U mdlZ @sddlmZddlmZmZddlZddlZddlZ ddlm Z ddl m Z ddl mZddlmZmZddlmZdd lmZdd lmZmZmZmZd d d ddddddddg ZdFdd ZdGddZdHddZdId"d#d$d%d&d'd(d ZdJd)d Z d*dZ!d+dZ"d,d-Z#d.d/Z$d0d1Z%d2dZ&d3dZ'd4dZ(d5dZ)d6dZ*d7d8Z+d9d:Z,d;d<Z-d=d>Z.d?d@Z/dAdBZ0dCd"dDdEdZ1dS)K) annotations)lrangeLiteralN) DataFrame)offsets) to_offset) _is_recarray_is_using_pandas) ValueWarning)NDArray) array_like bool_likeint_like string_likelagmat lagmat2ds add_trendduplication_matrixelimination_matrixcommutation_matrixvecvechunvecunvechfreq_to_periodcFskipcCst|d}t|ddd}t|ddd}dddg}|d kr@|S|d krZ|d d }d }nB|dksj|dkr|d d}|dkr|d d}d }n |dkrd}t|rd dlm}t|t|d }|rt|t j rt |}q|}n t |}t|}t t jd |d t jd|d } t | } |dkr@| d d d f} d |krJ|rfdd} || d } n0t jt |d d} | d k} | |d d k@}|} t | rJ|dkr |jd krd}nHt |jd | }t|t j r|j}ddd|D}d|d}|d|d}t|n*|d krJ|d d }| d d d d f} |rTd nd!}|rt j | |j|d"} | |g}t j|d d |d d}n| |g}t |d d |}|S)#a Add a trend and/or constant to an array. Parameters ---------- x : array_like Original array of data. trend : str {'n', 'c', 't', 'ct', 'ctt'} The trend to add. * 'n' add no trend. * 'c' add constant only. * 't' add trend only. * 'ct' add constant and linear trend. * 'ctt' add constant and linear and quadratic trend. prepend : bool If True, prepends the new data to the columns of X. has_constant : str {'raise', 'add', 'skip'} Controls what happens when trend is 'c' and a constant column already exists in x. 'raise' will raise an error. 'add' will add a column of 1s. 'skip' will return the data without change. 'skip' is the default. Returns ------- array_like The original data with the additional trend columns. If x is a pandas Series or DataFrame, then the trend column names are 'const', 'trend' and 'trend_squared'. See Also -------- statsmodels.tools.tools.add_constant Add a constant column to an array. Notes ----- Returns columns as ['ctt','ct','c'] whenever applicable. There is currently no checking for an existing trend. prependtrend)nrtctcttoptions has_constant)raiseaddrconstZ trend_squaredrrNrr!r r")recarray_exception)dtypecSs2zt|dkot|dkWSYdSXdS)NgF)npptpany)sr1Q/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/statsmodels/tsa/tsatools.py safe_is_const}sz add_trend..safe_is_constaxisr&zx is constant.z, cSsg|] }t|qSr1str.0rr1r1r2 szadd_trend..z3x contains one or more constant columns. Column(s) z are constant.z Adding a constant with trend='z' is not allowed.rindexcolumns)r rcopyrstatsmodels.tools.sm_exceptionsr+NotImplementedErrorr isinstancepdZSeriesrr- asanyarraylenvanderarangeZfloat64Zfliplrapplyr.r/ndimshaper>join ValueErrorr=concat column_stack)xrrr%r>Z trendorderr+ is_pandasnobsZtrendarrr3Z col_constZptp0Z col_is_constZnz_constZbase_errZ const_colsmsgorderr1r1r2r&s(                     r)Tc CsVt|d}t|d}t|ddd}|dkr.d}|dkrD|jd|}|jdkr^|dddf}|dd|f}|d kr|d}nV|d kr|jd}nB|dkr|jd|d}||jdkr|jd}td t|}t||d d }t |}t ||jd} |r.||kr| | |n| | |t ||d|f|||d| ffS)a Returns an array with lags included given an array. Parameters ---------- x : array_like An array or NumPy ndarray subclass. Can be either a 1d or 2d array with observations in columns. col : int or None `col` can be an int of the zero-based column index. If it's a 1d array `col` can be None. lags : int The number of lags desired. drop : bool Whether to keep the contemporaneous variable for the data. insert : bool or int If True, inserts the lagged values after `col`. If False, appends the data. If int inserts the lags at int. Returns ------- array : ndarray Array with lags Examples -------- >>> import statsmodels.api as sm >>> data = sm.datasets.macrodata.load() >>> data = data.data[['year','quarter','realgdp','cpi']] >>> data = sm.tsa.add_lag(data, 'realgdp', lags=2) Notes ----- Trims the array both forward and backward, so that the array returned so that the length of the returned array is len(`X`) - lags. The lags are returned in increasing order, ie., t-1,t-2,...,t-lags lagsdroprOr*)rINrr)TFz number of variables, inserting at the last positionZBoth)trim)rr r rJrIwarningswarnr rrpopr=r-rN) rOcolrTrUinsertZcontempZins_idxZndlagsZ first_colsZ last_colsr1r1r2add_lags>'       r\cCst|d}t|d}|jdkr2t|dkr2|j}n|jdkrDtd|jd}|dkrh||jdd}n>tjt t ||dd}tj | |}|t ||}|jdkrt|dkr|j}|S) a Detrend an array with a trend of given order along axis 0 or 1. Parameters ---------- x : array_like, 1d or 2d Data, if 2d, then each row or column is independently detrended with the same trendorder, but independent trend estimates. order : int The polynomial order of the trend, zero is constant, one is linear trend, two is quadratic trend. axis : int Axis can be either 0, observations by rows, or 1, observations by columns. Returns ------- ndarray The detrended series is the residual of the linear regression of the data on the trend of given order. rSr5r*r)z0x.ndim > 2 is not implemented until it is neededrr4)N)rrIintTrArJZmeanr-rFrGfloatZlinalgZpinvdot)rOrSr5rQZresidZtrendsbetar1r1r2detrends"    rcforwardexr^z0Literal[('forward', 'backward', 'both', 'none')]zLiteral[('ex', 'sep', 'in')]boolzKNDArray | DataFrame | tuple[NDArray, NDArray] | tuple[DataFrame, DataFrame])maxlagrVoriginal use_pandasreturncszt|d}t|d}t|dddd}t|ddd }|}t|d d d d }t|d oR|}|d kr`dn|}|}|r|dkrtdd}|j\}} |dkr| }||krtdt ||| |df} t dt |dD]8} || || ||| | || | || df<q|dkr d} n|dkr0|} ntd|dkrLt | } n|} |r.|}t |trdd|jD}t t||jdkrtdn t|jg}dd|D}t |D]*}t|d|fdd|Dqt| d | |j|d} | j| d }|dkr`||}|j|dd}n2| | | |d f}|d kr`| | | d |f}|d krr||fS|Sd S)!a, Create 2d array of lags. Parameters ---------- x : array_like Data; if 2d, observation in rows and variables in columns. maxlag : int All lags from zero to maxlag are included. trim : {'forward', 'backward', 'both', 'none', None} The trimming method to use. * 'forward' : trim invalid observations in front. * 'backward' : trim invalid initial observations. * 'both' : trim invalid observations on both sides. * 'none', None : no trimming of observations. original : {'ex','sep','in'} How the original is treated. * 'ex' : drops the original array returning only the lagged values. * 'in' : returns the original array and the lagged values as a single array. * 'sep' : returns a tuple (original array, lagged values). The original array is truncated to have the same number of rows as the returned lagmat. use_pandas : bool If true, returns a DataFrame when the input is a pandas Series or DataFrame. If false, return numpy ndarrays. Returns ------- lagmat : ndarray The array with lagged observations. y : ndarray, optional Only returned if original == 'sep'. Notes ----- When using a pandas DataFrame or Series with use_pandas=True, trim can only be 'forward' or 'both' since it is not possible to consistently extend index values. Examples -------- >>> from statsmodels.tsa.tsatools import lagmat >>> import numpy as np >>> X = np.arange(1,7).reshape(-1,2) >>> lagmat(X, maxlag=2, trim="forward", original='in') array([[ 1., 2., 0., 0., 0., 0.], [ 3., 4., 1., 2., 0., 0.], [ 5., 6., 3., 4., 1., 2.]]) >>> lagmat(X, maxlag=2, trim="backward", original='in') array([[ 5., 6., 3., 4., 1., 2.], [ 0., 0., 5., 6., 3., 4.], [ 0., 0., 0., 0., 5., 6.]]) >>> lagmat(X, maxlag=2, trim="both", original='in') array([[ 5., 6., 3., 4., 1., 2.]]) >>> lagmat(X, maxlag=2, trim="none", original='in') array([[ 1., 2., 0., 0., 0., 0.], [ 3., 4., 1., 2., 0., 0.], [ 5., 6., 3., 4., 1., 2.], [ 0., 0., 5., 6., 3., 4.], [ 0., 0., 0., 0., 5., 6.]]) rgrirVTrdbackwardbothnoneoptionalr$rh)resepinr#rOr*N)rIr,rn)rnrlzEtrim cannot be 'none' or 'backward' when used on Series or DataFramesr)rerqzmaxlag should be < nobsr))rnrd)rlrmztrim option not validcSsg|] }t|qSr1r6r8r1r1r2r:szlagmat..zSColumns names must be distinct after conversion to string (if not already strings).cSsg|] }t|qSr1r6r9rZr1r1r2r:scsg|]}t|dqS)z.L.r6rsZlag_strr1r2r:sr<)rqrer4rq)rr rr r lowerrLrJr-zerosranger^rErBrr>setr7nameextendr=ilocrU)rOrgrVrhriorigrPZdropidxrQnvarZlmkZstartobsZstopobsZ x_columnsr>ZlagrTZleadsr1rtr2r(sI                 c Cst|d}t|ddd}t|dddd}|dkr4|}t||}t|d}|jd krt|rbt|}q|dddf}n|jd ks|jd krtd |j\}} |r@|r@t |j ddd f||d dd} | j ddd|d fg} t d | D]D} t |j dd| f||d dd} | | j dd||d fqtj | d dS|rPt|}t |ddd f||d dddd|d fg} t d | D]<} | t |dd| f||d ddd||d fqt| S)a Generate lagmatrix for 2d array, columns arranged by variables. Parameters ---------- x : array_like Data, 2d. Observations in rows and variables in columns. maxlag0 : int The first variable all lags from zero to maxlag are included. maxlagex : {None, int} The max lag for all other variables all lags from zero to maxlag are included. dropex : int Exclude first dropex lags from other variables. For all variables, except the first, lags from dropex to maxlagex are included. trim : str The trimming method to use. * 'forward' : trim invalid observations in front. * 'backward' : trim invalid initial observations. * 'both' : trim invalid observations on both sides. * 'none' : no trimming of observations. use_pandas : bool If true, returns a DataFrame when the input is a pandas Series or DataFrame. If false, return numpy ndarrays. Returns ------- ndarray The array with lagged observations, columns ordered by variable. Notes ----- Inefficient implementation for unequal lags, implemented for convenience. maxlag0maxlagexT)rprVrkroNr)rr*z'Only supports 1 and 2-dimensional data.rr)rVrhrir4)rVrh)rrmaxr rIrCrrLrJrr{rwappendrMr-rDrN) rOrrZdropexrVrirgrPrQr}rTZlagslir~r1r1r2rsd&       " . cCs |dS)NF)ravelmatr1r1r2rscCs|jtt|SN)r_take _triu_indicesrErr1r1r2rscCst|\}}|||Sr)r-Z tril_indicesrrowscolsr1r1r2 _tril_indices"srcCst|\}}|||Sr)r- triu_indicesrr1r1r2r'srcCst|\}}|||Sr)r- diag_indicesrr1r1r2 _diag_indices,srcCs8ttt|}||t|ks&t|j||fddS)NrrS)r^r-sqrtrEAssertionErrorreshape)vr~r1r1r2r1scCslddtddt|}tt|}t||f}||t|<||j}|t|d<|S)Ng?r;r)r*) r-rrEr^roundrvrr_r)rrresultr1r1r2r7s cCs6t|d}t||dd}tdd|DjS)z Create duplication matrix D_n which satisfies vec(S) = D_n vech(S) for symmetric matrix S Returns ------- D_n : ndarray rr)r*cSsg|]}t|qSr1)rr)r9rOr1r1r2r:Qsz&duplication_matrix..)rr-eyearrayr_)rtmpr1r1r2rFs cCs8t|d}ttt||f}t|||dkS)z Create the elimination matrix L_n which satisfies vech(M) = L_n vec(M) for any matrix M Parameters ---------- Returns ------- rr)rrr-ZtrilZonesr)rZ vech_indicesr1r1r2rTs cCsPt|d}t|d}t||}t||j||fdd}|j|ddS)z Create the commutation matrix K_{p,q} satisfying vec(A') = K_{p,q} vec(A) Parameters ---------- p : int q : int Returns ------- K : ndarray (pq x pq) pqrrrr4)rr-rrGrrr)rrKindicesr1r1r2rds  c Cs~t|d}t|d}tdt|D]N}||}t|D]$}||||||d8<q>|d||d|<q*|S)z Transforms params to induce stationarity/invertability. Parameters ---------- params : array_like The AR coefficients Reference --------- Jones(1980) r*r)N)r-tanhrwrE)params newparamsrjakiterr1r1r2_ar_transparamsys  "rcCs|}|}tt|dddD]Z}||}t|D]0}||||||dd|d||<q8|d||d|<q$dt|}|S)z Inverse of the Jones reparameterization Parameters ---------- params : array_like The transformed AR coefficients r)rr;r*N)r?rwrEr-Zarctanh)rrrrrZ invarcoefsr1r1r2_ar_invtransparamss   rc Csdt| dt| }dt| dt| }tdt|D]N}||}t|D]$}||||||d7<qj|d||d|<qV|S)z Transforms params to induce stationarity/invertability. Parameters ---------- params : ndarray The ma coeffecients of an (AR)MA model. Reference --------- Jones(1980) r)N)r-expr?rwrE)rrrrbrr1r1r2_ma_transparamss $$ "rcCs|}tt|dddD]Z}||}t|D]0}||||||dd|d||<q0|d||d|<qtd|d| }|S)z Inverse of the Jones reparameterization Parameters ---------- params : ndarray The transformed MA coefficients r)rr;r*N)r?rwrEr-log)ZmacoefsrrrrZ invmacoefsr1r1r2_ma_invtransparamss   rcs8tddtfddtddDS)a Returns the successive differences needed to unintegrate the series. Parameters ---------- x : array_like The original series d : int The number of differences of the differenced series. Returns ------- y : array_like The increasing differences from 0 to d-1 of the first d elements of x. See Also -------- unintegrate dNcs g|]}t|dqS)r)r-diff)r9irrOr1r2r:sz&unintegrate_levels..rr;)rr-Zasarrayrw)rOrr1rr2unintegrate_levelss  rcCs\t|dd}t|dkr@|d}tttj||f|S|d}ttj||fS)ay After taking n-differences of a series, return the original series Parameters ---------- x : array_like The n-th differenced series levels : list A list of the first-value in each differenced series, for [first-difference, second-difference, ..., n-th difference] Returns ------- y : array_like The original series de-differenced Examples -------- >>> x = np.array([1, 3, 9., 19, 8.]) >>> levels = unintegrate_levels(x, 2) >>> levels array([ 1., 2.]) >>> unintegrate(np.diff(x, 2), levels) array([ 1., 3., 9., 19., 8.]) Nr)r;r)listrErY unintegrater-ZcumsumZr_)rOZlevelsZx0r1r1r2rs   rzstr | offsets.DateOffset)freqrjcCst|tjst|}t|tjs$t|j}|dks@|drDdS|dksV|drZdS|dksl|drpd S|d ks|d rd S|d krdS|dkrdS|dkrdStd |dS)a$ Convert a pandas frequency to a periodicity Parameters ---------- freq : str or offset Frequency to convert Returns ------- int Periodicity of freq Notes ----- Annual maps to 1, quarterly maps to 4, monthly to 12, weekly to 52. A)zA-zAS-r)Q)zQ-zQS-M)zM-ZMS WzW-4DBHzDfreq {} not understood. Please report if you think this is in error.N) rBrZ DateOffsetrrZ rule_codeupper startswithrLformat)rr1r1r2rs.  )rFr)Nr)FT)r)r)rdreF)NrrdF)2 __future__rZstatsmodels.compat.pythonrrrWnumpyr-ZpandasrCrZpandas.tseriesrZpandas.tseries.frequenciesrZstatsmodels.tools.datarr r@r Zstatsmodels.tools.typingr Zstatsmodels.tools.validationr r rr__all__rr\rcrrrrrrrrrrrrrrrrrrrr1r1r1r2sl        P 1 W"