U Ùf/ã@sŠddlmZddlZddlZzddlmZddlZWne k rRe  d¡YnXddl m Z ddl m Z ddlmZmZddd„ZdS)é)ÚdivisionNzmatplotlib could not be loaded!é)Úlabels)Úcolorsé)Ú convert_nameÚapproximate_interactionsÚautoú#1E88E5ú#333333éTc2 s( |dkrtj}|s8||krdnd}tj|d}| ¡}n| ¡}tt|ƒƒ d¡rf|dkr`|j }|j }tt|ƒƒ d¡rŽ|dkr†|j }|j }n |dkrš|}|dkrºdd„t |j dƒDƒ}t |j ƒdkrÚt |t |ƒd¡}t |j ƒdkrút |t |ƒd¡}t|||ƒ}t |j ƒd krît |ƒd krît|d ||ƒ}t|d||ƒ}||krf|dd…|dd…f}n|dd…|dd…fd }t|||||||d | |d ||kr¾| td||¡n| td||||f¡|rêt ¡dS|j d |j d ks tdƒ‚|j d|j dks*tdƒ‚t |j d ¡}tj |¡|||f tj¡}|||f}|||f}t|d ƒtkr¸i‰t t |ƒƒD]}||ˆ||<q”tˆ ¡ƒ}t|ƒtkrÌ|g}||}|dkrît|||ƒd }t|||ƒ}d }d}|dk r0|dd…|f}|dd…|f} t | tj¡d¡}!t | tj¡d¡}"t| d ƒtkr i‰t t |ƒƒD]}||ˆ| |<qvtˆ ¡ƒ}#d}n.|!dd krÎ|"dd krÎ|"|!dkrÎd}|r0|!|"kr0t  | tj¡¡}!t !| tj¡¡}"t "|!|"t#|"|!d ƒ¡}$t$j %|$|j&d¡}| d krÔ| dkrHd} | '¡}%t(|%d tƒr||% tj¡}%|%t )|%¡}%t *|%¡}%t |%ƒd krÔt +t ,t -|%¡¡¡}&| |&}'|tjj.t |ƒd|'|'d 7}t )|¡}(t /|(¡})|dk r€|||f tj¡}*|* '¡}+|!|"d|+t )|*¡<|"|*|+|"k<|!|*|+|!k<|j0||)||)| d |*|)|| |!|"|t |ƒdkd },|, 1|*|)¡n |j0||| d || t |ƒdkd},||kr |dk r t| d ƒtkr ‡fdd„|#Dƒ}-t |-ƒd kr|-d d8<|-dd7<tj2|,|-d}.|. 3|#¡n t 2|,¡}.|.j4||dd|.j5j6d d!|r^|.j5j6d d"|. 7d¡|.j8 9d ¡|.j5 :¡ ;|j< =¡¡}/|.j5 >|/j?d#d$¡| dk s´|dk rt| ƒtkræ|  @d%¡ræt |t| d d&…ƒ¡} t|ƒtkr| @d%¡rt |t|d d&…ƒ¡}| dks2| t  |¡krNt  |¡|t  |¡d$} |dksh|t !|¡kr„t !|¡t !|¡| d$}| A| |¡| B¡}0|dk rè|j0|0d t C|( D¡¡||(dd |+|(|| |!|"d' },|, 1|*|(¡n,|j0|0d t C|( D¡¡||(dd || d(| A|0¡|jE||dd)|jtd*||dd)| dk r`|jF| |dd)|jG Hd+¡|jI Hd,¡|jJd- 9d ¡|jJd. 9d ¡|j6||d d/|jJ  ¡D]}1|1 K|¡q²t|d ƒtkrö|jL‡fd0d„|Dƒ|d1d d2| r$tM N¡tM Od3tP¡t ¡W5QRXdS)4a Create a SHAP dependence plot, colored by an interaction feature. Plots the value of the feature on the x-axis and the SHAP value of the same feature on the y-axis. This shows how the model depends on the given feature, and is like a richer extenstion of the classical parital dependence plots. Vertical dispersion of the data points represents interaction effects. Grey ticks along the y-axis are data points where the feature's value was NaN. Parameters ---------- ind : int or string If this is an int it is the index of the feature to plot. If this is a string it is either the name of the feature to plot, or it can have the form "rank(int)" to specify the feature with that rank (ordered by mean absolute SHAP value over all the samples). shap_values : numpy.array Matrix of SHAP values (# samples x # features). features : numpy.array or pandas.DataFrame Matrix of feature values (# samples x # features). feature_names : list Names of the features (length # features). display_features : numpy.array or pandas.DataFrame Matrix of feature values for visual display (such as strings instead of coded values). interaction_index : "auto", None, int, or string The index of the feature used to color the plot. The name of a feature can also be passed as a string. If "auto" then shap.common.approximate_interactions is used to pick what seems to be the strongest interaction (note that to find to true stongest interaction you need to compute the SHAP interaction values). x_jitter : float (0 - 1) Adds random jitter to feature values. May increase plot readability when feature is discrete. alpha : float The transparency of the data points (between 0 and 1). This can be useful to the show density of the data points when using a large dataset. xmin : float or string Represents the lower bound of the plot's x-axis. It can be a string of the format "percentile(float)" to denote that percentile of the feature's value used on the x-axis. xmax : float or string Represents the upper bound of the plot's x-axis. It can be a string of the format "percentile(float)" to denote that percentile of the feature's value used on the x-axis. ax : matplotlib Axes object Optionally specify an existing matplotlib Axes object, into which the plot will be placed. In this case we do not create a Figure, otherwise we do. N)g@é)ér )Úfigsizez'pandas.core.frame.DataFrame'>cSsg|]}tdt|ƒ‘qS)ZFEATURE)rÚstr)Ú.0Úi©rúcsz#dependence_plot..rérrF)Ú feature_namesÚinteraction_indexÚdisplay_featuresÚaxÚshowÚxminÚxmaxZ MAIN_EFFECTZINTERACTION_EFFECTzF'shap_values' and 'features' values must have the same number of rows!zA'shap_values' must have the same number of columns as 'features'!r r é_Té )Úsizeg@iô) ÚsÚ linewidthÚcÚcmapÚalphaÚvminÚvmaxZnormÚ rasterized)r!r"Úcolorr%r(csg|] }ˆ|‘qSrr©rÚn)Ú cname_maprrrÝsgÐ?)Zticksé é )Ú labelsize)Úlengthgffffffæ?éZ percentileéÿÿÿÿ)Úmarkerr"r#r$r%r&r')r3r"r)r%)r)ÚfontsizeZ VALUE_FORÚbottomÚleftÚrightÚtop)r)Z labelcolorr/csg|] }ˆ|‘qSrrr*)Úname_maprrrsÚvertical)Zrotationr4Úignore)QrZred_blueÚplZfigureZgcaZ get_figurerÚtypeÚendswithÚcolumnsÚvaluesÚrangeÚshapeÚlenÚnpZreshaperÚdependence_plotZ set_ylabelrrÚAssertionErrorZarangeÚrandomÚshuffleZastypeZfloat64ÚlistÚkeysrZ nanpercentileÚfloatZnanminZnanmaxZlinspaceÚintÚ matplotlibZ BoundaryNormÚNÚcopyÚ isinstanceÚisnanÚuniqueÚminÚdiffÚsortZranfÚinvertZscatterZ set_arrayZcolorbarZset_ticklabelsZ set_labelrZ tick_paramsZ set_alphaÚoutlineZ set_visibleZget_window_extentZ transformedZdpi_scale_transÚinvertedZ set_aspectÚheightÚ startswithZset_xlimZget_xlimZonesÚsumZ set_xlabelÚ set_titleZxaxisZset_ticks_positionZyaxisZspinesZ set_edgecolorZ set_xticksÚwarningsÚcatch_warningsÚ simplefilterÚRuntimeWarning)2ÚindZ shap_valuesÚfeaturesrrrr)Z axis_colorr$Zdot_sizeZx_jitterr%ÚtitlerrrrrZfigZind1Zind2Zproj_shap_valuesZoindsZxvZxdr!rZxnamesÚnameZcategorical_interactionZ color_normZcvÚcdZclowZchighZcnamesZboundsZxvalsZ smallest_diffZ jitter_amountZxv_nanZ xv_notnanZcvalsZ cvals_impÚpZtick_positionsÚcbZbboxZxlimZspiner)r,r9rrEs†<    ý ÿÿ        *    "      ý ÿ      ýþ       rE)NNr r r Nr rrNNNNT)Ú __future__rÚnumpyrDr]Zmatplotlib.pyplotZpyplotr<rMÚ ImportErrorÚwarnÚrrÚcommonrrrErrrrÚs2      ý