B ZQ"@sdZddlmZmZmZddlZddlmZ ddl m Z m Z ddl mZddlmZd d Zd d Zd:ddZGdddeZedkreddddddddddddd d!d"d#d$d%d&d'd(d)d*d+d,d-d.d/d0d1d2d3g Zeed4d5Zdd6lmZmZeeed7eed8d9ZeeZdS);z+ Seasonal Decomposition by Moving Averages )lmaprange iteritemsN)nanmean)_maybe_get_pandas_wrapper_freq_maybe_get_pandas_wrapper)convolution_filter)freq_to_periodcstfddtDS)z Return means for each period in x. freq is an int that gives the number of periods per cycle. E.g., 12 for monthly. NaNs are ignored in the mean. cs"g|]}t|dddqS)Nr)axis) pd_nanmean).0i)freqx7lib/python3.7/site-packages/statsmodels/tsa/seasonal.py sz!seasonal_mean..)nparrayr)rrr)rrr seasonal_mean src Csptddt|D}|jddtddt|dddD}t|||}t|||}tjjtjt ||t ||f|||ddd\}}t d|tj|tj|j }|j dkr| }||d|<tjjtjt ||t ||f|||ddd\}}t |d|jdtj|tj|j }|j dkr\| }|||dd<|S) z Replace nan values on trend's end-points with least-squares extrapolated values with regression considering npoints closest defined points. css&|]\}}tt|s|VqdS)N)ranyisnan)r rvalsrrr sz%_extrapolate_trend..rrcss&|]\}}tt|s|VqdS)N)rrr)r rrrrrrsN)Zrcond)next enumerateshapeminmaxrZlinalgZlstsqZc_ZarangeZonesTndimsqueeze) trendZnpointsfrontZbackZ front_lastZ back_firstknZextrarrr_extrapolate_trends&."  , r(additiveTcCs|dkrt|\}}n t|}d}t|}t|}tt|sPtd| drpt |dkrptd|dkr|dk rt |}|}ntd|dkr|ddkrt dgd g|d dg|}nt d ||}t|d } t||| } |d kr |d }|dkr"t| |d } | dr8|| } n|| } t| |} | drj| tj| dd } n| tj| dd 8} t| j||d jd|} | dr|| | }n| | }t|| | ||g}t|d|d |d|d dS)a Seasonal decomposition using moving averages Parameters ---------- x : array-like Time series. If 2d, individual series are in columns. model : str {"additive", "multiplicative"} Type of seasonal component. Abbreviations are accepted. filt : array-like The filter coefficients for filtering out the seasonal component. The concrete moving average method used in filtering is determined by two_sided. freq : int, optional Frequency of the series. Must be used if x is not a pandas object. Overrides default periodicity of x if x is a pandas object with a timeseries index. two_sided : bool The moving average method used in filtering. If True (default), a centered moving average is computed using the filt. If False, the filter coefficients are for past values only. extrapolate_trend : int or 'freq', optional If set to > 0, the trend resulting from the convolution is linear least-squares extrapolated on both ends (or the single one if two_sided is False) considering this many (+1) closest points. If set to 'freq', use `freq` closest points. Setting this parameter results in no NaN values in trend or resid components. Returns ------- results : obj A object with seasonal, trend, and resid attributes. Notes ----- This is a naive decomposition. More sophisticated methods should be preferred. The additive model is Y[t] = T[t] + S[t] + e[t] The multiplicative model is Y[t] = T[t] * S[t] * e[t] The seasonal component is first removed by applying a convolution filter to the data. The average of this smoothed series for each period is the returned seasonal component. See Also -------- statsmodels.tsa.filters.bk_filter.bkfilter statsmodels.tsa.filters.cf_filter.xffilter statsmodels.tsa.filters.hp_filter.hpfilter statsmodels.tsa.filters.convolution_filter Nz,This function does not handle missing valuesmrzJMultiplicative seasonality is not appropriate for zero and negative valueszhYou must specify a freq or x must be a pandas object with a timeseries index with a freq not set to Noneg?rg?r)r )seasonalr$residobserved)rrrZ asanyarrayr#lenallZisfinite ValueError startswithrr rrepeatintr r(rZmeanZtiler!rDecomposeResult)rZmodelZfiltrZ two_sidedZextrapolate_trendZ_pandas_wrapperZpfreqnobsZnsidesr$Z detrendedZperiod_averagesr-r.resultsrrrseasonal_decompose5sP6  &          r9c@seZdZddZddZdS)r6cKs2x t|D]\}}t|||q Wt|j|_dS)N)rsetattrr0r/r7)selfkwargskeyvaluerrr__init__szDecomposeResult.__init__cCs`ddlm}|}|jdddd\}}t|jdr|jj|ddd |dd |jj|ddd |dd |jj|d dd |d d |j j|ddd |ddn|d|j|dd |d|j|dd |d |j|d d |d|j |dd|d d|d d|j | |S)Nr) _import_mplrT)ZsharexplotF)ZaxZlegendZObservedZTrendr+ZSeasonalr,ZResidualZTime)Zstatsmodels.graphics.utilsr@Zsubplotshasattrr/rBZ set_ylabelr$r-r.Z set_xlabelZset_xlimr7Z tight_layout)r;r@ZpltZfigZaxesrrrrBs0  zDecomposeResult.plotN)__name__ __module__ __qualname__r?rBrrrrr6sr6__main__iiIii)iiiiiQfir,b+isii}iiirA)r) DataFrame DatetimeIndexz1/1/1951Q)startZperiodsr)r)NNTr) __doc__Zstatsmodels.compat.pythonrrrZnumpyrZpandas.core.nanopsrr Zfilters._utilsrrZfilters.filtertoolsr Zstatsmodels.tsa.tsatoolsr rr(r9objectr6rDrrr8ZpandasrXrYr0dataZresrrrrs*     t#