{KgzdZddlmZddlZddlmZddlmZddl m Z m Z ddl m Z dd lmZdd lmZdd lmZdd lmZdd lmZmZmZddlmZmZmZddlmZddl m!Z!m"Z"m#Z#m$Z$m%Z%ddl&m'Z'ddl(m)Z)m*Z*ddl+m,Z,m-Z-dgZ.dZ/dZ0 d-dZ1e%e!ddge!ddge!ddggddgde"e2gddgddgddge$hdge3ge#e"ddd !ge$hd"ge$hd#gd$ d%&dddd'd(d)d'd*d+d,Z4y).zBPartial dependence plots for regression and classification models.)IterableN)sparse) mquantiles) is_classifier is_regressor)RandomForestRegressor)BaseGradientBoosting)BaseHistGradientBoosting)NotFittedError)DecisionTreeRegressor)Bunch_safe_indexing check_array)_determine_key_type_get_column_indices _safe_assign)check_matplotlib_support) HasMethodsIntegralInterval StrOptionsvalidate_params) cartesian)_check_sample_weightcheck_is_fitted)_check_feature_names_get_feature_indexpartial_dependencect|trt|dk7r tdt d|Ds td|d|dk\r td|dkr tdg}t |D]\}} t jt||d }|s|jd|kr|} n`tt||d |d } t j| d| dr tdt j| d| d|d} |j| t||fS#t$r}td |d |d }~wwxYw)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. 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``, or the number of unique values in ``X[:, j]``, whichever is smaller. rz/'percentiles' must be a sequence of 2 elements.c3<K|]}d|cxkxrdkncyw)rrN).0xs j/home/alanp/www/video.onchill/myenv/lib/python3.12/site-packages/sklearn/inspection/_partial_dependence.py z_grid_from_X..Ss0KqqA{{{Ksz''percentiles' values must be in [0, 1].rrz9percentiles[0] must be strictly less than percentiles[1].z2'grid_resolution' must be strictly greater than 1.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) isinstancerlen ValueErrorall enumeratenpuniquer TypeErrorshaperallcloselinspaceappendr) X percentilesis_categoricalgrid_resolutionvaluesfeatureis_catuniquesexcr)emp_percentiless r& _grid_from_XrC)sP k8 ,K0@A0EJKK 0K0 0BCC1~Q'TUU!MNN F%^4 iiq' BCG W]]1%7D)q'21O{{?1-q/AB . ;;""# D  dE5H V f $$C wi(==    s!D99 EEEcl|j||}|jdk(r|jdd}|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_recursionndimreshape)estgridfeaturesaveraged_predictionss r&_partial_dependence_recursionrMsAbDDT8T  A% 4;;ArB cPg}g}t|r |j}n\t|dd} t|dd} |dk(r| xs| }n |dk(r| n| }|+|dk(r td|dk(r tdtd|j } |D]g} t |D]\} }t | | | | || }|j||jtj|d | i|jd }tj|j}t|r"|jd k(r|j|d }n4t!|r)|jd d k(r|d}|j|d }tj|j}t|r%|jdk(r|jdd }||fSt!|r)|jd d k(r|d}|jdd }||fS#t$r}td |d}~wwxYw)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`. predict_probaNdecision_functionautozCThe estimator has no predict_proba and no decision_function method.z*The estimator has no predict_proba method.z.The estimator has no decision_function method.)column_indexerr)r)weightsz0'estimator' parameter must be a fitted estimatorrrEr)rpredictgetattrr/copyr1rr8r2averager r5arrayTrGrHr)rIrJrKr9response_method sample_weight predictionsrLprediction_methodrPrQX_eval new_valuesivariableprede n_sampless r&_partial_dependence_bruterfsaPKCKK_d; #C)rRrPrQleft)closed>rRbrute recursion>bothrX individual) estimatorr9rKr\categorical_features feature_namesr[r:r<methodkindT)prefer_skip_nested_validationrR)g?gffffff?drX)r\rorpr[r:r<rqrrcvt|t|st|s tdt|r2t |j dt jr tdt|ds'tj|st|dt}t|r|dk7r td| d k7r| d k(r td d } | d k(r | td | dk(rD|d } n?t |tr|jd } n t |tt t"frd } nd } | d k(rqt |ttt t"fs+d} tdj%dj'| |dk(rd}|dk7rtdj%|| t)||}t+|ddk(rSt j,t j.|dr*tdj%|j0ddz t j2t5||t j6dj9} t;||}|j0d} |dgt=| z}nt j2|}|j>j@dk(r>|jB| k7rtd|jBd| d| Dcgc]}|| }}n]|j>j@dvr,|Dcgc]}tE||}}| Dcgc]}||v}}ntd |j>d!tGtI|| d"|||\}}| d k(rPtK||| |||\}}|jLd#|j0dg|Dcgc]}|j0dc}}n tO||| }|jLd#g|Dcgc]}|j0dc}}tQ|$}| d k(r||d <|S| d%k(r|d%<|S||d <|d%<|Scc}wcc}wcc}wcc}wcc}w)&a Partial dependence of ``features``. Partial dependence of a feature (or a set of features) corresponds to the average response of an estimator for each possible value of the feature. Read more in the :ref:`User Guide `. .. 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]. grid_resolution : int, default=100 The number of equally spaced points on the grid, for each target feature. 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)force_all_finitedtyperRzKThe response_method parameter is ignored for regressors and must be 'auto'.rXrkzCThe 'recursion' method only applies when 'kind' is set to 'average'rjzFThe 'recursion' method can only be applied when sample_weight is None.)GradientBoostingClassifierGradientBoostingRegressorHistGradientBoostingClassifierHistGradientBoostingRegressorr|r r z[Only the following estimators support the 'recursion' method: {}. Try using method='brute'.z, rQzUWith the 'recursion' method, the response_method must be 'decision_function'. Got {}.F) accept_sliceintzall features must be in [0, {}]rC)rxorderbzeWhen `categorical_features` is a boolean array-like, the array should be of shape (n_features,). Got z elements while `X` contains z features.)raOU)rpzXExpected `categorical_features` to be an array-like of boolean, integer, or string. Got z instead.r(rE) grid_valuesrm))rrrr/r-classes_r2ndarrayhasattrrissparserobjectr initr r r formatjoinrranylessr5asarrayrintpravelrr.rxrrsizerrCrrfrHrMr)rnr9rKr\rorpr[r:r<rqrrsupported_classes_recursionfeatures_indices n_featuresr;idxcatcategorical_features_idxrJr=rLr]val pdp_resultss r&r r [sjI ) $ Y(?PQQYJy/A/A!/Dbjj$QNOO A{ #vq'9 Kv FI?f#<    y [ U  !: T    $F  #7 8Y^^=S F   %'<>S T !FF  $(%%   + '88>II9:9  f $1O 1 1//5vo/F   ,]A> 8%8EA 66"''(A& '>EEaggajSTnUV VzzAx(s eg)M:MJ#3'7#88!zz*>?  % % * *c 1#((J6 G+0011N!l*. DTTCSC237CSNT ! ' ' , , ?0(/C#3mD/ %( .s P"P' P,P1 P6 )N)5__doc__collections.abcrnumpyr2scipyrscipy.stats.mstatsrbaserrensembler ensemble._gbr 2ensemble._hist_gradient_boosting.gradient_boostingr exceptionsr treer utilsrrrutils._indexingrrrutils._optional_dependenciesrutils._param_validationrrrrr utils.extmathrutils.validationrr _pd_utilsrr__all__rCrMrfstrtupler r#rNr&rsJH%).,/((66TTC&D?  Y%x7 v<@Y-x y) * / 0 23 4 O ,!8S1&-!-t 4&-&'UVWw$Xq$vFG<=>=>?"#'%2  b)(brN