'YHh7dZddlZddlmZddlmZddlmZm Z ddl m Z m Z m Z mZgdZGdd ZGd d e ZGd d e Zy)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$eZdZdZddZdZdZy)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. c||_||_||_||_||_||_t |||j|_|j|_ y)N)bwvar_type) endogexogrfform estimatornbootrr _compute_sigsig)selfrrrrrrrs h/var/www/html/planif/env/lib/python3.12/site-packages/statsmodels/sandbox/nonparametric/kernel_extras.py__init__zTestFForm.__init__PsR     " !$2ADD$$&c|j}|j}|j||}|j||}t j |d}||z }|t j |z }|j||_t jd}d|z dz }d|zdz } ||z} | |z} | |z } t j|jdf} t|jD]}| j}tjjdd|f}|| k}| |||<||z}|j||}|j||}||z }|j|| |<| |_d}|jt#| dkDrd}|jt#| d kDrd }|jt#| d kDrd }|S) Nrg@g@sizezNot Significantg?*gffffff?z**gGz?z***)rrrrnpshapemean_compute_test_stat test_statsqrtemptyrrangecopyrandomuniform boots_resultsr)rYXbmnresidsqrt5fct1fct2u1u2rI_distju_bootprobindY_bootb_hatm_hat u_boot_hatrs rrzTestFForm._compute_sigZs JJ II NN1a  JJq!  HHQKNA&007 E RE R E\ E\ 5L4::a.)tzz" >Jvs3 3C >>Jvt4 4C >>Jvt4 4C rc ftj|d}t|j}t|dddfj }d}d}t |D]\}}t |} tj| } t|j| |j|ddf |jd} ||| z| z} | j| jk(sJ|| jz }|| dzjz }tj|dk(sJtj|dk(rJ|d||dz zz z}t|jd} |j| j} |d| z||dz zz z}||ztj| |z z}|S)NrF)data data_predictrtosumrg?)r"r#rr__iter__ enumeratenextsqueezerrrsumr r prodr')rur2XLOOuLOOivalS2iX_not_iu_jKf_iix_conthpTs rr%zTestFForm._compute_test_stats HHQKN499%1QtV9%..0 #D/ $JAwt*C**S/CTWWG8499QT?:J"mm5:AQ4#:>C99' '' CGGI D 36,,. B774=A% %%772;!# ## $ a1q5k"" .q1 WWW  " " $ a"fQU $$ HrwwrBw' 'rN)d)__name__ __module__ __qualname____doc__rrr%rrr r ,s"F'$Lrr c0eZdZdZdZdZdZddZdZy) r a Single index semiparametric model ``y = g(X * b) + e``. Parameters ---------- endog : array_like The dependent variable exog : array_like The independent variable(s) var_type : str The type of variables in X: - c: continuous - o: ordered - u: unordered Attributes ---------- b : array_like The linear coefficients b (betas) bw : array_like Bandwidths Methods ------- fit(): Computes the fitted values ``E[Y|X] = g(X * b)`` and the marginal effects ``dY/dX``. References ---------- See chapter on semiparametric models in [1] Notes ----- This model resembles the binary choice models. The user knows that X and b interact linearly, but ``g(X * b)`` is unknown. In the parametric binary choice models the user usually assumes some distribution of g() such as normal or logistic. c||_t||_|jd|_t|d|_t||j|_t j|j d|_|j|_ d|_ d|_ d|_ |j|_|j\|_|_y)Nrrgaussian wangryzinaitchisonaitken)rlenrVr rrr"r#nobs data_typeckertypeokertypeukertype_est_loc_linearfunc _est_b_bwr0r)rrrrs rrzSingleIndexModel.__init__s  X a( "5!, !$/ HHTYY'* " # ) (( ..*rctjj|jdzf}t j |j |d}|d|j}||jd}|j|}||fS)Nrrrdisp)r"r+r,rVrfmincv_loo_set_bw_boundsrparams0b_bwr0rs rrnzSingleIndexModel._est_b_bwsp))##$&&1*#8}}T[[': 466N $&&']   $"u rc $tj|}|d|j}||jd}t|j}t|j j }d}t|D]\}}t|} |j|| tj||dddf tj|j||dzddf| d} ||j || z dzz }||jz S)NrrrrrErG) r"asarrayrVrrrrHrIrJrmdotrg) rparamsr0rLOO_XLOO_YLrSrTr.Gs rrszSingleIndexModel.cv_loosF# 1tvv  DFFG_DII&DJJ'002 #E* *JAwU A "ARVVGQ-?$-G,G(*tyy1Q3/BA(F'FHHIKA $**Q-!#) )A *499}rNc h| |j}nt||j}tj|d}tj |f}tj ||jf}t |D]}|j|j|jtj|j|jdddftj|||dzddf|j}|d||<tj|d}|||ddf<||fS)NrrrE) rr rVr"r#r(r)rmrrr{r0rK)rrEN_data_predictr$mfxrSmean_mfxmfx_cs rfitzSingleIndexModel.fits   99L(tvv>L,/2xx)*hh/0~& Ayy$**!# 466!:1T6!B.0ff\!AaC%(5KDFF.S!UHqkDGJJx{+EC1I  Syrcd}|dt|jzdzz }|dt|jzdzz }|d|jzdzz }|dz }|dz }|S) Provide something sane to print.zSingle Index Model Number of variables: K =  zNumber of samples: nobs = Variable types: BW selection method: cv_ls Estimator type: local constant strrVrgrrreprs r__repr__zSingleIndexModel.__repr__su& +c$&&k9D@@ .TYY?$FF '$--7$>> 33 77 r)N r\r]r^r_rrnrsrrr`rrr r s!&N +(&rr c0eZdZdZdZdZdZddZdZy) 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|_|j#\|_|_y)Nrrrcrdre)r rrrfrVexog_nonparametrick_linearr"r#rgrrhrirjrkrlrmrnr0r)rrrrrrs rrzSemiLinear.__init__;s"5!, !$1 X"/0BDFF"K  HHTYY'*   " # ) (( ..*rctjj|j|jzf}t j |j|d}|d|j}||jd}||fS)z Computes the (beta) coefficients and the bandwidths. Minimizes ``cv_loo`` with respect to ``b`` and ``bw``. rrrpN)r"r+r,rrVrrrrsrus rrnzSemiLinear._est_b_bwKsj ))##$--$&&*@)C#D}}T[[': T]] # $--. !"u rc tj|}|d|j}||jd}t|j}t|j j }t|jj }tj|j|dddf}d}t|D]\} } t|} t|} tj| |dddf} | | z }|j||| |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] rNryrG) r"rzrrrrrHrr{rIrJrm)rr|r0rr}r~LOO_ZXbriirTr.ZXb_jYxrlts rrszSemiLinear.cv_looXsM*F# 1t}} % DMMN #DII&DJJ'002D334==? VVDIIq !!D& ) $U+ 0KBU AU A66'1%af-DTB "BaR(,(?(?A(F'FHHIKABEB $**R.2%)a/ /A 0rNc v| |j}nt||j}| |j}nt||j}t j |d}t j|f}t j||jf}|jt j||jdddfz }t|D][}|j|j||j||ddf}|d||<t j|d} | ||ddf<]||fS)z+Computes fitted values and marginal effectsNrrr)rr rrrVr"r#r(rr{r0r)rmrrK) r exog_predictexog_nonparametric_predictrr$rr.rSrrs rrzSemiLinear.fits(  99L(t}}EL % -)-)@)@ &)67QSWSYSY)Z &"<=a@xx)*hh/0 JJ dff5af= =~& Ayy!T-D-D.HA.N!PHqkDGJJx{+EC1I  Syrcd}|dt|jzdzz }|dt|jzdzz }|d|jzdzz }|dz }|dz }|S)rz'Semiparamatric Partially Linear Model rrzNumber of samples: N = rrrrrs rrzSemiLinear.__repr__su9 +c$&&k9D@@ +c$))n> 33 77 r)NNrr`rrr r s",\+ 'R4rr )r_numpyr"scipyrscipy.stats.mstatsrstatsmodels.nonparametric.apirr&statsmodels.nonparametric._kernel_baserrr r __all__r r r r`rrrsS>)D44 :ll^nynbWWr