:i"!>SSKrSSKJrJr SSKJr "SS\5rg)N) MaskedModelsafe_isinstance) Explainerc\^\rSrSrSrS U4SjjrSSS.U4Sjjr\S5rS r S r U=r $) AdditiveExplaineraComputes SHAP values for generalized additive models. This assumes that the model only has first-order effects. Extending this to second- and third-order effects is future work (if you apply this to those models right now you will get incorrect answers that fail additivity). Nc ,>[T U]XXES9 [US5(a:URUlUR cUR Ul[S5e[UR S5(dS5e[URUR URUR[R"UR RS55n[R"UR RSS-UR RS4[ S9n[#SUR RSS-5H nS XxUS- 4'M U"U5n U S Ul[R"URS5Ul[#SUR RSS-5H$nXUR$- UR&US- 'M& UR&R)5UR$-Ulg) aBuild an Additive explainer for the given model using the given masker object. Parameters ---------- model : function A callable python object that executes the model given a set of input data samples. masker : function or numpy.array or pandas.DataFrame A callable python object used to "mask" out hidden features of the form ``masker(mask, *fargs)``. It takes a single a binary mask and an input sample and returns a matrix of masked samples. These masked samples are evaluated using the model function and the outputs are then averaged. As a shortcut for the standard masking used by SHAP you can pass a background data matrix instead of a function and that matrix will be used for masking. To use a clustering game structure you can pass a ``shap.maskers.Tabular(data, hclustering="correlation")`` object, but note that this structure information has no effect on the explanations of additive models. ) feature_nameslinearize_link0interpret.glassbox.ExplainableBoostingClassifierNziMasker not given and we don't yet support pulling the distribution centering directly from the EBM model!zshap.maskers.IndependentzFThe Additive explainer only supports the Tabular masker at the moment!r)dtypeFr)super__init__rdecision_functionmodelmasker intercept__expected_valueNotImplementedErrorrlinkr npzerosshapeonesboolrange _zero_offset_input_offsetssum) selfrrrr r fmmasksioutputs __class__s \/srv/projetos/modelo_ml_acdoc/venv/lib/python3.13/site-packages/shap/explainers/_additive.pyrAdditiveExplainer.__init__s$ mc 5"T U U00DJ{{"','7'7$* t{{,FGG T G T[[$))T=P=PRTRZRZ[_[f[f[l[lmn[oRp q**1-14;;3D3DQ3GHPTUq$++++A.23A#EQU(O4U)#AJ hhv||A7q$++++A.23A)0d6G6G)GD  A &4 $226684;L;LLF max_evalssilentc$>[TU]"X1US.6$)z^Explains the output of model(*args), where args represents one or more parallel iterable args.r+)r__call__)r"r,r-argsr's r(r/AdditiveExplainer.__call__Gsw6JJr*c^[US5(aURS:wa [S5egg)zDetermines if this explainer can handle the given model. This is an abstract static method meant to be implemented by each subclass. rrz,Need to add support for interaction effects!TF)r interactionsr)rrs r(supports_model_with_masker,AdditiveExplainer.supports_model_with_maskerMs2 5"T U U!!Q&)*XYYr*c USn[R"[U5[U545n [[U55H n XXU 4'M UR U 5UR - UR - n U URUV s/sHoRPM sn U [URSS5S.$s sn f)z_Explains a single row and returns the tuple (row_values, row_expected_values, row_mask_shapes).r clusteringN)valuesexpected_values mask_shapes main_effectsr7) rrlenrrrr rrgetattrr) r"r,r; error_bounds batch_sizer&r-row_argsxinputsr%phias r( explain_rowAdditiveExplainer.explain_rowZs QK3q63q6*+s1vA4Fa4Ljj 4#4#44t7J7JJ#33-56XGGX6!$++|TB   7sB?)rr rr)NNT) __name__ __module__ __qualname____firstlineno____doc__rr/ staticmethodr4rE__static_attributes__ __classcell__)r's@r(r r s@6Mp)-UKK     r*r )numpyrutilsrr _explainerrr r*r(rSs0!b b r*