qtj>dZddlmZddlZddlmZddlmZddl m Z m Z ddl m Z ddlmZdd lmZdd lmZmZdd lmZdd lmZmZmZdd lmZmZmZddlm Z ddl!m"Z"m#Z#m$Z$m%Z%m&Z&ddl'm(Z(ddl)m*Z*ddl+m,Z,m-Z-dgZ.dZ/dZ0 d,dZ1e&e"ddge"ddge"ddggddgde#e2gddgddgddge%hdge3ge$e#ddd ge%hd!ge%hd"ge4dgd# d$%dddd&d'd(dd&d)d* d+Z5dS)-zBPartial dependence plots for regression and classification models.)IterableN)sparse) mquantiles) is_classifier is_regressor)RandomForestRegressor)BaseGradientBoosting)BaseHistGradientBoosting)_check_feature_names_get_feature_index)DecisionTreeRegressor)Bunch_safe_indexing check_array)_determine_key_type_get_column_indices _safe_assign)check_matplotlib_support) HasMethodsIntegralInterval StrOptionsvalidate_params)_get_response_values) cartesian)_check_sample_weightcheck_is_fittedpartial_dependencec t|trt|dkrtdt d|Dstd|d|dkrtd|dkrtdd fd |D}t d |DrCd d |D}td|g}t|D]\}}||vr ||} n tj t||d} n&#t$r} td|d| d} ~ wwxYw|s| jd|kr| } nvtt||d|d} tj| d| drtdtj| d| d|d} || t'||fS)a!Generate a grid of points based on the percentiles of X. The grid is a cartesian product between the columns of ``values``. The ith column of ``values`` consists in ``grid_resolution`` equally-spaced points between the percentiles of the jth column of X. If ``grid_resolution`` is bigger than the number of unique values in the j-th column of X or if the feature is a categorical feature (by inspecting `is_categorical`) , then those unique values will be used instead. Parameters ---------- X : array-like of shape (n_samples, n_target_features) The data. percentiles : tuple of float The percentiles which are used to construct the extreme values of the grid. Must be in [0, 1]. is_categorical : list of bool For each feature, tells whether it is categorical or not. If a feature is categorical, then the values used will be the unique ones (i.e. categories) instead of the percentiles. grid_resolution : int The number of equally spaced points to be placed on the grid for each feature. custom_values: dict Mapping from column index of X to an array-like of values where the partial dependence should be calculated for that feature Returns ------- grid : ndarray of shape (n_points, n_target_features) A value for each feature at each point in the grid. ``n_points`` is always ``<= grid_resolution ** X.shape[1]``. values : list of 1d ndarrays The values with which the grid has been created. The size of each array ``values[j]`` is either ``grid_resolution``, the number of unique values in ``X[:, j]``, if j is not in ``custom_range``. If j is in ``custom_range``, then it is the length of ``custom_range[j]``. z/'percentiles' must be a sequence of 2 elements.c36K|]}d|cxkodkncVdS)rN).0xs d/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/sklearn/inspection/_partial_dependence.py z_grid_from_X..Zs600qqA{{{{{{{{000000z''percentiles' values must be in [0, 1].rr"z9percentiles[0] must be strictly less than percentiles[1].z2'grid_resolution' must be strictly greater than 1.crtd|Drtnd}tj||S)Nc3@K|]}t|tVdSN) isinstancestrr$vs r&r'z?_grid_from_X.._convert_custom_values..ds,AAQjC00AAAAAAr()dtype)anyobjectnpasarray)valuesr0s r&_convert_custom_valuesz,_grid_from_X.._convert_custom_valuesbs<AA&AAAAAKtz&....r(c.i|]\}}||Sr#r#)r$kr/r6s r& z _grid_from_X..gs+TTTdaQ..q11TTTr(c3,K|]}|jdkVdS)r"Nndimr.s r&r'z_grid_from_X..hs( 7 7116Q; 7 7 7 7 7 7r(, c3NK|] \}}|jdkd|d|jdV!dS)r"zFeature z: z dimensionsNr;)r$r8r/s r&r'z_grid_from_X..isO! ! 1v{{ 0q / /AF / / /{{{! ! r(zBThe custom grid for some features is not a one-dimensional array. axisz The column #z contains mixed data types. Finding unique categories fail due to sorting. It usually means that the column contains `np.nan` values together with `str` categories. Such use case is not yet supported in scikit-learn.N)probr@ztpercentiles are too close to each other, unable to build the grid. Please choose percentiles that are further apart.T)numendpoint)r,rlen ValueErrorallitemsr1r5join enumerater3uniquer TypeErrorshaperallcloselinspaceappendr)X percentilesis_categoricalgrid_resolution custom_values error_stringr5featureis_catr@uniquesexcemp_percentilesr6s @r& _grid_from_Xr[+sZ k8 , ,LK0@0@A0E0EJKKK 00K000 0 0DBCCC1~Q''TUUU!MNNN/// UTTTm>Q>Q>S>STTTM 7 7 4 4 6 6 7 7 777  yy! ! %++--! ! !         F%^44'' m # # )DD )N1gA$F$F$FGG   !A7AAA    q)O;;#-"1gA666[q###;q1?13EFF$2 {#A&#A&'!   d V  f $$s $E22 F<FFct|||}|jdkr|dd}|S)a} Calculate partial dependence via the recursion method. The recursion method is in particular enabled for tree-based estimators. For each `grid` value, a weighted tree traversal is performed: if a split node involves an input feature of interest, the corresponding left or right branch is followed; otherwise both branches are followed, each branch being weighted by the fraction of training samples that entered that branch. Finally, the partial dependence is given by a weighted average of all the visited leaves values. This method is more efficient in terms of speed than the `'brute'` method (:func:`~sklearn.inspection._partial_dependence._partial_dependence_brute`). However, here, the partial dependence computation is done explicitly with the `X` used during training of `est`. Parameters ---------- est : BaseEstimator A fitted estimator object implementing :term:`predict` or :term:`decision_function`. Multioutput-multiclass classifiers are not supported. Note that `'recursion'` is only supported for some tree-based estimators (namely :class:`~sklearn.ensemble.GradientBoostingClassifier`, :class:`~sklearn.ensemble.GradientBoostingRegressor`, :class:`~sklearn.ensemble.HistGradientBoostingClassifier`, :class:`~sklearn.ensemble.HistGradientBoostingRegressor`, :class:`~sklearn.tree.DecisionTreeRegressor`, :class:`~sklearn.ensemble.RandomForestRegressor`, ). grid : array-like of shape (n_points, n_target_features) The grid of feature values for which the partial dependence is calculated. Note that `n_points` is the number of points in the grid and `n_target_features` is the number of features you are doing partial dependence at. features : array-like of {int, str} The feature (e.g. `[0]`) or pair of interacting features (e.g. `[(0, 1)]`) for which the partial dependency should be computed. Returns ------- averaged_predictions : array-like of shape (n_targets, n_points) The averaged predictions for the given `grid` of features values. Note that `n_targets` is the number of targets (e.g. 1 for binary classification, `n_tasks` for multi-output regression, and `n_classes` for multiclass classification) and `n_points` is the number of points in the `grid`. r")%_compute_partial_dependence_recursionr<reshape)estgridfeaturesaveraged_predictionss r&_partial_dependence_recursionrdsGbDDT8TT A%% 4;;ArBB r(cg}g}|dkrt|rdnddg}|}|D]} t|D]\} } t|| | | t |||\} } || |t j| d||jd}t j |j }t|r"|j d kr| |d }n>t|r/|jdd kr|d }| |d }t j |j }|j d kr| d d }||fS) a&Calculate partial dependence via the brute force method. The brute method explicitly averages the predictions of an estimator over a grid of feature values. For each `grid` value, all the samples from `X` have their variables of interest replaced by that specific `grid` value. The predictions are then made and averaged across the samples. This method is slower than the `'recursion'` (:func:`~sklearn.inspection._partial_dependence._partial_dependence_recursion`) version for estimators with this second option. However, with the `'brute'` force method, the average will be done with the given `X` and not the `X` used during training, as it is done in the `'recursion'` version. Therefore the average can always accept `sample_weight` (even when the estimator was fitted without). Parameters ---------- est : BaseEstimator A fitted estimator object implementing :term:`predict`, :term:`predict_proba`, or :term:`decision_function`. Multioutput-multiclass classifiers are not supported. grid : array-like of shape (n_points, n_target_features) The grid of feature values for which the partial dependence is calculated. Note that `n_points` is the number of points in the grid and `n_target_features` is the number of features you are doing partial dependence at. features : array-like of {int, str} The feature (e.g. `[0]`) or pair of interacting features (e.g. `[(0, 1)]`) for which the partial dependency should be computed. X : array-like of shape (n_samples, n_features) `X` is used to generate values for the complement features. That is, for each value in `grid`, the method will average the prediction of each sample from `X` having that grid value for `features`. response_method : {'auto', 'predict_proba', 'decision_function'}, default='auto' Specifies whether to use :term:`predict_proba` or :term:`decision_function` as the target response. For regressors this parameter is ignored and the response is always the output of :term:`predict`. By default, :term:`predict_proba` is tried first and we revert to :term:`decision_function` if it doesn't exist. sample_weight : array-like of shape (n_samples,), default=None Sample weights are used to calculate weighted means when averaging the model output. If `None`, then samples are equally weighted. Note that `sample_weight` does not change the individual predictions. Returns ------- averaged_predictions : array-like of shape (n_targets, n_points) The averaged predictions for the given `grid` of features values. Note that `n_targets` is the number of targets (e.g. 1 for binary classification, `n_tasks` for multi-output regression, and `n_classes` for multiclass classification) and `n_points` is the number of points in the `grid`. predictions : array-like The predictions for the given `grid` of features values over the samples from `X`. For non-multioutput regression and binary classification the shape is `(n_instances, n_points)` and for multi-output regression and multiclass classification the shape is `(n_targets, n_instances, n_points)`, where `n_targets` is the number of targets (`n_tasks` for multi-output regression, and `n_classes` for multiclass classification), `n_instances` is the number of instances in `X`, and `n_points` is the number of points in the `grid`. autopredict predict_probadecision_function)column_indexer)response_methodr)r@weightsr r]r")rcopyrIrrrOr3averagerLarrayTr<r_r)r`rarbrPrk sample_weight predictionsrcX_eval new_valuesivariablepred_ n_sampless r&_partial_dependence_bruterzsPK&  %c** VIIBU0V VVXXFUU $X.. I IKAx Ax H H H H H'sFOTTTa4   ##BJt!]$S$S$STTTT I(;'')KC9[-22!)))R88 s  9 1! 4 9 9"!n !)))R88 8$899; A%% 4;;ArBB  ,,r(fitrgrhriz array-likez sparse matrix>rfrhrir"left)closed>rfbrute recursion>bothrn individual) estimatorrPrbrqcategorical_features feature_namesrkrQrSmethodkindrTT)prefer_skip_nested_validationrf)g?gffffff?drn) rqrrrkrQrSrTrrc   t|t|st|stdt|r4t |jdt jrtdt|ds+tj |st|dt}t|r|dkrtd| d kr| d krtd d } | d kr|td| dkrK|d } nFt |tr |jd } n't |tt t"frd } nd } | d krt |ttt t"fs7d} tdd| |dkrd}|dkrtd|d|t)||}t+|ddkrHt jt j|dr!td|jddz dt jt5||t jd} t;||jd}dgt=| z}nt jjdkrtdj j!dkr5j|krtdjd |d!fd"| D}nCj j!d#vrfd$Dfd%| D}ntd&j d' pi t |tDtFfr|g}tI| ||D]:\}}}|r tK||d(j j!d)vrtd*|d+;tK|| d(} fd,tM|D}tO|||||\}}| d kr`. .. warning:: For :class:`~sklearn.ensemble.GradientBoostingClassifier` and :class:`~sklearn.ensemble.GradientBoostingRegressor`, the `'recursion'` method (used by default) will not account for the `init` predictor of the boosting process. In practice, this will produce the same values as `'brute'` up to a constant offset in the target response, provided that `init` is a constant estimator (which is the default). However, if `init` is not a constant estimator, the partial dependence values are incorrect for `'recursion'` because the offset will be sample-dependent. It is preferable to use the `'brute'` method. Note that this only applies to :class:`~sklearn.ensemble.GradientBoostingClassifier` and :class:`~sklearn.ensemble.GradientBoostingRegressor`, not to :class:`~sklearn.ensemble.HistGradientBoostingClassifier` and :class:`~sklearn.ensemble.HistGradientBoostingRegressor`. Parameters ---------- estimator : BaseEstimator A fitted estimator object implementing :term:`predict`, :term:`predict_proba`, or :term:`decision_function`. Multioutput-multiclass classifiers are not supported. X : {array-like, sparse matrix or dataframe} of shape (n_samples, n_features) ``X`` is used to generate a grid of values for the target ``features`` (where the partial dependence will be evaluated), and also to generate values for the complement features when the `method` is 'brute'. features : array-like of {int, str, bool} or int or str The feature (e.g. `[0]`) or pair of interacting features (e.g. `[(0, 1)]`) for which the partial dependency should be computed. sample_weight : array-like of shape (n_samples,), default=None Sample weights are used to calculate weighted means when averaging the model output. If `None`, then samples are equally weighted. If `sample_weight` is not `None`, then `method` will be set to `'brute'`. Note that `sample_weight` is ignored for `kind='individual'`. .. versionadded:: 1.3 categorical_features : array-like of shape (n_features,) or shape (n_categorical_features,), dtype={bool, int, str}, default=None Indicates the categorical features. - `None`: no feature will be considered categorical; - boolean array-like: boolean mask of shape `(n_features,)` indicating which features are categorical. Thus, this array has the same shape has `X.shape[1]`; - integer or string array-like: integer indices or strings indicating categorical features. .. versionadded:: 1.2 feature_names : array-like of shape (n_features,), dtype=str, default=None Name of each feature; `feature_names[i]` holds the name of the feature with index `i`. By default, the name of the feature corresponds to their numerical index for NumPy array and their column name for pandas dataframe. .. versionadded:: 1.2 response_method : {'auto', 'predict_proba', 'decision_function'}, default='auto' Specifies whether to use :term:`predict_proba` or :term:`decision_function` as the target response. For regressors this parameter is ignored and the response is always the output of :term:`predict`. By default, :term:`predict_proba` is tried first and we revert to :term:`decision_function` if it doesn't exist. If ``method`` is 'recursion', the response is always the output of :term:`decision_function`. percentiles : tuple of float, default=(0.05, 0.95) The lower and upper percentile used to create the extreme values for the grid. Must be in [0, 1]. This parameter is overridden by `custom_values` if that parameter is set. grid_resolution : int, default=100 The number of equally spaced points on the grid, for each target feature. This parameter is overridden by `custom_values` if that parameter is set. custom_values : dict A dictionary mapping the index of an element of `features` to an array of values where the partial dependence should be calculated for that feature. Setting a range of values for a feature overrides `grid_resolution` and `percentiles`. See :ref:`how to use partial_dependence ` for an example of how this parameter can be used. .. versionadded:: 1.7 method : {'auto', 'recursion', 'brute'}, default='auto' The method used to calculate the averaged predictions: - `'recursion'` is only supported for some tree-based estimators (namely :class:`~sklearn.ensemble.GradientBoostingClassifier`, :class:`~sklearn.ensemble.GradientBoostingRegressor`, :class:`~sklearn.ensemble.HistGradientBoostingClassifier`, :class:`~sklearn.ensemble.HistGradientBoostingRegressor`, :class:`~sklearn.tree.DecisionTreeRegressor`, :class:`~sklearn.ensemble.RandomForestRegressor`, ) when `kind='average'`. This is more efficient in terms of speed. With this method, the target response of a classifier is always the decision function, not the predicted probabilities. Since the `'recursion'` method implicitly computes the average of the Individual Conditional Expectation (ICE) by design, it is not compatible with ICE and thus `kind` must be `'average'`. - `'brute'` is supported for any estimator, but is more computationally intensive. - `'auto'`: the `'recursion'` is used for estimators that support it, and `'brute'` is used otherwise. If `sample_weight` is not `None`, then `'brute'` is used regardless of the estimator. Please see :ref:`this note ` for differences between the `'brute'` and `'recursion'` method. kind : {'average', 'individual', 'both'}, default='average' Whether to return the partial dependence averaged across all the samples in the dataset or one value per sample or both. See Returns below. Note that the fast `method='recursion'` option is only available for `kind='average'` and `sample_weights=None`. Computing individual dependencies and doing weighted averages requires using the slower `method='brute'`. .. versionadded:: 0.24 Returns ------- predictions : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. individual : ndarray of shape (n_outputs, n_instances, len(values[0]), len(values[1]), ...) The predictions for all the points in the grid for all samples in X. This is also known as Individual Conditional Expectation (ICE). Only available when `kind='individual'` or `kind='both'`. average : ndarray of shape (n_outputs, len(values[0]), len(values[1]), ...) The predictions for all the points in the grid, averaged over all samples in X (or over the training data if `method` is 'recursion'). Only available when `kind='average'` or `kind='both'`. grid_values : seq of 1d ndarrays The values with which the grid has been created. The generated grid is a cartesian product of the arrays in `grid_values` where `len(grid_values) == len(features)`. The size of each array `grid_values[j]` is either `grid_resolution`, or the number of unique values in `X[:, j]`, whichever is smaller. .. versionadded:: 1.3 `n_outputs` corresponds to the number of classes in a multi-class setting, or to the number of tasks for multi-output regression. For classical regression and binary classification `n_outputs==1`. `n_values_feature_j` corresponds to the size `grid_values[j]`. See Also -------- PartialDependenceDisplay.from_estimator : Plot Partial Dependence. PartialDependenceDisplay : Partial Dependence visualization. Examples -------- >>> X = [[0, 0, 2], [1, 0, 0]] >>> y = [0, 1] >>> from sklearn.ensemble import GradientBoostingClassifier >>> gb = GradientBoostingClassifier(random_state=0).fit(X, y) >>> partial_dependence(gb, features=[0], X=X, percentiles=(0, 1), ... grid_resolution=2) # doctest: +SKIP (array([[-4.52, 4.52]]), [array([ 0., 1.])]) z5'estimator' must be a fitted regressor or classifier.rz3Multiclass-multioutput estimators are not supported __array__z allow-nan)ensure_all_finiter0rfzKThe response_method parameter is ignored for regressors and must be 'auto'.rnrzCThe 'recursion' method only applies when 'kind' is set to 'average'r~NzFThe 'recursion' method can only be applied when sample_weight is None.)GradientBoostingClassifierGradientBoostingRegressorHistGradientBoostingClassifierHistGradientBoostingRegressorrr rz[Only the following estimators support the 'recursion' method: {}. Try using method='brute'.r=rizRWith the 'recursion' method, the response_method must be 'decision_function'. Got .F) accept_sliceintzall features must be in [0, r"]C)r0orderzPassing an empty list (`[]`) to `categorical_features` is not supported. Use `None` instead to indicate that there are no categorical features.bzeWhen `categorical_features` is a boolean array-like, the array should be of shape (n_features,). Got z elements while `X` contains z features.c g|] }| Sr#r#)r$idxrs r& z&partial_dependence..sTTTC237TTTr()ruOUc2g|]}t|S))r)r )r$catrs r&rz&partial_dependence..s6(((#3mDDD(((r(cg|]}|vSr#r#)r$rcategorical_features_idxs r&rz&partial_dependence..s,47//r(zXExpected `categorical_features` to be an array-like of boolean, integer, or string. Got z instead.r?iuz The column a contains integer data. Partial dependence plots are not supported for integer data: this can lead to implicit rounding with NumPy arrays or even errors with newer pandas versions. Please convert numerical features to floating point dtypes ahead of time to avoid problems.cJi|]\}}|v || Sr#)get)r$indexrVrTs r&r9z&partial_dependence..sB""" E7 m # # }  )) # # #r(r]c(g|]}|jdSrrLr$vals r&rz&partial_dependence..s===scil===r(c(g|]}|jdSrrrs r&rz&partial_dependence..s - - -scil - - -r() grid_valuesr),rrrrEr,classes_r3ndarrayhasattrrissparserr2r initr r rformatrHrrr1lessrLr4rintpravelr rDsizer0rr-rziprrIr[rzr_rdr)rrPrbrqrrrkrQrSrTrrsupported_classes_recursionfeatures_indices n_featuresrR feature_idxrVrWX_subsetcustom_values_for_X_subsetrar5rcrr pdp_resultsrs `` ` @r&rr]sNI ) $ $R Y(?(?RPQQQYPJy/A!/Dbj$Q$QPNOOO A{ # #Hvq'9'9H [ G G GI ?f#<#<     y [ U  !: T     $FF  #7 8 8 Y^=S FF   %'<>S T   !FFF  $(%%     + '88>II9::99  f $ $1O 1 1 1?,;???   ,]A>> 8%888EAA 6"'(A&& ' ' OMAGAJNMMMNN NzAx((s egg)M::MJ#3'7#8#88!z*>??  $ ) )(  % *c 1 1#(J66 .+0.."... UTTTCSTTTNN ! ' , ? ?((((/((( $;KNNR,@,FRRR  "'RM(S#J'':(+,rsWHH %$$$$$))))))44444444222222555555RQQQQQQQ......<<<<<<<<<< JIIIII988888++++++JJJJJJJJ  u%u%u%p7 7 7 v<@}-}-}-}-@ Jy) * * J/ 0 0 J23 4 4 O ,!8S1&-!-t 4&-&J'U'U'UVVWw$HXq$vFFFG:<<<==>===>>?!$#''4  SSSS+*SSSr(