M/PhP&ddlZddlmZddlmZddlmZmZddl m Z ddl m Z dZ dd Zdd Z dd Z dd Z ddZdS)N) arima_process)prefix_dtype_map) _get_epsilonapprox_fprime_cs)find_best_blas_type)_arma_innovationszThe model's autoregressive parameters (ar_params) indicate that the process is non-stationary. The innovations algorithm cannot be used. Fc tj|d}|jdk}|r |dddf}tj|gn|}tj|gn|}|j\}}tjd| f} tjd|f} |)t |||tj|g\}} } t|} tj || }tj || }tj || }| | }tt|dz} tt|dz}tt|dz}tj| | || |z }| | | |\}}||||||\}}tj|}tj|d ksLtj|r&tj|st%t&g}t)|D]A}tj||dd|f|||}||Btj|j}|r||dddfd zz}|r|}||fS) ay Compute innovations using a given ARMA process. Parameters ---------- endog : ndarray The observed time-series process, may be univariate or multivariate. ar_params : ndarray, optional Autoregressive parameters. ma_params : ndarray, optional Moving average parameters. sigma2 : ndarray, optional The ARMA innovation variance. Default is 1. normalize : bool, optional Whether or not to normalize the returned innovations. Default is False. prefix : str, optional The BLAS prefix associated with the datatype. Default is to find the best datatype based on given input. This argument is typically only used internally. Returns ------- innovations : ndarray Innovations (one-step-ahead prediction errors) for the given `endog` series with predictions based on the given ARMA process. If `normalize=True`, then the returned innovations have been "whitened" by dividing through by the square root of the mean square error. innovations_mse : ndarray Mean square error for the innovations. WC) requirementsrNdtypearma_transformed_acovf_fastarma_innovations_algo_fastarma_innovations_filter)sigma2nobsrg?)nprequirendim atleast_1dshaper_rarrayrasfortranarrayitemgetattrr r arma_acovfanyisfiniteall ValueErrorNON_STATIONARY_ERRORrangeappendvstackTsqueeze)endog ar_params ma_paramsr normalizeprefixsqueezedrk_endogarmar_rrrracovfacovf2thetavuiu_is l/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/statsmodels/tsa/innovations/arma_innovations.pyarma_innovationsr;sB JuD 1 1 1EzQHaaag I$5bb9EEI I$5bb9EEIKMD' q9*} B q)| B~. Iy"(6*:*: ;==q V $E  e5 1 1 1E!)5999I!)5999I U6]]   ! !F#*6$AA#C#C!(6$@@"B"B%6$==??)"b17dDDDFLMJ//B CCME6))$ 9*/99HE1  A q1u / E""&&((/ A""$$/-... A 7^^h..uQQQT{I/8%AABB   ! A Qqqq$wZ_ IIKK a4KcRt|||||}tj|S)a Compute the log-likelihood of the given data assuming an ARMA process. Parameters ---------- endog : ndarray The observed time-series process. ar_params : ndarray, optional Autoregressive parameters. ma_params : ndarray, optional Moving average parameters. sigma2 : ndarray, optional The ARMA innovation variance. Default is 1. prefix : str, optional The BLAS prefix associated with the datatype. Default is to find the best datatype based on given input. This argument is typically only used internally. Returns ------- float The joint loglikelihood. )r*r+rr-)arma_loglikeobsrsum)r)r*r+rr-llf_obss r: arma_loglikerAns10eyI%+F<<r>s2 HUOOE I$5bb9EEI I$5bb9EEI ~. Iy"(6*:*: ;==q V $E  e 4 4 4E!)5999I!)5999I U6]]   ! !F $f/E&E F FD 4y)V 4 44r<c |gn|}|gn|}t|t|  fd}tj|||f}t|ddt|}t |||S)a Compute the score (gradient of the log-likelihood function). Parameters ---------- endog : ndarray The observed time-series process. ar_params : ndarray, optional Autoregressive coefficients, not including the zero lag. ma_params : ndarray, optional Moving average coefficients, not including the zero lag, where the sign convention assumes the coefficients are part of the lag polynomial on the right-hand-side of the ARMA definition (i.e. they have the same sign from the usual econometrics convention in which the coefficients are on the right-hand-side of the ARMA definition). sigma2 : ndarray, optional The ARMA innovation variance. Default is 1. prefix : str, optional The BLAS prefix associated with the datatype. Default is to find the best datatype based on given input. This argument is typically only used internally. Returns ------- ndarray Score, evaluated at the given parameters. Notes ----- This is a numerical approximation, calculated using first-order complex step differentiation on the `arma_loglike` method. Ncdt|d|z|zdSN)rAparamsr)pqs r:rEzarma_score..funcs7E6"1":vaAgq1uvvOOOr<@lenrrrr r)r*r+rr-rEparams0epsilonrKrLs ` @@r: arma_scorerSsD 'YI'YI IA IAPPPPPPPeIy&01G7Bc'll;;G GT7 3 33r<c |gn|}|gn|}t|t|  fd}tj|||f}t|ddt|}t |||S)a Compute the score (gradient) per observation. Parameters ---------- endog : ndarray The observed time-series process. ar_params : ndarray, optional Autoregressive coefficients, not including the zero lag. ma_params : ndarray, optional Moving average coefficients, not including the zero lag, where the sign convention assumes the coefficients are part of the lag polynomial on the right-hand-side of the ARMA definition (i.e. they have the same sign from the usual econometrics convention in which the coefficients are on the right-hand-side of the ARMA definition). sigma2 : ndarray, optional The ARMA innovation variance. Default is 1. prefix : str, optional The BLAS prefix associated with the datatype. Default is to find the best datatype based on given input. This argument is typically only used internally. Returns ------- ndarray Score per observation, evaluated at the given parameters. Notes ----- This is a numerical approximation, calculated using first-order complex step differentiation on the `arma_loglike` method. Ncdt|d|z|zdSrH)r>rIs r:rEzarma_scoreobs..funcs>ufRaRj&1q5/%a!eff~// /r<rMrNrPs ` @@r: arma_scoreobsrVsD 'YI'YI IA IA///////eIy&01G7Bc'll;;G GT7 3 33r<)NNrFN)NNrN)numpyrstatsmodels.tsar statsmodels.tsa.statespace.toolsrstatsmodels.tools.numdiffrrscipy.linalg.blasrr r#r;rAr>rSrVr<r:r^s))))))======DDDDDDDD111111 DE-1\\\\~:CD(5(5(5(5V>?-4-4-4-4`AB.4.4.4.4.4.4r<