ó ‡ˆ\c @s/dZddlmZddlZddlZddlmZddlm Z ddl m Z m Z ddl mZdd lmZmZmZdd lmZdd lmZdd lmZd dlmZd dlmZddd„Zddddd„Zddddddddddd„ Z dS(s-Partial dependence plots for tree ensembles. iÿÿÿÿ(tcountN(t mquantilesi(t cartesian(tParalleltdelayed(tsix(tmaptrangetzip(t check_array(tcheck_is_fitted(tDTYPEi(t_partial_dependence_tree(tBaseGradientBoostinggš™™™™™©?gffffffî?idcCs t|ƒdkr!tdƒ‚ntd„|DƒƒsFtdƒ‚ng}t|d|ddƒ}x•t|jdƒD]€}tj|d d …|fƒ}|jd|kr¹|}n2tj|d|f|d|fd |d t ƒ}|j |ƒqxWt |ƒ|fS( sÿGenerate 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. is!percentile must be tuple of len 2css+|]!}d|ko dknVqdS(ggð?N((t.0tx((sBlib/python2.7/site-packages/sklearn/ensemble/partial_dependence.pys 4ss#percentile values must be in [0, 1]tprobtaxisiiNtnumtendpoint( tlent ValueErrortallRRtshapetnptuniquetlinspacetTruetappendR(tXt percentilestgrid_resolutiontaxestemp_percentilestcoltuniquesR((sBlib/python2.7/site-packages/sklearn/ensemble/partial_dependence.pyt _grid_from_Xs c Cs‰t|tƒstdƒ‚nt|dƒ|d krC|d ks[|d k rj|d k rjtdƒ‚ntj|dtjddƒjƒ}t g|D]&}d|ko¸|j kn ^q˜ƒrátd|j d ƒ‚n|d k r0t |dt ddƒ}t |d d …|f||ƒ\}}nh|d k sBt‚d }|jd krs|d d …tjf}n|jd kr˜td |jƒ‚ntj|dt ddƒ}|jd |jdksÓt‚|jjd }|jjd} tj||jdfdtjddƒ} x^t| ƒD]P} xGt|ƒD]9} |j| | fj} t| |||j| | ƒq>Wq+W| |fS( s8Partial 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.])]) s2gbrt has to be an instance of BaseGradientBoostingt estimators_s"Either grid or X must be specifiedtdtypetordertCis#target_variables must be in [0, %d]iNisgrid must be 2d but is %dd(t isinstanceR RR tNoneRtasarraytint32traveltanyt n_features_R R R$tAssertionErrortndimtnewaxisRR%tzerostfloat64Rttree_R t learning_rate(tgbrtttarget_variablestgridRRRtfxR tn_trees_per_staget n_estimatorstpdptstagetkttree((sBlib/python2.7/site-packages/sklearn/ensemble/partial_dependence.pytpartial_dependenceHs@3 09  "  iic 1 søddlj}ddlm}ddlm}ddlm}tˆtƒs]t dƒ‚nt ˆdƒt ˆdƒrðt j ˆjƒd krð|dkr¬t d ƒ‚nt jˆj|ƒ}ˆj||kröt d t|ƒƒ‚qönd }tˆd tddƒ‰ˆjˆjdkr3t dƒ‚n| dkrOidd6} n| dkrdi} nˆdkr›gtˆjƒD]}t|ƒ^q€‰n!tˆt jƒr¼ˆjƒ‰n‡fd†}g}xÌ|D]Ä}t|tjftjƒr|f}ny5t jg|D]}||ƒ^qd t jƒ}Wntk rZt dƒ‚nXdt j |ƒko{d knst dƒ‚n|j |ƒqØW|}g}yJxC|D];}g}x|D]}|j ˆ|ƒqÉW|j |ƒq¶WWn/t!k r't dj"t#ˆƒ|ƒƒ‚nXt$d|d| ƒ‡‡‡‡fd†|Dƒƒ}i}x|D]…\}}||j%ƒ||j&ƒ}}t#|ƒ} |j'| ||fƒ\}!}"t%||!ƒ}t&||"ƒ}||f|| ˆdd…|d fd+t j?d,d-d,ƒƒ},|j@| jA| jBƒ}-| jCƒ}.| jD|,d gd.d/|-dd!ƒ| jE|'d ƒ| jF|.ƒ| jGjH|d0d1d2d3ƒƒ|ƒ}/|/jIdBƒ| jGjJ|/ƒt#|ƒdkr|t>ˆdd…|dfd+t j?d,d-d,ƒƒ},|j@| jB| jAƒ}-| jKƒ}0| jL|,d gd.d/|-dd!ƒ| jM|'dƒ| jN|0ƒn | jMd6ƒt#|ƒdkr¯| jF|dƒn|&j | ƒq§W|$jOd7d8d9d:d;d,d<d=d>d?d@dAƒ|$|&fS(Cs: 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 ... iÿÿÿÿN(t transforms(t MaxNLocator(tScalarFormatters2gbrt has to be an instance of BaseGradientBoostingR%tclasses_is&label is not given for multi-class PDPs!label %s not in ``gbrt.classes_``iR&R'R(is*X.shape[1] does not match gbrt.n_features_tgreentcolorcsPt|tjƒrLyˆj|ƒ}WqLtk rHtd|ƒ‚qLXn|S(NsFeature %s not in feature_names(R)Rt string_typestindexR(R:(t feature_names(sBlib/python2.7/site-packages/sklearn/ensemble/partial_dependence.pytconvert_features  s5features must be either int, str, or tuple of int/strs)target features must be either one or twosLAll entries of features must be less than len(feature_names) = {0}, got {1}.tn_jobstverbosec 3s6|],}ttƒˆ|dˆdˆdˆƒVqdS(RRRN(RRA(Rtfxs(RR7RR(sBlib/python2.7/site-packages/sklearn/ensemble/partial_dependence.pys =sRitlevelst linewidthsgà?tcolorsR?tvmaxtvmintalphagè?tfmts%2.2ftfontsizei tinlineRgš™™™™™¹?gð?gš™™™™™©?t transformtnbinsitprunetloweriýÿÿÿisPartial dependencetbottomg333333Ã?ttopgffffffæ?tlefttrightgffffffî?twspacegš™™™™™Ù?thspaceg333333Ó?(iýÿÿÿi(Ptmatplotlib.pyplottpyplott matplotlibRBtmatplotlib.tickerRCRDR)R RR thasattrRtsizeRER*t searchsortedtstrR R R/RRtndarrayttolisttnumberstIntegralRRHtarrayR,t TypeErrorRt IndexErrortformatRRtmintmaxtgetRtfiguret get_figuretcleartinttceiltfloatRRt add_subplottplotR-R0tmeshgridtreshapetlistRtTtcontourtcontourftclabelRRtarangetblended_transform_factoryt transDatat transAxestget_ylimtvlinest set_xlabeltset_ylimtxaxistset_major_locatortset_powerlimitstset_major_formattertget_xlimthlinest set_ylabeltset_xlimtsubplots_adjust(1R7RtfeaturesRJtlabeltn_colsRRRLRMtaxtline_kwt contour_kwtfig_kwtpltRBRCRDt label_idxtiRKt tmp_featuresRNR:tnamestlt pd_resulttpdp_limR=R tmin_pdtmax_pdtn_fxt old_min_pdt old_max_pdtZ_leveltfigtn_rowstaxstnametXXtYYtZtCStdecilesttranstylimttick_formattertxlim((RRJR7RRsBlib/python2.7/site-packages/sklearn/ensemble/partial_dependence.pytplot_partial_dependence¦sÖK '     +   5 %     !     %$ ( "%5   "   5   " '(gš™™™™™©?gffffffî?(gš™™™™™©?gffffffî?(gš™™™™™©?gffffffî?(!t__doc__t itertoolsRRltnumpyRtscipy.stats.mstatsRt utils.extmathRt utils._joblibRRt externalsRtexternals.six.movesRRRtutilsR tutils.validationR t tree._treeR t_gradient_boostingR tgradient_boostingR R$R*RAR·(((sBlib/python2.7/site-packages/sklearn/ensemble/partial_dependence.pyts*  0]