0Ph&dZddlZddlZddlZddlmZddlmZddl m Z ddl m Z m Z mZddl mZddlmZdd lmZmZd Zejejdd d jZejgd jZejeedkeZeeZ ej!ej"eZ#de#e dk<de#e dke dkz<de#e dk<e ddZ$e de$e ddedde ddzgZ%de%DZ&ej'(de%dZ)dZ*ej'(de&dZ+ej'(de%dZ,ej'(de%d Z-ej'(de&d!Z.ej'(de%d"Z/d#Z0ej'(de&d$Z1ej'(de%d%Z2ej'(de%d&Z3d'Z4ej'(d(de die5d)fgd*Z6dS)+z+Testing for Gaussian process classificationN) approx_fprime)ConvergenceWarning)GaussianProcessClassifier)RBFCompoundKernel WhiteKernel)ConstantKernel) MiniSeqKernel)assert_almost_equalassert_array_equalc*tj|S)N)npsin)xs g/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/sklearn/gaussian_process/tests/test_gpc.pyfrs 6!99 )@g@g@g@g@dtypegffffffֿgffffff??fixed length_scalelength_scale_boundsg?)r)MbP?@@g{Gz?Y@c(g|]}|tk |S) fixed_kernel).0kernels r r)/s"LLLV|5K5KV5K5K5Krr(ct|tt}t |t|tdddfdkdS)Nr(r?)rfitXyr predict predict_probar(gpcs rtest_predict_consistentr42sd $6 2 2 2 6 6q! < > >F #6 2 2 2 6 6q! < r?r2s rtest_lml_precomputedrCKsg $6 2 2 2 6 6q! < r?shapefloat64r=r )r(r3 input_thetas rtest_lml_without_cloning_kernelrJTsx $6 2 2 2 6 6q! < r?rallabsbounds)r(r3lml lml_gradients rtest_converged_to_local_maximumrR^s $6 2 2 2 6 6q! < z#test_lml_gradient..ssC$?$?u$M$Mrg|=)rr-r.r/r=r?rr )r(rPrQlml_gradient_approxr3s @rtest_lml_gradientrXls $6 2 2 2 6 6q! < r?finfofloat32eps) global_random_seed n_samples n_featuresrngr.r/r(last_lmlr]gprPs rtest_random_startsroys["Iz )   2 3 3C )Z((1,q0A A  A!2!2!2!:!: :a?A sK 3Vj({mj>X$$$FwH %a &!5+    #a)) (()9::X 4 4 888888rcfd}t||}|tt||jj||jksJdS)Nc ~tj }|||d}}tdD]{}tj|tjd|dddftjd|dddf}||d}||kr||}}|||fS)NF) eval_gradientrrr)rr_r`re atleast_1duniformmaximumminimum) obj_func initial_thetarOrl theta_optfunc_min_r?rris r optimizerz(test_custom_optimizer..optimizersi##$677+XX . . . 8 r / /AM BJr6!!!Q$<88"*QqqqRSt :U:UVVEe444A8||&+Q8 (""r)r(r})rr-r.y_mcr=r>r?)r(rir}r3s ` rtest_custom_optimizerrs # # # # # $6Y G G GCGGAt  & &    $ $V\ 2 2 3 3 3 3 3 3rcZt|}|tt|t }t |dd|t }ttj |d|dS)Nr+r) rr-r.r~r1X2r rbr0r rargmax)r(r3y_proby_preds rtest_multi_classrs $6 2 2 2CGGAt   r " "F 1 q))) [[__Fry++V44444rcPt|}|ttt|d}|tt|t }|t }t ||dS)Nr+r)r(n_jobs)rr-r.r~r1rr )r(r3gpc_2ry_prob_2s rtest_multi_class_n_jobsrs $6 2 2 2CGGAt %VA > > >E IIa   r " "F""2&&H)))))rctddg}t|}d}tjt|5|t tdddn #1swxYwYtddgtdd gz}t|}tj d 5}tj d |t tt|d ksJt|djtsJ|djjddksJt|djtsJ|djjddksJ dddn #1swxYwYt#jt d }tddgddg}t|}tj d 5}tj d ||tt|d ksJt|djtsJ|djjddksJt|djtsJ|djjddksJ ddddS#1swxYwYdS)Ngh㈵>r )rr+zThe optimal value found for dimension 0 of parameter length_scale is close to the specified upper bound 0.001. Increasing the bound and calling fit again may find a better value.match)noise_level_boundsr!gj@T)recordalwaysrrzThe optimal value found for dimension 0 of parameter k1__noise_level is close to the specified upper bound 0.001. Increasing the bound and calling fit again may find a better value.rzThe optimal value found for dimension 0 of parameter k2__length_scale is close to the specified lower bound 1000.0. Decreasing the bound and calling fit again may find a better value.rrg$@r#rzThe optimal value found for dimension 0 of parameter length_scale is close to the specified upper bound 100.0. Increasing the bound and calling fit again may find a better value.zThe optimal value found for dimension 1 of parameter length_scale is close to the specified upper bound 100.0. Increasing the bound and calling fit again may find a better value.)rrpytestwarnsrr-r.r/rwarningscatch_warnings simplefilterlen issubclasscategorymessageargsrtile) r(r3warning_message kernel_sumgpc_sumrX_tile kernel_dimsgpc_dimss rtest_warning_boundsrs dD\ 2 2 2F #6 2 2 2C  ( @ @ @ 1 t === #JAAAJ(z:::G   - - - h''' Aq6{{a&),.@AAAAA 1I  "1 %*1 1 1 1 1&),.@AAAAA 1I  "1 %*1 1 1 1 1 1%               4WQ]]FC:C:NNNK( <<rsm11  ((((((111111>>>>>> ONNNNNJJJJJJJJBM+"+aR(())+R],,,--/ BHQQqTTZZ\\A S)))QqTTZZ\\rxs###R%Z$%bEkb4i !R$YsAAA CSCSk:::Ac;##3KPPPP   ML'LLL7++JJ,+J JJJ#455657++,+7++;;,+;#455  65 7++ > >,+ >.#4553365327++ 5 5,+ 57++ * *,+ *F F F R!~~a(( )  /     r