:i gSrSSKJr SSKJr SSKJr SSKr SSK r SSK J r SSKJrJr SSKJr SS KJr SS jrS r"S S 5rSSSjjrSSjrg)z!Visualize cumulative SHAP values.) annotationsN)hclust_ordering) LogitLinkconvert_to_link)colors)labelscURS:XaX U- URS- -$URSnX3S--S-nX- U- S- nX%-n[R"US5nUSS2USUS4==U- ss'U$)zShift SHAP base value to a new value. This function assumes that `base_value` and `new_base_value` are scalars and that `shap_values` is a two or three dimensional array. rrrN)ndimshapenpdiag_indices_from) base_valuenew_base_value shap_values main_effects all_effectstempidxs W/srv/projetos/modelo_ml_acdoc/venv/lib/python3.13/site-packages/shap/plots/_decision.py__change_shap_base_valuers 1>9[=N=Nq=QQQQ$$Q'L"23q8K  '; 6 :D$K  {1~ .C3q63q6!"d*" c  SnU (a+[R"5RSUU-S-5 [R"USSS9 [ SU5Hn[R "UU SS SS 9 M [ R"S [S 9n[ R"UURS 5n[ R"SURS 5nUb SUU'SUU'[R"5nURU 5 [R"US9nURU 5 [ R "S US-5n/n[ URS 5HQn[R""UUSS24UUR%UUS4U 5UUUUS9nUR'US 5 MS [)SU5S5nUcSOSnURS S:XGa UGb[R"5R*R-5n[R"5R.R15nUS-n[ U5GHnUS U4n[3U[45(aS[5U5R75S3nO1SR9USR;S5R;S55nUR=[ R>"US UUS-245UUSU-USSSS 9n URAU RCUS!95n!U!RDU S:dMU RGUS-5 U RI[ RJ"US UUS-2455 U RMS"5 URAU RCUS!95n!U!RNU S :dGMcU RGU5 U RIU S 5 U RMS5 GM URPRSS#5 URTRSS$5 URVS"RYS%5 URVSRYS%5 UR[XS&S'9 [R\"[ R "U5S-UUS(9 UR[S)S*S+9 [R^"S U5 [R`"[bS,SS(9 U (Ga[R"US9nURe[ R"S S/55 [R^"S US--5 URgU S X:SU S - S-4UR.S.9n"[Rh"US S/S/U"S09n#U#Rk/5 U#RlR[S*S S19 U#RoU 5 U#RpRYS%5 [Rr"U5 U(a[Rt"U5 U(a#[R"5Rw5 UbURyUUUS29 U(a[Rz"5 gg)3z(Matplotlib rendering for decision_plot()g?g?z#999999)xcolorzorderrg?)r)yrlwdashesr-)dtyperNz-.r)cmap)r linewidth linestylec36# UHnSU;dM Uv M g7f) * N).0ss r -__decision_plot_matplotlib..\s 6A&A+aas   ()z({})z,.3f0.z leftcenter_baselinez#666666)fontsizehorizontalalignmentverticalalignmentr)rendererrightbothnoneFT)r labelcolorlabeltop)r8r ) labelsize MODEL_OUTPUTg?) transform horizontal)ticks orientationcax)rBlength)handlesr loc)>pltgcfset_size_inchesaxvlinerangeaxhlinerarrayobjectrepeatr gcaset_xlimcmScalarMappableset_climarangeplotto_rgbaappendnextcanvas get_renderer transDatainverted isinstancestrstripformatrstriptextmaxtransform_bboxget_window_extentxmaxset_textset_xminset_horizontalalignmentxminxaxisset_ticks_positionyaxisspines set_visible tick_paramsyticksylimxlabelr set_array inset_axescolorbarset_ticklabelsax set_alphaoutlinescatitle invert_yaxislegendshow)$rcumsum ascendingfeature_display_countfeatures feature_names highlight plot_color axis_colory_demarc_colorxlimalpha color_barauto_size_plotrr legend_labelslegend_location row_heightir(r'rmy_poslinesor-r8r;invertervtbbax_cbcbs$ r__decision_plot_matplotlibr#sR,J  !!!%:Z%G#%MNKK*Ib91+ , a~#fRP-F+I )V\\!_5I !V\\!_-I# ) ) BKK z*AJJt IIa.2 3E E 6<<? # HH 1a4L%qyy2'FR[\]R^jstujv   QqT $ 6 6=AYrAH  Q18#7779##002779&&//1 ,-AAA!S!!A 'q)MMQtH"4"4S"9"@"@"EFvaa!en-.aq!$*"3A(()<)>> range1, range2 = range(20), range(20, 40) >>> r = decision_plot(base, shap_values[range1], features[range1], return_objects=True) >>> decision_plot(base, shap_values[range2], features[range2], feature_order=r.feature_idx, xlim=r.xlim) Parameters ---------- base_value : float The base value used in the plot. For multioutput models, this will be the mean of the base values. This will inherit `new_base_value` if specified. shap_values : numpy.ndarray The `shap_values` passed to decision_plot re-ordered based on `feature_order`. If SHAP interaction values are passed to decision_plot, `shap_values` is a 2D (matrix) representation of the interactions. See `feature_names` to locate the feature positions. If `new_base_value` is specified, the SHAP values are relative to the new base value. feature_names : list of str The feature names used in the plot in the order specified in the decision_plot parameter `feature_order`. feature_idx : numpy.ndarray The index used to order `shap_values` based on `feature_order`. This attribute can be used to specify identical feature ordering in multiple decision plots. xlim : tuple[float, float] The x-axis limits. This attributed can be used to specify the same x-axis in multiple decision plots. N)rrr feature_idxr)selfrrrrrs r__init__DecisionPlotResult.__init__s >%&*& r)rrrrrN)__name__ __module__ __qualname____firstlineno____doc__r__static_attributes__r+rrrrs  #rrc[U[R5(a[U5S:XaUSn[U[5(d[U[5(a [ S5e[U[R5(d [ S5eUR S:XaURSS5nURSnURSn[U[R5(a*UcURR5nURnO[U[R5(a*UcURR5nURnOE[U[5(aUcUnSnO(Ub%UR S:XaUcUR!5nSn[U[R[#S545(d [ S5eUb"UR S:XaURSS5nUc/[%U5Vs/sHn[&S[)U5-PM nnOJ[U5U:wa [+S 5e[U[[R45(d [ S 5eUR S :XGa UUS- -S -n[R,"US5n[R."USS5n[R"UUU-4UR05nUSS2USUS4USS2SU24'USS2USUS4S -USS2US24'UnS/URS-nUUSU&[3[%UURS5USUS5HunnnUUS UU3UU'M UnURSnSn[U[5(a[R4"U5n O[U[R5(aUn OUbUR75S:Xa[R8"U5n OUS:Xa>[R:"[R<"[R>"U5SS95n O?US:Xa.[R4"[AURC555n O [+S5eU RU4:wd4[RD"U R0[RF5(d [+S5eUc[ISSS5nO[U[H[$45(d [ S5eURJS;a [+S5e[U[$5(a}[RL"[RF5RNn![IURPS:a URPOU!URRS:a URROU!URJ5nUb[UUUU5nUnURWU5n"Sn#U"S S:XaSn#U"SS-U"SS-S4n"U"SU"S- n$USS2U 4nU"SS:Xa][R"UU$S-4UR05n%UU%SS2S4'U[RX"USS2SU"S24SS9-U%SS2SS24'O*U[RX"USS9SS2U"SS- U"S24-n%[R4"U5nUU U"SU"SR!5n&UU R!5nUcSOUSS2U U"SU"S4n'U(dEUS:a[[SUS35eU$S:a[[SU$S35eUU-S:a[[S US!US"35eUSLn([]U5nUn)[U[^5(a,URaU5nURaU%5n%U((aS#nOU((ay[OU%RO5U45n*[cU%Rc5U45n+UU*- U+U- n-n,U,U-:a UU,- UU--4nO UU-- UU--4nUSUS- S$-n.USU.- USU.-4nU cS%n Uc[dRfn[iUU%U#U$U'U&UUU U UU U U UUUU5 U(dg[kU)XU U5$s snf)&aVisualize model decisions using cumulative SHAP values. Each plotted line explains a single model prediction. If a single prediction is plotted, feature values will be printed in the plot (if supplied). If multiple predictions are plotted together, feature values will not be printed. Plotting too many predictions together will make the plot unintelligible. Parameters ---------- base_value : float or numpy.ndarray This is the reference value that the feature contributions start from. Usually, this is ``explainer.expected_value``. shap_values : numpy.ndarray Matrix of SHAP values (# features) or (# samples x # features) from ``explainer.shap_values()``. Or cube of SHAP interaction values (# samples x # features x # features) from ``explainer.shap_interaction_values()``. features : numpy.array or pandas.Series or pandas.DataFrame or numpy.ndarray or list Matrix of feature values (# features) or (# samples x # features). This provides the values of all the features and, optionally, the feature names. feature_names : list or numpy.ndarray List of feature names (# features). If ``None``, names may be derived from the ``features`` argument if a Pandas object is provided. Otherwise, numeric feature names will be generated. feature_order : str or None or list or numpy.ndarray Any of "importance" (the default), "hclust" (hierarchical clustering), ``None``, or a list/array of indices. feature_display_range: slice or range The slice or range of features to plot after ordering features by ``feature_order``. A step of 1 or ``None`` will display the features in ascending order. A step of -1 will display the features in descending order. If ``feature_display_range=None``, ``slice(-1, -21, -1)`` is used (i.e. show the last 20 features in descending order). If ``shap_values`` contains interaction values, the number of features is automatically expanded to include all possible interactions: N(N + 1)/2 where N = ``shap_values.shape[1]``. highlight : Any Specify which observations to draw in a different line style. All numpy indexing methods are supported. For example, list of integer indices, or a bool array. link : str Use "identity" or "logit" to specify the transformation used for the x-axis. The "logit" link transforms log-odds into probabilities. plot_color : str or matplotlib.colors.ColorMap Color spectrum used to draw the plot lines. If ``str``, a registered matplotlib color name is assumed. axis_color : str or int Color used to draw plot axes. y_demarc_color : str or int Color used to draw feature demarcation lines on the y-axis. alpha : float Alpha blending value in [0, 1] used to draw plot lines. color_bar : bool Whether to draw the color bar (legend). auto_size_plot : bool Whether to automatically size the matplotlib plot to fit the number of features displayed. If ``False``, specify the plot size using matplotlib before calling this function. title : str Title of the plot. xlim: tuple[float, float] The extents of the x-axis (e.g. ``(-1.0, 1.0)``). If not specified, the limits are determined by the maximum/minimum predictions centered around base_value when ``link="identity"``. When ``link="logit"``, the x-axis extents are ``(0, 1)`` centered at 0.5. ``xlim`` values are not transformed by the ``link`` function. This argument is provided to simplify producing multiple plots on the same scale for comparison. show : bool Whether :external+mpl:func:`matplotlib.pyplot.show()` is called before returning. Setting this to ``False`` allows the plot to be customized further after it has been created. return_objects : bool Whether to return a :obj:`DecisionPlotResult` object containing various plotting features. This can be used to generate multiple decision plots using the same feature ordering and scale. ignore_warnings : bool Plotting many data points or too many features at a time may be slow, or may create very large plots. Set this argument to ``True`` to override hard-coded limits that prevent plotting large amounts of data. new_base_value : float SHAP values are relative to a base value. By default, this base value is the expected value of the model's raw predictions. Use ``new_base_value`` to shift the base value to an arbitrary value (e.g. the cutoff point for a binary classification task). legend_labels : list of str List of legend labels. If ``None``, legend will not be shown. legend_location : str Legend location. Any of "best", "upper right", "upper left", "lower left", "lower right", "right", "center left", "center right", "lower center", "upper center", "center". Returns ------- DecisionPlotResult or None Returns a :obj:`DecisionPlotResult` object if ``return_objects=True``. Returns ``None`` otherwise (the default). Examples -------- Plot two decision plots using the same feature order and x-axis. >>> range1, range2 = range(20), range(20, 40) >>> r = decision_plot(base, shap_values[range1], features[range1], return_objects=True) >>> decision_plot(base, shap_values[range2], features[range2], feature_order=r.feature_idx, xlim=r.xlim) See more `decision plot examples here `_. rrzgLooks like multi output. Try base_value[i] and shap_values[i], or use shap.multioutput_decision_plot().zCThe shap_values arg is the wrong type. Try explainer.shap_values().rNz*The features arg uses an unsupported type.FEATUREzKThe feature_names arg must include all features represented in shap_values.z5The feature_names arg requires a list or numpy array.rr*r> importance)axishclustzkThe feature_order arg requires 'importance', 'hclust', 'none', or an integer list/array of feature indices.zA list or array has been specified for the feature_order arg. The length must match the feature count and the data type must be integer.iz:The feature_display_range arg requires a slice or a range.)rrNz@The feature_display_range arg supports a step of 1, -1, or None.TFiz Plotting zc observations may be slow. Consider subsampling or set ignore_warnings=True to ignore this message.zX features may create a very large plot. Set ignore_warnings=True to ignore this message.izProcessing SHAP values for z features over zK observations may be slow. Set ignore_warnings=True to ignore this message.)g{GzgRQ?g{Gz?g?)6rcrndarraylenlist TypeErrorr reshaper pd DataFramecolumnsto_listvaluesSeriesindextolisttyperPr rd ValueErrorrtriu_indices_fromr%ziprRlowerrZargsortsumabsr transpose issubdtypeintegerslicestepiinforostartstoprindices nancumsum RuntimeErrorrrfinvrir red_bluerr)/rrrr feature_orderfeature_display_rangerlinkrrrrrrrrrreturn_objectsignore_warningsrrrobservation_count feature_countr triu_countidx_diagidx_triuabrowcolrcdrrrfeature_names_displayfeatures_display create_xlimbase_value_savedrqrlnres/ rdecisionrs`*bjj))c*o.B] *d##z+t'D'D u  k2:: . .]^^1!))!R0 #))!,%%a(M(BLL))  $,,446M?? Hbii ( (  $NN224M?? Hd # #  $M  (--1"49N )  hT$Z 8 9 9DEE8==A#5##Ar*=B==QR=Q *SV3=Q R ] } ,fgg  bjj'9 : :OPP1"ma&78A= '' A7'' A: $5}z7Q#RT_TeTef*1hqk8A;+FG!^m^ *1hqk8A;+FG!K!]^  #f{'8'8';;).=u]K4E4Ea4HI8TU;X`abXcdKAsC#C()mC.@-ABAaDe #))!, -&&hh}- M2:: . .#  ]%8%8%:f%Dii . , &jj{(;!!DE ( "hh{/D/D/FGH  "  m--r}}[EVEVXZXbXb7c7c ?  $ %b#r 2 -u~ > >TUU  # #= 8[\\ )5 1 1 HHRZZ $ $ %+@+F+F!+K ! ' 'QR*?*D*D*I ! & &q ! & &! !.z>;W # %%m4AItrz qTAXqtax #aD1Q4Kan-KtqyZZ):Y5Z  t #-./??  !3 &123  , ,y 8-m_OL]K^_ $,K 4 D!$ ""YYz* 6"  D 6::<456::<45T!TJ%61 q5NJN3DNJN3D !WtAw $ &Q! T!Wq[) }__     %*  . KY] ^^SSsa8c [U[5(a[U[5(d [S5e[R"U5nUR S:Xd?[R "UR[R5(d [S5e[R"U5nUR S;a [S5eURSURS:wa [S5eUR5n[URS5Hn[XXAU5X'M UbtS U;anUS n[U[R5(aUR S :Xa Xb/US 'O1[U[R5(aUR UUS '[#XASS2USS2440UD6$) aSDecision plot for multioutput models. Plots all outputs for a single observation. By default, the plotted base value will be the mean of base_values unless new_base_value is specified. Supports both SHAP values and SHAP interaction values. Parameters ---------- base_values : list of float This is the reference value that the feature contributions start from. Use explainer.expected_value. shap_values : list of numpy.ndarray A multioutput list of SHAP matrices or SHAP cubes from explainer.shap_values() or explainer.shap_interaction_values(), respectively. row_index : int The integer index of the row to plot. **kwargs : Any Arguments to be passed on to decision_plot(). Returns ------- DecisionPlotResult or None Returns a DecisionPlotResult object if `return_objects=True`. Returns `None` otherwise (the default). z2The base_values and shap_values args expect lists.rz0The base_values arg should be a list of scalars.)rzMThe shap_values arg should be a list of two or three dimensional SHAP arrays.rzr s'"#6&BJ))^EI    -e_"e_e_Be_./e_P 6Nr