U +if`\@sddlmZddlmZddlmZmZmZddlm Z m Z er\ddl m Z m Z ddlmZddlmZddlmZdd lmZmZmZdd lmZmZmZmZmZmZm Z m!Z!m"Z"m#Z#dd l$m%Z%m&Z&Gd d d e&Z'Gddde%e'Z(dS)) annotations)dedent) TYPE_CHECKINGAnyCallable)AxisWindowingRankType) DataFrameSeries)NDFrame)function)doc) BaseIndexerExpandingIndexerGroupbyIndexer) _shared_docs args_compatcreate_section_header kwargs_compat numba_notestemplate_headertemplate_returnstemplate_see_alsowindow_agg_numba_parameterswindow_apply_parameters)BaseWindowGroupbyRollingAndExpandingMixincsbeZdZUdZddddgZded<dd d dddfdd ZddddZee de de ddddfddZ e Z ee edeed ed d!d"d#d$d%fd&d'Zee ed(eedeed ed d!d"d)d*d% dd,d-d.d/d0d1d2fd3d4 Zee ed(eeeedeed eed5ed d!d"d6d6d%d d d7d.d/d7fd8d9Zee ed(eeeedeed eed5ed d!d"d:d;d%d d d7d.d/d7fdd?d%d d d7d.d/d7fd@dAZee ed(eeeedeed eed5ed d!d"dBdBd%d d d7d.d/d7fdCdDZee ed(eeedeed eed5ed d!d"dEdEd% dd.d/d7fdFdG Zee ed(e dHdIddeedJeedeed dKeed5e dLdIddedMe dNdIddd"dOdPd%dd d d7d d.d/dQfdRdSZee ed(e dHdIddeedJeedeed dTeed5e dUdIddedMe dVdIddd"dWdXd%dd d d7d d.d/dQfdYdZZee ed(e dHdIddeeedeed eed5d[edMe d\dIddd"d]d^d%dd d_fd`da Z ee ed(eedeed dbeed5dcd"ddded% fdfdgZ!ee ed(eedeed dheed5diedMe djdIddd"dkdld%fdmdnZ"ee ed(e dodIddeedeed ed d!d"dpdpd% ddrddsfdtdu Z#ee dved(e dwdIddeedeed eedMe dxdIddd"dydyd%dd|d-d-d}fd~d Z$ee ed(e ddIddeedeed ed d!d"ddd% dddd dfdd Z%ee ed(e ddIddeedeed e ddIddeed5e ddIddd"ddd%dddd 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``. center : bool, default False If False, set the window labels as the right edge of the window index. If True, set the window labels as the center of the window index. .. deprecated:: 1.1.0 axis : int or str, default 0 If ``0`` or ``'index'``, roll across the rows. If ``1`` or ``'columns'``, roll across the columns. 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_periodscenteraxismethodz list[str] _attributesNrsingler intrstr)objrr r!cstj||||||ddS)N)r'rrr r! selection)super__init__)selfr'rrr r!r( __class__O/home/mars/bis/venv/lib/python3.8/site-packages/pandas/core/window/expanding.pyr*{s zExpanding.__init__rreturncCstS)z[ Return an indexer class that will compute the window start and end bounds )rr+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_alsoZexamplesklassr cstj|f||SN)r)r4)r+funcargskwargsr,r.r/r4s zExpanding.aggregateZReturnszSee AlsoZ expandingzcount of non NaN observationscount)Z window_methodZaggregation_descriptionZ agg_methodcs tSr7)r)r<r2r,r.r/r<s zExpanding.countZ Parameterszcustom aggregation functionapplyFzCallable[..., Any]boolz str | Nonezdict[str, bool] | Noneztuple[Any, ...] | Nonezdict[str, Any] | None)r8rawengine engine_kwargsr9r:cstj||||||dS)N)r?r@rAr9r:)r)r=)r+r8r?r@rAr9r:r,r.r/r=szExpanding.applyZNotessumr@rAcs&td||tj|||d|S)NrBrC)nvvalidate_expanding_funcr)rBr+r@rAr9r:r,r.r/rBsz Expanding.summaximummaxcs&td||tj|||d|S)NrHrC)rDrEr)rHrFr,r.r/rHsz Expanding.maxminimummincs&td||tj|||d|S)NrJrC)rDrEr)rJrFr,r.r/rJsz Expanding.minmeancs&td||tj|||d|S)NrKrC)rDrEr)rKrFr,r.r/rK0szExpanding.meanmedianc stjf||d|S)NrC)r)rL)r+r@rAr:r,r.r/rLJszExpanding.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@rAcs(td||tjf|||d|S)NrNrO)rDrEr)rNr+rPr@rAr9r:r,r.r/rNas7z 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 Zvariancevarcs(td||tjf|||d|S)NrRrO)rDrEr)rRrQr,r.r/rRs7z 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 meansem)rPcstjfd|i|S)NrP)r)rS)r+rPr9r: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 skewnessskewc stjf|Sr7)r)rTr+r:r,r.r/rTszExpanding.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 biaskurtc stjf|Sr7)r)rVrUr,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. quantilelinearfloatrW interpolationc stjf||d|S)NrZ)r)rW)r+rWr[r:r,r.r/rW9s "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 rankaverageTrr! ascendingpctc stjf|||d|S)Nr^)r)r\)r+r!r_r`r:r,r.r/r\asDzExpanding.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 | NoneotherpairwiserPc stjf|||d|SNrb)r)rar+rcrdrPr:r,r.r/ras$z Expanding.covaN other : Series or DataFrame, optional If not supplied then will default to self and produce pairwise output. pairwise : bool, default None If False then only matching columns between self and other will be used and the output will be a DataFrame. If True then all pairwise combinations will be calculated and the output will be a MultiIndexed DataFrame in the case of DataFrame inputs. In the case of missing elements, only complete pairwise observations will be used. z cov : Similar method to calculate covariance. numpy.corrcoef : NumPy Pearson's correlation calculation. an This function uses Pearson's definition of correlation (https://en.wikipedia.org/wiki/Pearson_correlation_coefficient). When `other` is not specified, the output will be self correlation (e.g. all 1's), except for :class:`~pandas.DataFrame` inputs with `pairwise` set to `True`. Function will return ``NaN`` for correlations of equal valued sequences; this is the result of a 0/0 division error. When `pairwise` is set to `False`, only matching columns between `self` and `other` will be used. When `pairwise` is set to `True`, the output will be a MultiIndex DataFrame with the original index on the first level, and the `other` DataFrame columns on the second level. In the case of missing elements, only complete pairwise observations will be used. Z correlationcorrc stjf|||d|Sre)r)rgrfr,r.r/rgs?zExpanding.corr)r#Nrr$N)FNNNN)NN)r#)r#)r#)rX)r]TF)NNr#)NNr#)(__name__ __module__ __qualname____doc__r"__annotations__r*r3r rrr4Zaggrrrrr<rr=rrrrrBrHrJrKrLreplacerNrRrSrTrVrWr\rarg __classcell__r.r.r,r/r-s@ K             1 1   #%  ?   :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/r3s z$ExpandingGroupby._get_window_indexerN)rhrirjrkrr"rr3r.r.r.r/ros roN)) __future__rtextwraprtypingrrrZpandas._typingrrZpandasr r Zpandas.core.genericr Zpandas.compat.numpyr rDZpandas.util._decoratorsr Zpandas.core.indexers.objectsrrrZpandas.core.window.docrrrrrrrrrrZpandas.core.window.rollingrrrror.r.r.r/s$     0 l