B W0dP@sddlmZddlmZddlmZmZddlmZm Z m Z ddl m Z ddlmZddlmZmZmZmZmZmZmZmZmZmZddlmZmZmZdd lm Z m!Z!Gd d d e!Z"Gd d d e e"Z#dS)) annotations)dedent)AnyCallable)Axis FrameOrSeriesFrameOrSeriesUnion)function)doc) _shared_docs args_compatcreate_section_header kwargs_compat numba_notestemplate_headertemplate_returnstemplate_see_alsowindow_agg_numba_parameterswindow_apply_parameters) BaseIndexerExpandingIndexerGroupbyIndexer)BaseWindowGroupbyRollingAndExpandingMixincseZdZdZddddgZdd d d d dfdd ZddddZeede de ddddfddZ e Z ee e dee deddd d!d"d#fd$d%Zee e d&ee dee deddd d'd(d# dd*d+d,d-d.d/d0fd1d2 Zee e d&eeee dee dee d3eddd d4d4d#ddd5d,d-d5fd6d7Zee e d&eeee dee dee d3eddd d8d9d#ddd5d,d-d5fd:d;Zee e d&eeee dee dee d3eddd dd?Zee e d&eeee dee dee d3eddd d@d@d#ddd5d,d-d5fdAdBZee e d&eee dee dee d3eddd dCdCd# dd,d-d5fdDdE Zee e d&e dFdGddeee dee ddHee d3e dIdGdde dJe dKdGddd dLdMd#dd dNfdOdP Zee e d&e dFdGddeee dee ddQee d3e dRdGdde dJe dSdGddd dTdUd#dd dNfdVdW Zee e d&e dFdGddeee dee dee d3dXe dJe dYdGddd dZd[d#dd dNfd\d] Zee e d&ee dee dd^ee d3d_d d`dad# fdbdcZ ee e d&ee dee dddee d3dee dJe dfdGddd dgdhd#fdidjZ!ee e d&e dkdGddee dee deddd dldld# ddnd dofdpdq Z"ee e d&e drdGddee dee deddd dsdtd# ddudvd dwfdxdy Z#ee e d&e dzdGddee dee de d{dGddee d3e d|dGddd d}d~d#ddudvd dwfdd Z$Z%S) Expandinga Provide expanding transformations. Parameters ---------- min_periods : int, default 1 Minimum number of observations in window required to have a value (otherwise result is NA). center : bool, default False Set the labels at the center of the window. axis : int or str, default 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 ------- a Window sub-classed for the particular operation See Also -------- rolling : Provides rolling window calculations. ewm : Provides exponential weighted functions. Notes ----- By default, the result is set to the right edge of the window. This can be changed to the center of the window by setting ``center=True``. 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 >>> df.expanding(2).sum() B 0 NaN 1 1.0 2 3.0 3 3.0 4 7.0 min_periodscenteraxismethodNrsinglerintrstr)objrrrcstj||||||ddS)N)r#rrrr selection)super__init__)selfr#rrrrr$) __class__N/var/www/html/venv/lib/python3.7/site-packages/pandas/core/window/expanding.pyr&as zExpanding.__init__r)returncCstS)z[ Return an indexer class that will compute the window start and end bounds )r)r'r)r)r*_get_window_indexersszExpanding._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%r-)r'funcargskwargs)r(r)r*r-ys zExpanding.aggregateZReturnszSee AlsoZ expandingzcount of non NaN observationscount)Z window_methodZaggregation_descriptionZ agg_methodcs tS)N)r%r4)r')r(r)r*r4s zExpanding.countZ Parameterszcustom aggregation functionapplyFzCallable[..., Any]boolz str | Nonezdict[str, bool] | Noneztuple[Any, ...] | Nonezdict[str, Any] | None)r0rawengine engine_kwargsr1r2cstj||||||dS)N)r7r8r9r1r2)r%r5)r'r0r7r8r9r1r2)r(r)r*r5szExpanding.applyZNotessum)r8r9cs&td||tj|||d|S)Nr:)r8r9)nvvalidate_expanding_funcr%r:)r'r8r9r1r2)r(r)r*r:sz Expanding.summaximummaxcs&td||tj|||d|S)Nr>)r8r9)r;r<r%r>)r'r8r9r1r2)r(r)r*r>sz Expanding.maxminimummincs&td||tj|||d|S)Nr@)r8r9)r;r<r%r@)r'r8r9r1r2)r(r)r*r@sz Expanding.minmeancs&td||tj|||d|S)NrA)r8r9)r;r<r%rA)r'r8r9r1r2)r(r)r*rAszExpanding.meanmedianc stjf||d|S)N)r8r9)r%rB)r'r8r9r2)r(r)r*rB0szExpanding.medianz ddof : int, default 1 Delta Degrees of Freedom. The divisor used in calculations is ``N - ddof``, where ``N`` represents the number of elements.  z/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 deviationstd)ddofcs$td||tjfd|i|S)NrDrE)r;r<r%rD)r'rEr1r2)r(r)r*rDGs/z 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$td||tjfd|i|S)NrFrE)r;r<r%rF)r'rEr1r2)r(r)r*rFys/z Expanding.varz:A minimum of one period is required for the calculation. z >>> s = pd.Series([0, 1, 2, 3]) >>> s.expanding().sem() 0 NaN 1 0.707107 2 0.707107 3 0.745356 dtype: float64 zstandard error of meansemcstjfd|i|S)NrE)r%rG)r'rEr1r2)r(r)r*rGs$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|S)N)r%rH)r'r2)r(r)r*rHszExpanding.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|S)N)r%rI)r'r2)r(r)r*rIs&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. quantilelinearfloat)rJ interpolationc stjf||d|S)N)rJrM)r%rJ)r'rJrMr2)r(r)r*rJ s"zExpanding.quantilea 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 covariancecovzFrameOrSeriesUnion | Nonez bool | None)otherpairwiserEc stjf|||d|S)N)rOrPrE)r%rN)r'rOrPrEr2)r(r)r*rN3s$z Expanding.covaN other : Series or DataFrame, optional If not supplied then will default to self and produce pairwise output. pairwise : bool, default None If False then only matching columns between self and other will be used and the output will be a DataFrame. If True then all pairwise combinations will be calculated and the output will be a MultiIndexed DataFrame in the case of DataFrame inputs. In the case of missing elements, only complete pairwise observations will be used. z cov : Similar method to calculate covariance. numpy.corrcoef : NumPy Pearson's correlation calculation. an This function uses Pearson's definition of correlation (https://en.wikipedia.org/wiki/Pearson_correlation_coefficient). When `other` is not specified, the output will be self correlation (e.g. all 1's), except for :class:`~pandas.DataFrame` inputs with `pairwise` set to `True`. Function will return ``NaN`` for correlations of equal valued sequences; this is the result of a 0/0 division error. When `pairwise` is set to `False`, only matching columns between `self` and `other` will be used. When `pairwise` is set to `True`, the output will be a MultiIndex DataFrame with the original index on the first level, and the `other` DataFrame columns on the second level. In the case of missing elements, only complete pairwise observations will be used. Z correlationcorrc stjf|||d|S)N)rOrPrE)r%rQ)r'rOrPrEr2)r(r)r*rQYs?zExpanding.corr)rNrr N)FNNNN)NN)r)r)r)rK)NNr)NNr)&__name__ __module__ __qualname____doc__ _attributesr&r,r r rr-Zaggrr rrr4rr5r rrrr:r>r@rArBreplacerDrFrGrHrIrJrNrQ __classcell__r)r))r(r*r(s<5                 rc@s*eZdZdZejejZddddZdS)ExpandingGroupbyz5 Provide a expanding groupby implementation. r)r+cCst|jjtd}|S)z Return an indexer class that will compute the window start and end bounds Returns ------- GroupbyIndexer )Zgroupby_indiceswindow_indexer)r_grouperindicesr)r'rZr)r)r*r,sz$ExpandingGroupby._get_window_indexerN)rRrSrTrUrrVrr,r)r)r)r*rYs rYN)$ __future__rtextwraprtypingrrZpandas._typingrrrZpandas.compat.numpyr r;Zpandas.util._decoratorsr Zpandas.core.window.docr r r rrrrrrrZpandas.core.window.indexersrrrZpandas.core.window.rollingrrrrYr)r)r)r*s    0 w