U 3dY@s4dZddlmZddlZddlmZddlmZddl m Z m Z dd l m Z mZdd lmZdd lmZdd lmZdd lmZddlmZddlmZddlmZddlmZddlmZddlmZddlmZddlm Z ddl!m"Z"ddl#m$Z$dgZ%ddZ&ddZ'ddZ(dddd d!dd"d#d$dZ)dS)%zBPartial dependence plots for regression and classification models.)IterableN)sparse) mquantiles)_check_feature_names_get_feature_index) is_classifier is_regressor) cartesian) check_array)check_matplotlib_support)_safe_indexing) _safe_assign)_determine_key_type)_get_column_indices)check_is_fitted)Bunch)DecisionTreeRegressor)RandomForestRegressor)NotFittedError)BaseGradientBoosting)BaseHistGradientBoostingpartial_dependencec Cst|trt|dkrtdtdd|Ds8td|d|dkrPtd|dkr`td g}t|D]\}}tt||dd }|s|j d|kr|}nNt t||dd |dd } t | d| drtd tj | d| d|d d}| |qlt||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. 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.css&|]}d|kodknVqdS)rrN).0xrrJ/tmp/pip-unpacked-wheel-zrfo1fqw/sklearn/inspection/_partial_dependence.py Qsz_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)Zprobr ztpercentiles are too close to each other, unable to build the grid. Please choose percentiles that are further apart.T)numZendpoint) isinstancerlen ValueErrorall enumeratenpuniquershaperZallcloseZlinspaceappendr ) X percentilesis_categoricalgrid_resolutionvaluesZfeatureZis_catZuniquesr Zemp_percentilesrrr _grid_from_X's<(  r0cCs&|||}|jdkr"|dd}|S)Nr)Z%_compute_partial_dependence_recursionndimreshape)estgridfeaturesaveraged_predictionsrrr_partial_dependence_recursionws   r8c Csg}g}t|r|j}nnt|dd}t|dd} |dkrB|p>| }n|dkrN|n| }|dkr|dkrltdn|dkr~tdntd|} |D]} t|D]\} } t| | | | dqz*|| }|||tj |dd Wqt k r}ztd |W5d}~XYqXq|j d}t |j }t|rP|jd krP||d }n.t|r~|j dd kr~|d }||d }t |j }t|r|jd kr|d d }n.t|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.)Zcolumn_indexerrrz0'estimator' parameter must be a fitted estimatorrr1r)r Zpredictgetattrr$copyr&rr*r'Zmeanrr)arrayTr2r3r )r4r5r6r+response_method predictionsr7Zprediction_methodr9r:ZX_evalZ new_valuesivariablepredeZ n_samplesrrr_partial_dependence_brutesX          rFr;)g?gffffff?daverage)categorical_features feature_namesr@r,r.methodkindcs^t|t|s t|s tdt|rBt|jdtjrBtdt|dsdt |sdt |dt d}d} || krtd |d | t|r|d krtd d } || krtd |d | | dkr|dkrtdd}|d kr t|tr|jdkrd}nt|tttfrd}nd}|dkr|t|ttttfsVd} td d | |d krdd}|dkr|td |t|dddkrtt|drtd |jddtjt||tjdd} t||jd}dkrdgt| }ntjddjj dkrXj!|krDtd j!d!|d"fd#d$| D}nFjj d%krfd&d$Dfd'd$| D}ntd(jd)t"t#|| dd*|||\}}|dkrt$||| ||\}}|j%d+|jdfd,d$|D}n t&||| }|j%d2d-d$|D}| dkr6t'||d.S| d/krLt'||d0St'|||d1SdS)3aPartial 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. 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. 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'`. Computing 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 supportedZ __array__z allow-nan)Zforce_all_finitedtype)r;r9r: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 {}.rHrOzCThe 'recursion' method only applies when 'kind' is set to 'average'rNN)ZGradientBoostingClassifierZGradientBoostingRegressorZHistGradientBoostingClassifierHistGradientBoostingRegressorrPrrz[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)Z accept_sliceintzall features must be in [0, {}]rC)rMorder)r=bzeWhen `categorical_features` is a boolean array-like, the array should be of shape (n_features,). Got z elements while `X` contains z features.csg|] }|qSrrridx)rIrr sz&partial_dependence..)rBOUcsg|]}t|dqS)rJ)r)rcatrZrrrWscsg|] }|kqSrrrU)categorical_features_idxrrrWszXExpected `categorical_features` to be an array-like of boolean, integer, or string. Got z instead.rr1cSsg|]}|jdqSrr)rvalrrrrWscSsg|]}|jdqSr]r^r_rrrrW$s)rHr/ individual)rar/)rHrar/)r1)(rr r r$r"Zclasses_r'Zndarrayhasattrrissparser objectformatjoinrinitrrrranyZlessr)ZasarrayrZint32Zravelrr#r>rMrLsizer0rrFr3r8r)Z estimatorr+r6rIrJr@r,r.rKrLZaccepted_responsesZaccepted_methodsZsupported_classes_recursionZfeatures_indicesZ n_featuresr-r5r/r7rAr)rIr\rJrrs 4                      )*__doc__collections.abcrZnumpyr'ZscipyrZscipy.stats.mstatsrZ _pd_utilsrrbaser r Z utils.extmathr utilsr r rrrrZutils.validationrrtreerZensembler exceptionsrZ ensemble._gbrZ2ensemble._hist_gradient_boosting.gradient_boostingr__all__r0r8rFrrrrrsB                 P [