddgZded<dd d d dddfdd ZddddZee de de ddddfddZ e Z ee edeed ed d!d"d#d$d%dd'd(fd)d* Zee ed+eedeed ed d!d"d,d-d% dd.d'd/d0d1d2d3fd4d5 Zee ed+eeedeed eed6ed d!d"d7d7d% dd'd/d0d8fd9d: Zee ed+eeedeed eed6ed d!d"d;d Zee ed+eeedeed eed6ed d!d"d?d@d% dd'd/d0d8fdAdB Zee ed+eeedeed eed6ed d!d"dCdCd% dd'd/d0d8fdDdE Zee ed+eeedeed eed6ed d!d"dFdFd% dd'd/d0d8fdGdH Zee ed+e dIdJddeedKedeed dLeed6e dMdJddedNe dOdJddd"dPdQd%dd d'd/d0dRfdSdT Zee ed+e dIdJddeedKedeed dUeed6e dVdJddedNe dWdJddd"dXdYd%dd d'd/d0dRfdZd[ Zee ed+e dIdJddeedeed eed6d\edNe d]dJddd"d^d_d%dd d'd`fdadb Zee ed+eedeed dceed6ddd"dedfd% dd'd(fdgdh Z ee ed+eedeed dieed6djedNe dkdJddd"dldmd%dd'd(fdndo Z!ee ed+e dpdJddeedeed ed d!d"dqdqd% ddsdtd'dufdvdw Z"ee dxed+e dydJddeedeed eedNe dzdJddd"d{d{d%dd~d'd'd'dfdd Z#ee ed+e ddJddeedeed ed d!d"ddd% dddd d'dfdd Z$ee ed+e ddJddeedeed e ddJddeed6e ddJddd"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 ------- ``Expanding`` subclass 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] _attributesrsingleNr intrstrNone)objrrrreturncstj|||||ddS)N)r&rrr selection)super__init__)selfr&rrrr( __class__@/tmp/pip-unpacked-wheel-nbcvw55c/pandas/core/window/expanding.pyr*uszExpanding.__init__rr'cCstS)z[ Return an indexer class that will compute the window start and end bounds )r)r+r.r.r/_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_alsoZexamplesklassrcstj|f||S)N)r)r2)r+funcargskwargsr,r.r/r2s zExpanding.aggregateZReturnszSee AlsoZ expandingzcount of non NaN observationscount)Z window_methodZaggregation_descriptionZ agg_methodFbool numeric_onlycstj|dSNr;)r)r9r+r<r,r.r/r9s zExpanding.countZ Parameterszcustom aggregation functionapplyzCallable[..., Any]z str | Nonezdict[str, bool] | Noneztuple[Any, ...] | Nonezdict[str, Any] | None)r5rawengine engine_kwargsr6r7cstj||||||dS)N)r@rArBr6r7)r)r?)r+r5r@rArBr6r7r,r.r/r?szExpanding.applyZNotessumr<rArBcstj|||dSNrD)r)rCr+r<rArBr,r.r/rCs z Expanding.summaximummaxcstj|||dSrE)r)rHrFr,r.r/rHs z Expanding.maxZminimummincstj|||dSrE)r)rIrFr,r.r/rIs z Expanding.minmeancstj|||dSrE)r)rJrFr,r.r/rJ+s zExpanding.meanmediancstj|||dSrE)r)rKrFr,r.r/rKFs 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. 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 deviationstdddofr<rArBcstj||||dSNrN)r)rMr+rOr<rArBr,r.r/rMas 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||||dSrP)r)rRrQr,r.r/rRs 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 meansemrOr<cstj||dS)NrT)r)rS)r+rOr<r,r.r/rSs#z Expanding.semz:scipy.stats.skew : Third moment of a probability density. zDA minimum of three periods is required for the rolling calculation. zunbiased skewnessskewcstj|dSr=)r)rUr>r,r.r/rUszExpanding.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)rVr>r,r.r/rVs&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. quantilelinearfloatrrW interpolationr<cstj|||dS)NrZ)r)rW)r+rWr[r<r,r.r/rW8s "zExpanding.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 r ascendingpctr<cstj||||dS)Nr^)r)r\)r+rr_r`r<r,r.r/r\`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. zsample covariancecovzDataFrame | Series | Nonez bool | NoneotherpairwiserOr<cstj||||dSNrb)r)rar+rcrdrOr<r,r.r/ras $z Expanding.covaN other : Series or DataFrame, optional If not supplied then will default to self and produce pairwise output. pairwise : bool, default None If False then only matching columns between self and other will be used and the output will be a DataFrame. If True then all pairwise combinations will be calculated and the output will be a MultiIndexed DataFrame in the case of DataFrame inputs. In the case of missing elements, only complete pairwise observations will be used. z cov : Similar method to calculate covariance. numpy.corrcoef : NumPy Pearson's correlation calculation. an This function uses Pearson's definition of correlation (https://en.wikipedia.org/wiki/Pearson_correlation_coefficient). When `other` is not specified, the output will be self correlation (e.g. all 1's), except for :class:`~pandas.DataFrame` inputs with `pairwise` set to `True`. Function will return ``NaN`` for correlations of equal valued sequences; this is the result of a 0/0 division error. When `pairwise` is set to `False`, only matching columns between `self` and `other` will be used. When `pairwise` is set to `True`, the output will be a MultiIndex DataFrame with the original index on the first level, and the `other` DataFrame columns on the second level. In the case of missing elements, only complete pairwise observations will be used. Z correlationcorrcstj||||dSre)r)rgrfr,r.r/rgs ?zExpanding.corr)r!rr"N)F)FNNNN)FNN)FNN)FNN)FNN)FNN)r!FNN)r!FNN)r!F)F)F)rXF)r]TFF)NNr!F)NNr!F)'__name__ __module__ __qualname____doc__r __annotations__r*r1r rrr2Zaggrrrrr9rr?rrrrCrHrIrJrKreplacerMrRrSrUrVrWr\rarg __classcell__r.r.r,r/r,sB F              00  "%  ?  :rc@s*eZdZdZejejZddddZdS)ExpandingGroupbyz5 Provide a expanding groupby implementation. rr0cCst|jjtd}|S)z Return an indexer class that will compute the window start and end bounds Returns ------- GroupbyIndexer )Zgroupby_indiceswindow_indexer)r_grouperindicesr)r+rpr.r.r/r1$s z$ExpandingGroupby._get_window_indexerN)rhrirjrkrr rr1r.r.r.r/ros roN)& __future__rtextwraprtypingrrrZpandas._typingrrr Zpandasr r Zpandas.core.genericr Zpandas.util._decoratorsr Zpandas.core.indexers.objectsrrrZpandas.core.window.docrrrrrrrrrZpandas.core.window.rollingrrrror.r.r.r/s"    , v