Dj-dZddlZddlZddlmZddlm Z m Z ddl m Z ddl mZddlmZddlmZgd Zd Zd Z dd ZGd dZy)z+ Seasonal Decomposition by Moving Averages N)nanmean) PandasWrapper array_like)STL)convolution_filter)MSTL)freq_to_period)rseasonal_decompose seasonal_meanDecomposeResultrc Vtdt|D}|jddz tdt|dddDz }t||z|}t |||z }t j jt jt j||t j||z f|||dd\}}t jd|t j|zt j|zj}|jdk(r|j}||d|t j jt jt j||t j||z f|||dd\}}t j|dz|jdt j|zt j|zj}|jdk(r|j}|||dzd|S)z Replace nan values on trend's end-points with least-squares extrapolated values with regression considering npoints closest defined points. c3xK|]2\}}tjtj|r/|4ywNnpanyisnan.0ivalss \C:\Crop_Prediction\Backend\crop-ai-system\venv\Lib\site-packages\statsmodels\tsa\seasonal.py z%_extrapolate_trend..s,a1Gs0::rc3vK|]1\}}tjtj|s|3ywrrrs rrz%_extrapolate_trend.."s0 466"((4.)  s79N)rcond)next enumerateshapeminmaxrlinalglstsqc_arangeonesTndimsqueeze) trendnpointsfrontback front_last back_firstknextras r_extrapolate_trendr4s "5) E  A   $U4R4[1    UW_d+JUD7N+J 99?? biiz*BGGJ4F,GGH eJ    DAq YYq% 2558 +beeAh 6 9 9E zzQ E&5M 99?? bii D)2774*3D+EEF j    DAq YYtaxQ 02558 ;beeAh F I IE zzQ E$(* Lc tjt|Dcgc]}t||d|dc}Scc}w)z Return means for each period in x. period is an int that gives the number of periods per cycle. E.g., 12 for monthly. NaNs are ignored in the mean. Nraxis)rarrayrange pd_nanmean)xperiodrs rr r Bs6 88uV}M!Z!)V) 15M NNMs>cJ|}t|}|tt|dddd}t|dd}t|}t j t j |s td|jdr#t j|d kr td ||t|}|}n td |jd d|zkr"td d|zd |jd d|I|dzd k(r(t jdgdg|dz zzdgz|z }nt jd|z |}t|dz} t||| } |dk(r|dz }|d kDrt!| |dz} |jdr|| z } n|| z } t#| |} |jdr| t j$| d z} n| t j$| d z} t j&| j(||zdzj(d|} |jdr || z | z }n| | z }g}t+| | ||fdD]5\}}|j-|j/|j1|7t3|d |d|d|dS)a Seasonal decomposition using moving averages. Parameters ---------- x : array_like Time series. If 2d, individual series are in columns. x must contain 2 complete cycles. model : {"additive", "multiplicative"}, optional Type of seasonal component. Abbreviations are accepted. filt : array_like, optional The filter coefficients for filtering out the seasonal component. The concrete moving average method used in filtering is determined by two_sided. period : int, optional Period of the series (e.g., 1 for annual, 4 for quarterly, etc). Must be used if x is not a pandas object or if the index of x does not have a frequency. Overrides default periodicity of x if x is a pandas object with a timeseries index. two_sided : bool, optional 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 ------- DecomposeResult A object with seasonal, trend, and resid attributes. See Also -------- statsmodels.tsa.filters.bk_filter.bkfilter Baxter-King filter. statsmodels.tsa.filters.cf_filter.cffilter Christiano-Fitzgerald asymmetric, random walk filter. statsmodels.tsa.filters.hp_filter.hpfilter Hodrick-Prescott filter. statsmodels.tsa.filters.convolution_filter Linear filtering via convolution. statsmodels.tsa.seasonal.STL Season-Trend decomposition using LOESS. 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 results are obtained by first estimating the trend by applying a convolution filter to the data. The trend is then removed from the series and the average of this de-trended series for each period is the returned seasonal component. Nindex inferred_freqr<)maxdimz,This function does not handle missing valuesmrzJMultiplicative seasonality is not appropriate for zero and negative valueszxYou must specify a period or x must be a pandas object with a PeriodIndex or a DatetimeIndex with a freq not set to Nonez'x must have 2 complete cycles requires z observations. x only has z observation(s)g?rg?freqr7)seasonalr+residN)columns)rEr+rFobserved)rgetattrrlenrallisfinite ValueError startswithrr r r9repeatintrr4r meantiler(zipappendwrapr*r )r<modelfiltr= two_sidedextrapolate_trendpfreqpwnobsnsidesr+ detrendedperiod_averagesrErFresultssnames rr r KsL E q B ~7D1?DI1c!$A q6D 66"++a. !GHH  66!q&>/  ~  "5)EFO  wwqzAI5a%i[A(() |? D   | A:?88SEQC6A:$66#>?&HD99S6\62D ^a F q$ /EF""QJ1"5*;a*?@ I I #Iv6O 277?;;277?;;ww(($&.1*<=??FH H u$H$G 5%#%I;4 rwwqyy{Dw9:; ajaj  r5ceZdZdZd dZedZedZedZedZ edZ ed Z d d Z y) r a Results class for seasonal decompositions Parameters ---------- observed : array_like The data series that has been decomposed. seasonal : array_like The seasonal component of the data series. trend : array_like The trend component of the data series. resid : array_like The residual component of the data series. weights : array_like, optional The weights used to reduce outlier influence. Nc||_||_|Qtj|}t |t j r"t j ||jd}||_||_ ||_ y)Nweights)r?rc) _seasonal_trendr ones_like isinstancepdSeriesr?_weights_resid _observed)selfrIrEr+rFrfs r__init__zDecomposeResult.__init__sa! ?ll8,G(BII.))8>>    !r5c|jS)z Observed data)rorps rrIzDecomposeResult.observed~~r5c|jS)z The estimated seasonal component)rgrss rrEzDecomposeResult.seasonalrtr5c|jS)zThe estimated trend component)rhrss rr+zDecomposeResult.trend {{r5c|jS)zThe estimated residuals)rnrss rrFzDecomposeResult.residrwr5c|jS)z)The weights used in the robust estimation)rmrss rrfzDecomposeResult.weightss}}r5c.|jjS)zNumber of observations)ror rss rr]zDecomposeResult.nobss~~###r5cddlm}ddlm}|}||r|jdfgng} | |r|j dfgngz } |j jdk(r| |r|j dfgngz } n|j jdkDrt|j tjr5|j jD]} | |r|j | dfgngz } nDt|j jdD]} | |r|j dd| fdfgngz } !| |r|jd fgngz } | |r|jd fgngz } t|jtjtj frO|jjd} |jj"d|jj"| dz f} nd|jjddz f} |j%t'| dd \}}t)t+|| D]\} \}\} }|d k7r|j-| n)|j-| d d|j-| dddt/| d|}|dk7r|j1}| dk(r|r |j2n |j4}|||j7| |j9|S)a@ Plot estimated components Parameters ---------- observed : bool Include the observed series in the plot seasonal : bool Include the seasonal component in the plot trend : bool Include the trend component in the plot resid : bool Include the residual in the plot weights : bool Include the weights in the plot (if any) Returns ------- matplotlib.figure.Figure The figure instance that containing the plot. r)register_matplotlib_converters) _import_mplObservedr+rrENresidualrfT)sharexonone)marker linestyle)rrz#000000)colorzorderrc)pandas.plottingr|statsmodels.graphics.utilsr}ror+rEr)rjrk DataFramerGr:r rFrfrlr?subplotsrKrrTplotrJ capitalize set_title set_ylabelset_xlim tight_layout)rprIrEr+rFrfr|r}pltseriescolrr]xlimfigaxsaxdef_namerctitles rrzDecomposeResult.plots: C:m&(3;4>>:./UDJJ(): ==   " x z23R GF ]]  ! #$--6==00C>F$--,j9:BF t}}22156A?G$--1-z:;RF DJJ +,2=DLL),-b@ dnnr||RYY&? @>>''*D>>''*DNN,@,@,JJDt~~++A.23D<<F Qt<<S+4Sf5E+F  'A'&VX:%sf=fIbA6684D:%($%FxBLLR]]E $K KK    r5r)TTTTF) __name__ __module__ __qualname____doc__rqpropertyrIrEr+rFrfr]rr5rr r s" "$$  Lr5r )additiveNNTr)rnumpyrpandasrkpandas.core.nanopsrr;statsmodels.tools.validationrrstatsmodels.tsa.stl._stlr#statsmodels.tsa.filters.filtertoolsrstatsmodels.tsa.stl.mstlrstatsmodels.tsa.tsatoolsr __all__r4r r r rr5rrs[4B(B)3 (VO   RjIIr5