B \ < @sdZddlmZddlZddlZddlmZddlm Z ddl m Z m Z ddl mZdd lmZmZmZdd lmZdd lmZdd lmZd dlmZd dlmZdddZdddZdddZdS)z-Partial dependence plots for tree ensembles. )countN) mquantiles) cartesian)Paralleldelayed)six)maprangezip) check_array)check_is_fitted)DTYPE)_partial_dependence_tree)BaseGradientBoostingg?gffffff?dcCst|dkrtdtdd|Ds.tdg}t||dd}xlt|jdD]Z}t|d d |f}|jd|kr~|}n"tj|d|f|d|f|d d }| |qPWt ||fS) aGenerate a grid of points based on the ``percentiles of ``X``. The grid is generated by placing ``grid_resolution`` equally spaced points between the ``percentiles`` of each column of ``X``. Parameters ---------- X : ndarray The data percentiles : tuple of floats The percentiles which are used to construct the extreme values of the grid axes. grid_resolution : int The number of equally spaced points that are placed on the grid. Returns ------- grid : ndarray All data points on the grid; ``grid.shape[1] == X.shape[1]`` and ``grid.shape[0] == grid_resolution * X.shape[1]``. axes : seq of ndarray The axes with which the grid has been created. rz!percentile must be tuple of len 2css&|]}d|kodknVqdS)gg?N).0xrrBlib/python3.7/site-packages/sklearn/ensemble/partial_dependence.py 4sz_grid_from_X..z#percentile values must be in [0, 1]r)probaxisrNT)numZendpoint) len ValueErrorallrr shapenpuniquelinspaceappendr)X percentilesgrid_resolutionaxesZemp_percentilescolZuniquesrrrr _grid_from_Xs   r)c sttstdtd|dkr,|dks<|dk rD|dk rDtdtj|tjdd}tfdd|Drtd j d |dk rt |t dd}t |dd|f||\}}nD|dk st d}|jd kr|ddtjf}|jd krtd |jtj|t dd}|jd |jd ks$t jjd }jjd }tj||jd ftjdd} xLt|D]@} x8t|D],} j| | fj} t| ||j| | qpWqbW| |fS)a8Partial dependence of ``target_variables``. Partial dependence plots show the dependence between the joint values of the ``target_variables`` and the function represented by the ``gbrt``. Read more in the :ref:`User Guide `. Parameters ---------- gbrt : BaseGradientBoosting A fitted gradient boosting model. target_variables : array-like, dtype=int The target features for which the partial dependecy should be computed (size should be smaller than 3 for visual renderings). grid : array-like, shape=(n_points, len(target_variables)) The grid of ``target_variables`` values for which the partial dependecy should be evaluated (either ``grid`` or ``X`` must be specified). X : array-like, shape=(n_samples, n_features) The data on which ``gbrt`` was trained. It is used to generate a ``grid`` for the ``target_variables``. The ``grid`` comprises ``grid_resolution`` equally spaced points between the two ``percentiles``. percentiles : (low, high), default=(0.05, 0.95) The lower and upper percentile used create the extreme values for the ``grid``. Only if ``X`` is not None. grid_resolution : int, default=100 The number of equally spaced points on the ``grid``. Returns ------- pdp : array, shape=(n_classes, n_points) The partial dependence function evaluated on the ``grid``. For regression and binary classification ``n_classes==1``. axes : seq of ndarray or None The axes with which the grid has been created or None if the grid has been given. Examples -------- >>> samples = [[0, 0, 2], [1, 0, 0]] >>> labels = [0, 1] >>> from sklearn.ensemble import GradientBoostingClassifier >>> gb = GradientBoostingClassifier(random_state=0).fit(samples, labels) >>> kwargs = dict(X=samples, percentiles=(0, 1), grid_resolution=2) >>> partial_dependence(gb, [0], **kwargs) # doctest: +SKIP (array([[-4.52..., 4.52...]]), [array([ 0., 1.])]) z2gbrt has to be an instance of BaseGradientBoosting estimators_Nz"Either grid or X must be specifiedC)dtypeordercs(g|] }d|kojkn qS)r) n_features_)rfx)gbrtrr sz&partial_dependence..z#target_variables must be in [0, %d]rrzgrid must be 2d but is %ddr) isinstancerrr r Zasarrayint32ravelanyr.r rr)AssertionErrorndimZnewaxisrr*ZzerosZfloat64r Ztree_rZ learning_rate) r0Ztarget_variablesZgridr$r%r&r'Zn_trees_per_stageZ n_estimatorspdpZstagekZtreer)r0rpartial_dependenceHs@3           r:c 0 sddlm}ddlm}ddlm}ddlm}ttsBt dt dt drt jd kr|dkrvt d t j|}j||krt d t|nd}ttd d jjdkrt d| dkrddi} | dkri} dkr ddtjDntt jr fddg}x|D]}t|tjftjrV|f}y"t jfdd|Dt jd}Wntk rt dYnXdt |krd ksnt d||q6W|}g}y@x:|D]2}g}x|D]}||qW||qWWn*t k rBt d!t"|YnXt#|| dfdd|D}i}xh|D]`\}}||$||%}}t"|}|&|||f\}} t$||}t%|| }||f||<qrWd |krt j'|d ddi}!| dkr |j(f| }"n| )}"|"*t$|t"|}t+t ,t"|t-|}#g}$xFt.t/|||D]0\}}%}&\}}|"0|#||d} t"|dkr| j1|d||2f| nt"|d kst3t 4|d|d\}'}(||5t6t7t j |j8})| j9|'|(|)|!d d!d"}*| j:|'|(|)f|!|!d#|!dd$d%| | j;|*d&d!d'd(d)t<dd|%dft =d*d+d*d,}+|>| j?| j@},| A}-| jB|+dgd-|,d!d.| C|&d| D|-| jEF|d/d0d1|}.|.Gd2| jEH|.t"|dkr\t<dd|%dft =d*d+d*d,}+|>| j@| j?},| I}/| jJ|+dgd-|,d!d.| K|&d| L|/n | Kd3t"|dkr| D|d|$| q\W|"jMd4d5d*d6d7d8d9|"|$fS):a: Partial dependence plots for ``features``. The ``len(features)`` plots are arranged in a grid with ``n_cols`` columns. Two-way partial dependence plots are plotted as contour plots. Read more in the :ref:`User Guide `. Parameters ---------- gbrt : BaseGradientBoosting A fitted gradient boosting model. X : array-like, shape=(n_samples, n_features) The data on which ``gbrt`` was trained. features : seq of ints, strings, or tuples of ints or strings If seq[i] is an int or a tuple with one int value, a one-way PDP is created; if seq[i] is a tuple of two ints, a two-way PDP is created. If feature_names is specified and seq[i] is an int, seq[i] must be < len(feature_names). If seq[i] is a string, feature_names must be specified, and seq[i] must be in feature_names. feature_names : seq of str Name of each feature; feature_names[i] holds the name of the feature with index i. label : object The class label for which the PDPs should be computed. Only if gbrt is a multi-class model. Must be in ``gbrt.classes_``. n_cols : int The number of columns in the grid plot (default: 3). grid_resolution : int, default=100 The number of equally spaced points on the axes. percentiles : (low, high), default=(0.05, 0.95) The lower and upper percentile used to create the extreme values for the PDP axes. n_jobs : int or None, optional (default=None) ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context. ``-1`` means using all processors. See :term:`Glossary ` for more details. verbose : int Verbose output during PD computations. Defaults to 0. ax : Matplotlib axis object, default None An axis object onto which the plots will be drawn. line_kw : dict Dict with keywords passed to the ``matplotlib.pyplot.plot`` call. For one-way partial dependence plots. contour_kw : dict Dict with keywords passed to the ``matplotlib.pyplot.plot`` call. For two-way partial dependence plots. **fig_kw : dict Dict with keywords passed to the figure() call. Note that all keywords not recognized above will be automatically included here. Returns ------- fig : figure The Matplotlib Figure object. axs : seq of Axis objects A seq of Axis objects, one for each subplot. Examples -------- >>> from sklearn.datasets import make_friedman1 >>> from sklearn.ensemble import GradientBoostingRegressor >>> X, y = make_friedman1() >>> clf = GradientBoostingRegressor(n_estimators=10).fit(X, y) >>> fig, axs = plot_partial_dependence(clf, X, [0, (0, 1)]) #doctest: +SKIP ... rN) transforms) MaxNLocator)ScalarFormatterz2gbrt has to be an instance of BaseGradientBoostingr*classes_rz&label is not given for multi-class PDPz!label %s not in ``gbrt.classes_``r+)r,r-rz*X.shape[1] does not match gbrt.n_features_colorZgreencSsg|] }t|qSr)str)rirrrr1sz+plot_partial_dependence..cs@t|tjr.convert_featurecsg|] }|qSrr)rr/)rFrrr1#s)r,z5features must be either int, str, or tuple of int/strz)target features must be either one or twozLAll entries of features must be less than len(feature_names) = {0}, got {1}.)n_jobsverbosec3s$|]}tt|dVqdS))r$r&r%N)rr:)rfxs)r$r0r&r%rrr=sz*plot_partial_dependence..rg?r9)levelsZ linewidthscolorsg?)rKZvmaxZvminZalphaz%2.2f T)ZfmtrLZfontsizeZinlineg?g?)rg?)Z transformr@lower)ZnbinsZprune)zPartial dependenceg333333?gffffff?gffffff?g?g333333?)ZbottomtopleftrightZwspaceZhspace)NZmatplotlib.pyplotZpyplotZ matplotlibr<Zmatplotlib.tickerr=r>r2rrr hasattrr sizer?Z searchsortedrAr rr.rr ZndarraytolistnumbersZIntegralrrCZarrayr3 TypeErrorr# IndexErrorformatrrminmaxgetr"ZfigureZ get_figureclearintZceilfloatr rZ add_subplotZplotr4r6ZmeshgridZreshapelistr TZcontourZcontourfZclabelrZarangeZblended_transform_factoryZ transDataZ transAxesZget_ylimZvlinesZ set_xlabelZset_ylimZxaxisZset_major_locatorZset_powerlimitsZset_major_formatterZget_xlimZhlinesZ set_ylabelZset_xlimZsubplots_adjust)0r0r$ZfeaturesrEZlabelZn_colsr&r%rGrHZaxZline_kwZ contour_kwZfig_kwZpltr<r=r>Z label_idxZ tmp_featuresrInameslrBZ pd_resultZpdp_limr8r'Zmin_pdZmax_pdZn_fxZ old_min_pdZ old_max_pdZZ_levelZfigZn_rowsZaxsr/nameZXXZYYZZCSZdecilesZtransZylimZtick_formatterZxlimr)r$rFrEr0r&r%rplot_partial_dependencesK         "         &   &  ri)rr)NNrr) NNr;rrNrNNN) __doc__ itertoolsrrYZnumpyr Zscipy.stats.mstatsrZ utils.extmathrZ utils._joblibrrZ externalsrZexternals.six.movesr r r Zutilsr Zutils.validationr Z tree._treerZ_gradient_boostingrZgradient_boostingrr)r:rirrrrs*          0 ]