DjBddlmZddlmZddlmZddlmZm Z ddl Z ddl m Z ddlmZdd lmZmZmZd d lmZd d lmZgd ZGddeeZGddeeZGddeZGddeZGddeZy)) BaseEstimator)LinearRegression)api)ABCMetaabstractmethodN)DTYPE) deprecated)cdiff check_endog)approx)C_tseries_pp_sum)ADFTestKPSSTestPPTestc,eZdZedZedZy)_BaseStationarityTestc.||jddk(ryy)NrFT)shape)xs _C:\Crop_Prediction\Backend\crop-ai-system\venv\Lib\site-packages\pmdarima/arima/stationarity.py _base_casez _BaseStationarityTest._base_case s I1771:?c|jd}||kDr tdtt|dz ddDcgc] \}}||||z }}}t j |Scc}}w)Nrzk cannot exceed y dimr)r ValueError enumeraterangenpasarray)rknijrowss r_embedz_BaseStationarityTest._embed'sv GGAJ q545 5$-U1q5"b-A#B 1aAaAJ  zz$  sA&N)__name__ __module__ __qualname__ staticmethodrr(rrrrs(     rr) metaclasscDeZdZdZdZedZeddZy)_DifferencingStationarityTestuProvides the base class for stationarity tests such as the Kwiatkowski–Phillips–Schmidt–Shin, Augmented Dickey-Fuller and the Phillips–Perron tests. These tests are used to determine whether a time series is stationary. c||_y)Nalpha)selfr3s r__init__z&_DifferencingStationarityTest.__init__<s  rcy)aTest whether the time series is stationary or it needs differencing. Parameters ---------- x : array-like, shape=(n_samples,) The time series vector. Returns ------- pval : float The computed P-value of the test. sig : bool Whether the P-value is significant at the ``alpha`` level. More directly, whether to difference the time series. Nr-r4rs r should_diffz)_DifferencingStationarityTest.should_diff?srr8) use_insteadc$|j|S)aTest whether the time series is stationary. Parameters ---------- x : array-like, shape=(n_samples,) The time series vector. Returns ------- pval : float The computed P-value of the test. sig : bool Whether the P-value is significant at the ``alpha`` level. More directly, whether to difference the time series. )r8r7s r is_stationaryz+_DifferencingStationarityTest.is_stationarySs$""rN) r)r*r+__doc__r5rr8r r;r-rrr0r06s9   &M*#+#rr0cHeZdZdZddhZeddddZd fd Zd ZxZ S) ruConduct a KPSS test for stationarity. In econometrics, Kwiatkowski–Phillips–Schmidt–Shin (KPSS) tests are used for testing a null hypothesis that an observable time series is stationary around a deterministic trend (i.e. trend-stationary) against the alternative of a unit root. Parameters ---------- alpha : float, optional (default=0.05) Level of the test null : str, optional (default='level') Whether to fit the linear model on the one vector, or an arange. If ``null`` is 'trend', a linear model is fit on an arange, if 'level', it is fit on the one vector. lshort : bool, optional (default=True) Whether or not to truncate the ``l`` value in the C code. Notes ----- This test is generally used indirectly via the :func:`pmdarima.arima.ndiffs` function, which computes the differencing term, ``d``. References ---------- .. [1] R's tseries KPSS test source code: http://bit.ly/2eJP1IU trendnull{Gz?皙?皙?皙?cJtt| |||_||_yNr2)superrr5r?lshort)r4r3r?rG __class__s rr5zKPSSTest.__init__s# h&U&3  rc|j|stjdfSt|td}|j d}|j }|dk(r4tj|j|d}tdddd }nQ|d k(r4tj|j|d}td d d d}ntd|jztj||}||j|z }tj |}||zj#|dzz } ||zj#|z } |j$r(t'tj(d|dz dzz} n't'tj(d|dz dzz} t+||| | } | | z } t-||j.| d\} }|d|d|j0kfS)Test whether the time series is stationary or needs differencing. Parameters ---------- x : array-like, shape=(n_samples,) The time series vector. Returns ------- pval : float The computed P-value of the test. sig : bool Whether the P-value is significant at the ``alpha`` level. More directly, whether to difference the time series. Fdtypepreserve_seriesrr>rgS?gI +?g㥛 ?gX9v?levelgS?g|?5^?goʡ?gh|?5?znull must be one of %rrd? xoutrule)rr!nanr r rr?arangereshaper onesr_validrfitpredictcumsumsumrGinttruncrrtablepr3)r4rr$r?ttablelmesetas2l_stat_pvals rr8zKPSSTest.should_diffs"q!665=   > GGAJyy 7? ! $$Q*AeUE51E W_ ""1a(AeUE51E5 CD D  # #Aq )  1  IIaL1ukkmq!t$!e[[]Q  ;;RXXa1s7t"3345BRXXbAG#4456BaB +Rx $Q?4 AwQ$**,,,r)rBrNT) r)r*r+r<rZr rar5r8 __classcell__rHs@rrrhs/<v F tUD$ 'F D-rrc eZdZdZej gdZejdZe dddddd Z e d d d d ddddZ dfd Z e dZe dZdZxZS)ruConduct an ADF test for stationarity. In statistics and econometrics, an augmented Dickey–Fuller test (ADF) tests the null hypothesis of a unit root is present in a time series sample. The alternative hypothesis is different depending on which version of the test is used, but is usually stationarity or trend-stationarity. It is an augmented version of the Dickey–Fuller test for a larger and more complicated set of time series models. Parameters ---------- alpha : float, optional (default=0.05) Level of the test k : int, optional (default=None) The drift parameter. If ``k`` is None, it will be set to: ``np.trunc(np.power(x.shape[0] - 1, 1 / 3.0))`` Notes ----- This test is generally used indirectly via the :func:`pmdarima.arima.ndiffs` function, which computes the differencing term, ``d``. ADF test does not perform as close to the R code as do the KPSS and PP tests. This is due to the fact that is has to use statsmodels OLS regression for std err estimates rather than the more robust sklearn LinearRegression. References ---------- .. [1] https://wikipedia.org/wiki/Augmented_Dickey–Fuller_test .. [2] R's tseries ADF source code: https://bit.ly/2EnvM5V ))gQgg gQ g= ףp=ggg333333ÿ)ggffffffg gq= ףp g ףp= gףp= g(\gQο)g)\(gףp= g g333333 gQggףp= gQѿ)gQgQ gq= ףp ףp= gGzgq= ףpg{Gzgףp= ӿ)gףp= gq= ףp g\(\ rpgףp= g(\gg{GzԿ)gGzgHzG gHzG g(\ggGzgQgQտr2rP順r@rArBrC?ffffff?333333?Gz?cbtt| |||_||dkr t dyy)Nr2rz#k must be a positive integer (>= 0))rFrr5r#r)r4r3r#rHs rr5zADFTest.__init__s: gt%E%2 =QUBC C#=rc|jd}|dddf}tj|dz |}||}|dz }|jd}tjtj|j |df|j |df|j |dfg} |dkDr"|ddd|f} tj| | g} t j|| djdS)NrrT)hasconstqr)method) rr!rWhstackrYrXsmOLSr[) ryzr#r$ytttxt1_nXyt1s r_olsz ADFTest._olss GGAJ q!tW YYq1ua e aYYq\ IIrwwr{**B73{{B7+zz2q'*, - q5AqsF)C 1c(#A vvb!d+//t/< FF 9!''!*q.':;A FQJ G GGAJ KK1   ii1a#""3'884;;') 4;; 1a4 0qq A! D)* Xt{{AF 8{ TDJJ&&&+)s 4E9)rBN)r)r*r+r<r!rrcrrr rrar5r,rrr8rmrns@rrrs!D BHH E[[^F r2sCf -F tUD$dE4 @FD==6**<'rrc eZdZdZej gdj ZejdZ e dddddd je Z e d d d d ddddZdfd ZdZxZS)ru6Conduct a PP test for stationarity. In statistics, the Phillips–Perron test (named after Peter C. B. Phillips and Pierre Perron) is a unit root test. It is used in time series analysis to test the null hypothesis that a time series is integrated of order 1. It builds on the Dickey–Fuller test of the null hypothesis ``p = 0``. Parameters ---------- alpha : float, optional (default=0.05) Level of the test lshort : bool, optional (default=True) Whether or not to truncate the ``l`` value in the C code. Notes ----- This test is generally used indirectly via the :func:`pmdarima.arima.ndiffs` function, which computes the differencing term, ``d``. The R code allows for two types of tests: 'Z(alpha)' and 'Z(t_alpha)'. Since sklearn does not allow extraction of std errors from the linear model fit, ``t_alpha`` is much more difficult to achieve, so we do not allow that variant. References ---------- .. [1] R's tseries PP test source code: http://bit.ly/2wbzx6V ))g6@g333339@gffffff;@gffffff<@gfffff<@g=@)gfffff3@gffffff6@g7@gffffff8@g8@g9@)gfffff1@g3@g333334@gL5@g5@g5@)g333333/@g0@g1@g2@g2@gL2@)gHzG @gGz @gQ @g@gGz@g)\(@)gGz@g@g(\@gQ@g333333@gHzG@)g{Gz?g(\?gGz?{Gz?rgp= ף?)gQ?g?g?g= ףp=?gzG?gףp= ?rrqrrrPrsrtrur@rArBrCrvrwrxryc<tt| |||_yrE)rFrr5rG)r4r3rGrHs rr5zPPTest.__init__s fd$5$1 rc |j|stjdfSt|td}|j |d}|dddf}|dddf}|j d}tj|dz|dz z }tjtj|||gj}tj||}|j} ||j|z } | | zjt!|z } |j"sdnd } t%tj&| tj(|d z d z} t+| || | }||z}|tj|dzzj}||dz z|dzjzd z }||dzz}||dzz|z|jz}||dzzd|zdzz|jdzzd z }||z |z|z }| d}||dz z|dzd|zz || z zz }tjt-|j.Dcgc]/}t1|j2|j4dd|f|dd1c}}t1||j6|d\}}|d}|||j8kDfScc}w)rJFrKrrNrg@rRrOgY@rQg(@g@g8@rS)rr!rVr r r(rrWrrYrrr[coef_r\r^floatrGr_r`rrr rrrrcrar3)r4rrrrr$rrrcoefussqruscalarrissqrtln2syt11ntrm1trm2trm3trm4dxr3rr%rrkrrls rr8zPPTest.should_diffs"q!665=   > KK1  q!tW1g HHQKiilQ1s7 + HHbggaj"c* + - - $$Q+yy Q Q a(;;A &288AIt#<<= >!!QE2U1)*//1R!V}q~~//$6FaK AE{V#cggi/QU q1uqy)SWWY!^<C D[4 $ &QEAI!q&TBY!76E>!JJ884;;') 4;; 1a4 0qq A! D)* Xt{{AF 8{TDJJ&&&)s4K)rBT)r)r*r+r<r!rrrcrrr astyper rrar5r8rmrns@rrrns|>RXX   q E[[^F r2sCf - 4 4U ;F tUD$dE4 @F L'rr) sklearn.basersklearn.linear_modelr statsmodelsrrabcrrnumpyr! compat.numpyr decoratorsr utils.arrayr r r r_arimar__all__rr0rrrr-rrrs~'1!' #.. %  MW ./#$9W/#dl-,l-^T'+T'n@' *@'r