o tBhM@sdZddlmZddlZddlmZddlmZddl m Z m Z ddl m Z dd lmZdd lmZdd lmZdd lmZdd lmZddlmZddlmZddlmZddlmZddlmZddlmZddlm Z dgZ!ddZ"ddZ#ddZ$dddddd d!dZ%dS)"zBPartial dependence plots for regression and classification models.)IterableN)sparse) mquantiles) is_classifier is_regressor) cartesian) check_array)check_matplotlib_support)_safe_indexing)_determine_key_type)_get_column_indices)check_is_fitted)Bunch)DecisionTreeRegressor)RandomForestRegressor)NotFittedError)BaseGradientBoosting)BaseHistGradientBoostingpartial_dependencecCst|tr t|dkrtdtdd|Dstd|d|dkr(td|dkr0td g}t|jdD]B}tt ||dd }|jd|krO|}n't t ||dd |dd }t |d|dritd tj |d|d|d d}| |q9t||fS)aGenerate 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 jth column of X, then those unique values will be used instead. Parameters ---------- X : ndarray, shape (n_samples, n_target_features) The data. percentiles : tuple of floats The percentiles which are used to construct the extreme values of the grid. Must be in [0, 1]. grid_resolution : int The number of equally spaced points to be placed on the grid for each feature. Returns ------- grid : ndarray, 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.css(|]}d|ko dknVqdS)rN).0xrr}/var/www/html/riverr-enterprise-integrations-main/venv/lib/python3.10/site-packages/sklearn/inspection/_partial_dependence.py Hs&z_grid_from_X..z''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.axis)probrztpercentiles are too close to each other, unable to build the grid. Please choose percentiles that are further apart.T)numendpoint) isinstancerlen ValueErrorallrangeshapenpuniquer rallcloselinspaceappendr)X percentilesgrid_resolutionvaluesfeatureuniquesremp_percentilesrrr _grid_from_X%s8!  r3cCs&|||}|jdkr|dd}|S)Nr)%_compute_partial_dependence_recursionndimreshape)estgridfeaturesaveraged_predictionsrrr_partial_dependence_recursionls   r<c Csg}g}t|r |j}n5t|dd}t|dd} |dkr!|p| }n|dkr'|n| }|durA|dkr5td|dkr=tdtd|} |D]L} t|D]\} } t| drb| | | jdd| f<qM| | | dd| f<qMz|| }|||t j |dd WqGt y}ztd |d}~ww|j d}t |j}t|r|jd kr||d }nt|r|j dd kr|d }||d }t |j}t|r|jd kr|d d }||fSt|r|j dd kr|d }|d d }||fS)N predict_probadecision_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.ilocrrz0'estimator' parameter must be a fitted estimatorrr4r)rpredictgetattrr#copy enumeratehasattrr@r+r'meanrr&arrayTr6r7r)r8r9r:r,response_method predictionsr;prediction_methodr=r>X_eval new_valuesivariableprede n_samplesrrr_partial_dependence_brutevsb            rSr?)g?gffffff?daverage)rIr-r.methodkindcCst|t|st|stdt|r!t|jdtjr!tdt|ds2t |s2t |dt d}d}||vrCtd |d |t|rO|d krOtd d } || vr`td |d | |dkrn|dkrltdd}|d krt|tr|jdurd}n t|tttfrd}nd}|dkrt|ttttfsd} td d | |d krd}|dkrtd |t|dddkrtt|drtd |jddtjt||tjdd} tt|| dd||\} } |dkrt|| | ||\}}|jd|jdgd d!| DR}nt || | }|jdgd"d!| DR}|dkr/t!|| d#S|d$kr:t!|| d%St!||| d&S)'aGPartial 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 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} The feature (e.g. `[0]`) or pair of interacting features (e.g. `[(0, 1)]`) for which the partial dependency should be computed. 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. 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 line per sample or both. See Returns below. Note that the fast `method='recursion'` option is only available for `kind='average'`. Plotting individual dependencies requires using the slower `method='brute'` option. .. 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) 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='both'``. 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 ``values``. ``len(values) == len(features)``. The size of each array ``values[j]`` is either ``grid_resolution``, or the number of unique values in ``X[:, j]``, whichever is smaller. ``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 ``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_finitedtype)r?r=r>zEresponse_method {} is invalid. Accepted response_method names are {}.z, r?zKThe response_method parameter is ignored for regressors and must be 'auto'.)brute recursionr?z3method {} is invalid. Accepted method names are {}.rUr\zCThe 'recursion' method only applies when 'kind' is set to 'average'r[N)GradientBoostingClassifierGradientBoostingRegressorHistGradientBoostingClassifierHistGradientBoostingRegressorr`rrz[Only the following estimators support the 'recursion' method: {}. Try using method='brute'.r>zUWith the 'recursion' method, the response_method must be 'decision_function'. Got {}.F) accept_sliceintzall features must be in [0, {}]rC)rZorderrr4cSg|]}|jdqSrr&rvalrrr z&partial_dependence..cSrerfrgrhrrrrjrk)rUr/ individual)rlr/)rUrlr/)"rrrr#r!classes_r'ndarrayrErissparser objectformatjoinrinitrrrr anylessr&asarrayr int32ravelr3r rSr7r<r) estimatorr,r:rIr-r.rVrWaccepted_responsesaccepted_methodssupported_classes_recursionfeatures_indicesr9r/r;rJrrrrs             )&__doc__collections.abcrnumpyr'scipyrscipy.stats.mstatsrbaserr utils.extmathrutilsr r r r r utils.validationrrtreerensembler exceptionsr ensemble._gbr2ensemble._hist_gradient_boosting.gradient_boostingr__all__r3r<rSrrrrrs<                G ^