M/Ph7dZddlZddlmZddlmZddlmZm Z ddl m Z m Z m Z mZgdZGdd ZGd d e ZGd d e ZdS)aY Multivariate Conditional and Unconditional Kernel Density Estimation with Mixed Data Types References ---------- [1] Racine, J., Li, Q. Nonparametric econometrics: theory and practice. Princeton University Press. (2007) [2] Racine, Jeff. "Nonparametric Econometrics: A Primer," Foundation and Trends in Econometrics: Vol 3: No 1, pp1-88. (2008) http://dx.doi.org/10.1561/0800000009 [3] Racine, J., Li, Q. "Nonparametric Estimation of Distributions with Categorical and Continuous Data." Working Paper. (2000) [4] Racine, J. Li, Q. "Kernel Estimation of Multivariate Conditional Distributions Annals of Economics and Finance 5, 211-235 (2004) [5] Liu, R., Yang, L. "Kernel estimation of multivariate cumulative distribution function." Journal of Nonparametric Statistics (2008) [6] Li, R., Ju, G. "Nonparametric Estimation of Multivariate CDF with Categorical and Continuous Data." Working Paper [7] Li, Q., Racine, J. "Cross-validated local linear nonparametric regression" Statistica Sinica 14(2004), pp. 485-512 [8] Racine, J.: "Consistent Significance Testing for Nonparametric Regression" Journal of Business & Economics Statistics [9] Racine, J., Hart, J., Li, Q., "Testing the Significance of Categorical Predictor Variables in Nonparametric Regression Models", 2006, Econometric Reviews 25, 523-544 N)optimize) mquantiles)KDEMultivariate KernelReg)gpke LeaveOneOut _get_type_pos _adjust_shape)SingleIndexModel SemiLinear TestFFormc&eZdZdZddZdZdZdS)r a] Nonparametric test for functional form. Parameters ---------- endog : list Dependent variable (training set) exog : list of array_like objects The independent (right-hand-side) variables bw : array_like, str Bandwidths for exog or specify method for bandwidth selection fform : function The functional form ``y = g(b, x)`` to be tested. Takes as inputs the RHS variables `exog` and the coefficients ``b`` (betas) and returns a fitted ``y_hat``. var_type : str The type of the independent `exog` variables: - c: continuous - o: ordered - u: unordered estimator : function Must return the estimated coefficients b (betas). Takes as inputs ``(endog, exog)``. E.g. least square estimator:: lambda (x,y): np.dot(np.pinv(np.dot(x.T, x)), np.dot(x.T, y)) References ---------- See Racine, J.: "Consistent Significance Testing for Nonparametric Regression" Journal of Business & Economics Statistics. See chapter 12 in [1] pp. 355-357. dc||_||_||_||_||_||_t |||j|_||_ dS)N)bwvar_type) endogexogrfform estimatornbootrr _compute_sigsig)selfrrrrrrrs o/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/statsmodels/sandbox/nonparametric/kernel_extras.py__init__zTestFForm.__init__Ps\     " !$2AAAD$$&&c|j}|j}|||}|||}t j|d}||z }|t j|z }|||_t j d}d|z dz }d|zdz } ||z} | |z} | |z } t j |j df} t|j D]}| }tjdd|f}|| k}| |||<||z}|||}|||}||z }||| |<| |_d}|jt#| dkrd}|jt#| d krd }|jt#| d krd }|S) Nrg@g@sizezNot Significantg?*gffffff?z**gGz?z***)rrrrnpshapemean_compute_test_stat test_statsqrtemptyrrangecopyrandomuniform boots_resultsr)rYXbmnresidsqrt5fct1fct2u1u2rI_distju_bootprobindY_bootb_hatm_hat u_boot_hatrs rrzTestFForm._compute_sigZs J I NN1a  JJq!   HQKKNA&0077 E RE R E\ E\ 5L4:a.))tz"" < Jvs33 3 3C >Jvt44 4 4C >Jvt44 4 4C rc tj|d}t|j}t|dddf}d}d}t |D]\}}t |} tj| } t|j | |j|ddf |j d} ||| z| z} | j| jksJ|| z }|| dz z }tj |dksJtj |dksJ|d||dz zz z}t|j d} |j | } |d| z||dz zz z}||ztj| |z z}|S)NrF)data data_predictrtosumrg?)r#r$rr__iter__ enumeratenextsqueezerrrsumr!r prodr()rur3XLOOuLOOivalS2iX_not_iu_jKf_iix_conthpTs rr&zTestFForm._compute_test_stats HQKKN49%%1QQQtV9%%..00 #D// $ $JAwt**C*S//CTWG849QT?:J"m5:::AQ4#:>C9'''' CGGII D 36,,.. B74==A%%%%72;;!##### a1q5k"" ..q1 WW  " " $ $ a"fQU $$ HrwrBw'' 'rN)r)__name__ __module__ __qualname____doc__rrr&rrr r ,sR""F''''$$$Lrr c2eZdZdZdZdZdZddZdZdS) r a Single index semiparametric model ``y = g(X * b) + e``. Parameters ---------- endog : array_like The dependent variable exog : array_like The independent variable(s) var_type : str The type of variables in X: - c: continuous - o: ordered - u: unordered Attributes ---------- b : array_like The linear coefficients b (betas) bw : array_like Bandwidths Methods ------- fit(): Computes the fitted values ``E[Y|X] = g(X * b)`` and the marginal effects ``dY/dX``. References ---------- See chapter on semiparametric models in [1] Notes ----- This model resembles the binary choice models. The user knows that X and b interact linearly, but ``g(X * b)`` is unknown. In the parametric binary choice models the user usually assumes some distribution of g() such as normal or logistic. c||_t||_|jd|_t|d|_t||j|_t j|jd|_|j|_ d|_ d|_ d|_ |j |_|\|_|_dS)Nrrgaussian wangryzinaitchisonaitken)rlenrWr rrr#r$nobs data_typeckertypeokertypeukertype_est_loc_linearfunc _est_b_bwr1r)rrrrs rrzSingleIndexModel.__init__s  X a( "5!,, !$// HTY''* " # ) ( ..**rctj|jdzf}t j|j|d}|d|j}||jd}||}||fS)Nrr rdisp)r#r,r-rWrfmincv_loo_set_bw_boundsrparams0b_bwr1rs rrnzSingleIndexModel._est_b_bwst)##$&1*#88}T['::: 46N $&'']   $ $"u rc 0tj|}|d|j}||jd}t|j}t|j}d}t|D]\}}t|} | || tj ||dddf tj |j||dzddf| d} ||j|| z dzz }||j z S)NrrrrrFrH) r#asarrayrWrrrrIrJrKrmdotrg) rparamsr1rLOO_XLOO_YLrTrUr/Gs rrszSingleIndexModel.cv_loosF## 1tv:  DFGG_DI&&DJ''0022 #E** * *JAwU A "ARVGQ-?-?$-G,G(*ty1Q3/BA(F(F'FHHHIKA $*Q-!#) )AA49}rNc >||j}nt||j}tj|d}tj|f}tj||jf}t |D]}||j|j tj |j|j dddftj |||dzddf|j }|d||<tj |d}|||ddf<||fS)NrrrF) rr rWr#r$r)r*rmrrr{r1rL)rrFN_data_predictr%mfxrTmean_mfxmfx_cs rfitzSingleIndexModel.fits  9LL(tv>>L,//2x)**h/00~&&  Ayy$*!# 46!:!:111T6!B.0f\!AaC%(5KDF.S.S!UUHqkDGJx{++EC111IISyrcd}|dt|jzdzz }|dt|jzdzz }|d|jzdzz }|dz }|dz }|S) Provide something sane to print.zSingle Index Model Number of variables: K =  zNumber of samples: nobs = Variable types: BW selection method: cv_ls Estimator type: local constant strrWrgrrreprs r__repr__zSingleIndexModel.__repr__ss& +c$&kk9D@@ .TY?$FF '$-7$>> 33 77 r)N r\r]r^r_rrnrsrrr`rrr r so&&N + + +(&rr c2eZdZdZdZdZdZddZdZdS) r a} Semiparametric partially linear model, ``Y = Xb + g(Z) + e``. Parameters ---------- endog : array_like The dependent variable exog : array_like The linear component in the regression exog_nonparametric : array_like The nonparametric component in the regression var_type : str The type of the variables in the nonparametric component; - c: continuous - o: ordered - u: unordered k_linear : int The number of variables that comprise the linear component. Attributes ---------- bw : array_like Bandwidths for the nonparametric component exog_nonparametric b : array_like Coefficients in the linear component nobs : int The number of observations. k_linear : int The number of variables that comprise the linear component. Methods ------- fit Returns the fitted mean and marginal effects dy/dz Notes ----- This model uses only the local constant regression estimator References ---------- See chapter on Semiparametric Models in [1] ct|d|_t|||_t||_t||j|_||_tj|jd|_ ||_ |j |_ d|_ d|_ d|_|j|_|\|_|_dS)Nrrrcrdre)r rrrfrWexog_nonparametrick_linearr#r$rgrrhrirjrkrlrmrnr1r)rrrrrrs rrzSemiLinear.__init__;s"5!,, !$11 X"/0BDF"K"K  HTY''*   " # ) ( ..**rctj|j|jzf}t j|j|d}|d|j}||jd}||fS)z Computes the (beta) coefficients and the bandwidths. Minimizes ``cv_loo`` with respect to ``b`` and ``bw``. r rrpN)r#r,r-rrWrrrrsrus rrnzSemiLinear._est_b_bwKsj )##$-$&*@)C#DD}T['::: T]" # $-.. !"u rc tj|}|d|j}||jd}t|j}t|j}t|j}tj|j|dddf}d}t|D]\} } t|} t|} tj| |dddf} | | z }| ||| |j| ddf d}|| ddf}||j| |z |z dzz }|S)a Similar to the cross validation leave-one-out estimator. Modified to reflect the linear components. Parameters ---------- params : array_like Vector consisting of the coefficients (b) and the bandwidths (bw). The first ``k_linear`` elements are the coefficients. Returns ------- L : float The value of the objective function References ---------- See p.254 in [1] rNryrH) r#rzrrrrrIrr{rJrKrm)rr|r1rr}r~LOO_ZXbriirUr/ZXb_jYxrlts rrszSemiLinear.cv_looXso*F## 1t}$ % DMNN #DI&&DJ''0022D344==?? VDIq ! !!!!D& ) $U++ 0 0KBU AU A6'1%%aaaf-DTB "BaR(,(?AAA(F'FHHHIKABEB $*R.2%)a/ /AArNc L||j}nt||j}||j}nt||j}t j|d}t j|f}t j||jf}|jt j ||j dddfz }t|D]]}| |j ||j||ddf}|d||<t j|d} | ||ddf<^||fS)z+Computes fitted values and marginal effectsNrrr)rr rrrWr#r$r)rr{r1r*rmrrL) r exog_predictexog_nonparametric_predictrr%rr/rTrrs rrzSemiLinear.fits8  9LL(t}EEL % -)-)@ & &)67QSWSY)Z)Z &"<==a@x)**h/00 J df55aaaf= =~&&  Ayy!T-D.HAAA.N!PPHqkDGJx{++EC111IISyrcd}|dt|jzdzz }|dt|jzdzz }|d|jzdzz }|dz }|dz }|S)rz'Semiparamatric Partially Linear Model rrzNumber of samples: N = rrrrrs rrzSemiLinear.__repr__ss9 +c$&kk9D@@ +c$)nn> 33 77 r)NNrr`rrr r sp,,\+++   '''R4rr )r_numpyr#scipyrscipy.stats.mstatsrstatsmodels.nonparametric.apirr&statsmodels.nonparametric._kernel_baserrr r __all__r r r r`rrrsD>))))))DDDDDDDD444444444444 : 9 9llllllll^nnnnnynnnbWWWWWWWWWWr