a SicT"@s,dZddlmZddlmZddlZddlZddlZddlZ ddl Z ddl Z ddlmZddlmZddlmZddlmZddlmZdd lmZmZmZdd lmZdd l m!Z!m"Z"dd l#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z)dd l*m+Z+ddl,m-Z-ddl.m/Z/ddl0m1Z1m2Z2gdZ3e4dddddddZ5e1j6e2de1e"e1e5e17ej8e17ej8e17ej8dZ9GdddeZ:Gddde:Z;dIdddddd dddd!d"d"d#d$d"dd!dddddd!dddddddd"dd% d&d'Zd4j=e9e2d)e2d*d+e>_dKddddd5d!ddddd"dd6 d7d8Z?d9j=e9e2d)e2d*d+e?_dLdddd:d"dddd"dd; dj=e9e2d)e2d*d+e@_dMddddddd?d!ddd"dddddddd@dddAdBdCZAdDj=e9e2d)e2d*d+eA_dEdFZBdNdGdHZCdS)Oz1Plotting functions for visualizing distributions.)Number)partialN)to_rgba)LineCollection) VectorPlotter)ECDF HistogramKDE)Hist) FacetGrid _facet_docs) remove_na _kde_support_normalize_kwargs_check_argument_assign_default_kwargs_default_color) color_palette)husl) gaussian_kde)DocstringComponents _core_docs)displothistplotkdeplotecdfplotrugplotdistplotz multiple : {{"layer", "stack", "fill"}} Method for drawing multiple elements when semantic mapping creates subsets. Only relevant with univariate data. ao log_scale : bool or number, or pair of bools or numbers Set axis scale(s) to log. A single value sets the data axis for univariate distributions and both axes for bivariate distributions. A pair of values sets each axis independently. Numeric values are interpreted as the desired base (default 10). If `False`, defer to the existing Axes scale. zM legend : bool If False, suppress the legend for semantic variables. z cbar : bool If True, add a colorbar to annotate the color mapping in a bivariate plot. Note: Does not currently support plots with a ``hue`` variable well. zU cbar_ax : :class:`matplotlib.axes.Axes` Pre-existing axes for the colorbar. zd cbar_kws : dict Additional parameters passed to :meth:`matplotlib.figure.Figure.colorbar`. )multiple log_scalelegendcbarcbar_axcbar_kwsparams)corefacetsdistkdehistecdfcseZdZdZdddZddiZdiffdd Zed d Zed d Z ed dZ ddZ ddZ ddZ ddZddZddZd,ddZddZd d!Zd"d#Zd$d%Zd&d'Zd(d)Zd*d+ZZS)-_DistributionPlotter)xyhueweightsz@valuesz@columns)r-r/r-Ncstj||ddS)Ndata variables)super__init__)selfr2r3 __class__Q/var/www/html/django/DPS/env/lib/python3.9/site-packages/seaborn/distributions.pyr5ksz_DistributionPlotter.__init__cCstddht|jS)z$Return True if only x or y are used.r-r.boolsetr3r6r9r9r: univariatessz_DistributionPlotter.univariatecCs"|jstdddh|jS)z3Return the variable with data for univariate plots.zThis is not a univariate plotr-r.)r?AttributeError intersectionr3popr>r9r9r: data_variable|sz"_DistributionPlotter.data_variablecCstddht|j@S)z.Return True at least one of x or y is defined.r-r.r;r>r9r9r: has_xy_datasz _DistributionPlotter.has_xy_datac  Csg} g} |jjD]T} || } |||||| |} d| vrF| dd| |fi| | | qt|tjjr|j | | fd|j di|n2t t | | }|j |f|j d|jdd|dS)zDAdd artists that reflect semantic mappings and put then in a legend. facecolorcolorNtitler/)rG label_order)_hue_maplevels _artist_kwsrBappend isinstancemplaxesAxesr!r3dictzip add_legend var_levels)r6ax_objartistfillelementralpha artist_kws legend_kwshandleslabelslevelrFkws legend_datar9r9r: _add_legends,      z _DistributionPlotter._add_legendcCs|}|rtt|tjj}|dt|||dkrz9_DistributionPlotter._cmap_from_color..) rr rgb_to_huslrolinspaceintzeroscosrmrNcolorsListedColormap) r6rFrgb_hsxxZramprr9r9r:_cmap_from_colors z%_DistributionPlotter._cmap_from_colorcCs@|jr|j|jdk}n$|jddk}|jddk}||f}|S)zHFind default values for discrete hist estimation based on variable type. categoricalr-r.)r? var_typesrC)r6discreteZ discrete_xZ discrete_yr9r9r:_default_discretes z&_DistributionPlotter._default_discretecCs.dd|D}d|jvr$||fS|dvrt|jdddddf}i}ttt|jD]:\}}| dd| ddf}| |g|| |q`| }| D]l}|j|} || jd d } || jd d || <|d kr|| j| d d || <|| jd d d d|| <q|dkr&|jd} t| } |D]} t| d}|| jdd}| |}||jrt|d}t|d|d}||| }td|||}td||d |}|||d<||d<n(|d| <|d||d7<|ddgd|| <q:||fS)z?Modify the density data structure to handle multiple densities.cSsi|]\}}|t|qSr9)ro zeros_likerkvr9r9r: rz:_DistributionPlotter._resolve_multiple..r/rdNrlcolrowcolumnsaxisrWindexrrdodgeheightsnameedgeswidths )itemsr3pd DataFrameiloc enumeratemaprQrgetrjrLrgrxrtrsdivshiftfillnarTlen reset_indexr _log_scaledrCrolog10power set_index)r6curvesr baselinesZ column_groupsiZkeydZ facet_keyZcol_idxscolsZ norm_constant hue_levelsnkeyr^r*Z level_idxZlog_minZlog_maxZ log_widthnew_minnew_maxr9r9r:_resolve_multiplesJ            z&_DistributionPlotter._resolve_multipleTc Cs|tfi|}t|jddhr>|rB|j}|||nd}|j} |rfd| vrf| d} nt| } i} |j dddD]\} } | |}d|jvr| d}|}n d}t| }t | }t|dkpt |d }z|s|||d \}}Wnt jjyd}Yn0|r4d }|rtj|td d q|rFt d|}|rX||| 9}t| }tj||d| |<q| S)Nr-r.Fr0r/Tfrom_comp_datarrr0zfDataset has 0 variance; skipping density estimate. Pass `warn_singular=False` to disable this warning. stacklevelr)r)r r=r3 comp_datadropnadefine_support plot_datartr iter_dataro nan_to_numvarmathiscloselinalg LinAlgErrorwarningswarn UserWarningrtuplerrSeries)r6rC common_norm common_grid estimate_kwsr warn_singular estimatorZall_observationsall_data whole_weight densitiessub_varssub_data observationsr0 part_weightvariancesingulardensitysupportmsgrr9r9r:_compute_univariate_density-sL          z0_DistributionPlotter._compute_univariate_densityc O Ks |dur in|}| dur in| } | dur4in| } tdgd|tdgd|d|jvo| ddko| dduo| d  }|rd }t|td | d<| d d krd}|j}tfi| }i}|j }| dd}t |jddh}|r|r| ||d}nd}|r.|dur.| }nt|}|rx|dd| d|d<||j}|j|j||||dd}|jdddD]\}}t|}|j}d|jvr|d|d<|d }nt|}|r|s| ||d}|||||}||j}|d} ||| d}!||jrdtd |!| td |!} td |!}!|r||vr||}"|jr|}#n ||  }#|||#9<|!d|d| }!| |9} tj tj!|!ddtj!| ddg}$tj"||$dd }%|r |%||9}%|%||<q|#||\}}&|rL|#||d!krBdn|\}}'|d"krZd#ndtj$f}(|d"kr|j%&})|)d}!|)d} |!'|!| j(|!)f}*ng}*|rd|jvr|d$kr|d%krd&nd'}+n|rd&}+nd(}+nd}+| d)|+},g}-|jddd*D]d\}}'t|}||*d+}%t,|&|}.|-|}/d|jvrl|.|d}0n| }0|/| ||||0|,}1|d%kr8|jdkr|/j0n|/j1}2|2|%d|%d|.|%d|.fd+d,i|1}3|3D]T}4|jdkr|*|4j2j3dd<|(|4j2j4dd<n |(|4j2j3dd<|*|4j2j4dd<q|-5|3nv|d-kr|%j6d.}5t7|%d|5d|5d}6t7|%d|5d}7t7|.|.d.}8|jdkrd/}9d0}:nd/}9d1}:n2|d2kr|%d|%dd}6|%d}7|.}8d}9d}:|jdkrH|r |/j8|6|8|7fd-|9i|1};n|/j9|6|7fd3|:i|1\};|*|;j2j3dd<|(|;j2j4dd<n\|rj|/j:|6|8|7fd-|9i|1};n|/j9|7|6fd3|:i|1\};|(|;j2j3dd<|*|;j2j4dd<|-7|;|rz ||}"Wnt;yYqYn0|"j%}}?n|"|}?t<|0d| d4<|/j9|=i| \}@|>durZ|>|@j2j3dd<|?dur|?|@j2j4dd<q|d%krd5| vrt=d6d7|Dj+dd8}A|Ad>}B|Aj(|Bdf}C|Aj(|Bdf}Dt?j$}E|D]|\}}'|-|}/|/@d9|/jAjBtC|/jDE|D|Cgd|/jDE|Dgd\}F}G|jdkrJ|F}Hn|G}Ht'd:|H|E}Eq|-D]D}4|4F}I|s~|Id;9}It'|E|I}J|sd&}Kt|J|K}J|4G|Jqd|jHdur|jHn |jIjJjKd}/d<}L}M|jdkr|jL}M|jdkr|jL}L|M|/|L|Md|jv r|| r|| s.|d%k r.)dropHg?g?)Urgrr3rrrrCr rrrr=Z_define_bin_paramsrtrrjrrrrrrB _normalize_evalrto_numpyrorrmaxr MultiIndex from_arraysIndexrrinfrrminlocidxmaxrenamerrp _get_axesrIrKbarbarh sticky_edgesr-r.extendrrL fill_betweenplot fill_betweenxKeyErrorrconcatidxminrautoscale_viewfiguredpiabs transData transform get_linewidth set_linewidthaxr'rOflat capitalize_add_axis_labelsrrNpatchesPatchlinesLine2Dra)Or6rrXrWr common_binsshrinkr)kde_kwsrFr!line_kwsrplot_kwsZauto_bins_with_weightsrorientr histogramsr all_weightsZmultiple_histogramsbin_kwsrr rrrrrresrrrrZ hist_normrr*rrZ sticky_statZbin_valsZ sticky_data default_alpharYZ hist_artistsbottomr) sub_colorrZ plot_funcartistsrfinalr-r.rrrrVrZ line_argsZsticky_xZsticky_ylineZ hist_metadataZ thin_bar_idxr left_edgedefault_linewidthZpts_xZpts_yZbinwidth_pointsZ max_linewidthrZ min_linewidth default_x default_yrUr9r9r:plot_univariate_histogram{s                                                          z._DistributionPlotter.plot_univariate_histogramc ! Ks| dur in| } tfi| } t|jddhrb|j}|rf| |d|d|ddnd}g}|jddD]2\}}| |d|d|dd\}}| |qvt|jddh p|}|dur|r| ||}| dd|r|dur| ||}n| d t ttj |}nd}|dur0d }|jd ddD]*\}}|jrTq>| |d|d|ddd \}\}}|drtd |}|drtd |}| jdkr|r|t|t|9}| }d |jvr||d }||}||d<nB| dd}t|tr,t|dd}n|dur@||}||d<|sd|durd| ||}|durv||d <|s|r| ||}|durtj||}||}tdd|jD}tdd|j D}|j!|||j"fi|}|dur"g|j#j$dd<g|j#j%dd<|r@|j&j'|| |fi| |rT|j(ddd|r>|j(dddq>|j)dur~|j)n |j*j+j,d}|-|d |jvr|ri}t.t/j0j1}|j)dur|j)n|j*} |2| |dddd|idS)Nr-r.r0FTrvminrvmaxC0r/rrrcmapas_cmapcSsg|] }|qSr9 get_visiblerlr9r9r:rVrzA_DistributionPlotter.plot_bivariate_histogram..cSsg|] }|qSr9rMrOr9r9r:rWrrrr)3rgr r=r3rrdefine_bin_paramsrrrLr|rjrBr rroemptyrrrrrIrrMstrrmamasked_less_equalranyxaxis get_gridlinesyaxis pcolormeshTrr-r.r"colorbargridr)r'rOr*r,rrNr-r.ra)!r6r1rthreshpthreshpmaxrFr!r"r#r$rr5rrZ full_heightsrrZ sub_heightsZcommon_color_normrHrrZx_edgesZy_edgesrZrJr)x_gridy_gridmeshrVrUr9r9r:plot_bivariate_histograms                               z-_DistributionPlotter.plot_bivariate_histogramc  Ks |dur|dv}|rtjj} ntjj} t| | } tdgd|tt|j ddh} | rf|dvrfd}| |j } | |j |||| |} | | |\} }|dkrdnd tjf}|dkr| j| jf}ng}|r|d krd }qd }nd }| d|}|jdddD]@\}}t|}z | |}WntyBYqYn0|j}||}||}d|j vrx||d}n|}|| |d|||}d|j vr|r|j|||fi|} n|j||fi|\} || jjdd<|| jjdd<nT|r|j |||fi|} n|j||fi|\} || jjdd<|| jjdd<q|j!dur\|j!n |j"j#j$d }d}}|j dkrd}|j dkrd}|%|||d|j vr|r|rt&tj'j(} nt&tjjgg} |j!dur|j!n|j"}|)|| |d||| idS)Nrdr)rrerWr-r.TrWrrrrrrrYr/rFr ZDensity)*rNrhrir/r0rrr<r=r3rrCrrrorrrr rBrrrrrrIrKrrrr-r.rr)r'rOr*r,rr-r.ra)r6rrrrrWrFr!rr5rVsubsetsr rrZsticky_densityZsticky_supportr;rYrrrrrZ fill_fromr)r=rZrDrErUr9r9r:plot_univariate_densitys                z,_DistributionPlotter.plot_univariate_densityc ) sr| } tfi| } tjddhs,d}j}ii}}jdddD]&\}}|ddg}|d }|d|df}djvr|d}nd}t |d}z|s| |d|i\}}Wnt j jyd}Yn0|rd }|rNtj|td d qN|\}}dr t d |}dr8t d |}||f}|rZ|t|t|9}t|}|||<|||<qN|durd}ttrt |d n$t dkstd krtd|rt|fdd|D}nfdd|D}djvrPdD]0}|| vr|d}t|t| |qnzt| ddh@}|r~|s~ |} | | d<|s|s|g| d<| dd} t| t!rt"| dd} | dur| | d<dD]\}}!d|vr#|d}|r  || d<n |g| d<$|}"|r.|"j%}#n|"j&}#t|}||vrNq||}||\}}| dd}$|#|||fd||i| }%djvr|%j'd(|$|r| durin| } |"j)j*|%| |"fi| qԈj+durj+n j,j-j.d}"/|"djvrn|rni}&|r.t0t1j2j3}'nt0t1j4j5gg}'j+durPj+nj,}(6|(|'|ddd |&idS)Nr-r.Fr/Trrr0zoKDE cannot be estimated (0 variance or perfect covariance). Pass `warn_singular=False` to disable this warning.r~rrrzlevels must be in [0, 1]csi|] }|qSr9r9)rr) common_levelsr9r:rfrz?_DistributionPlotter.plot_bivariate_density..csi|]\}}||qSr9)r|)rrd)rJr6r9r:rhs)rJrz* parameter ignored when using hue mapping.rJrrKlabelrJr)7rgr r=r3rrrrrrrrrorrrrrrrrrrrMrrr  ValueErrorr|listrxrBrrSrrIrcontourfcontourrh set_labelr"r\r)r'rOr*r,rrNr-r.r/r0ra))r6rrWrJr^rFr!r"rr#r$rZ contour_kwsrrrZsupportsrrrZ min_variancer0rrrrryyrZ draw_levelsparamZcoloring_givenrJrr)Z contour_funcricsetrZrVrUr9)rgrJr6r:plot_bivariate_density s                                       z+_DistributionPlotter.plot_bivariate_densityc Kstfi|}tddd}||j|d<|jddddD]\}}|jrHq8||j}|dd} ||| d \} } |} d|jvr||d| d <| |jrt d | } t j | d <|jd kr| | f} d}n | | f} d }|j dkrt|}nd}||}|j| i| \}t|j|}d |f|dd<q8|jdur>|jn |jjjd }|j } d}}|jd krn| }|jdkr~| }||||d|jvr|rttjjgg}|dd}|jdur|jn|j}|||ddd||idS)Nrrr-r.rr/T)rrr0rrFrrr-r.rrr rYF)rrQrCrrRrrgr3rIrrorrrrrrgetattrrr)r'rOr*r+r,rrNr/r0ra)r6rr!r5rZ drawstylesrrrr0rvalsrZ plot_argsZ stat_variabletop_edger)rVrrDrErYrUr9r9r:plot_univariate_ecdfsX                 z)_DistributionPlotter.plot_univariate_ecdfc Ks|jddD]\}}||}|dd|rv|\}} d|jvrR| |d7} d|jvrh||d7}|j|| dd |jvr|d d|d dd|jvr||d|||d|jvr||d|||||d |jvr |r tt j j gg} | || d d ddiiq dS) NTrrrr-rr.rsr/crFF) rrrjmarginsr3rB_plot_single_rugr,rrNr/r0ra) r6heightexpand_marginsr!r_rrr)xmargymarg legend_artistr9r9r:plot_rug s.             z_DistributionPlotter.plot_rugc Cs||}t|}||r&td|}d|jvr@||d}nd}|dkr~t|j|j } t t |dt d|g|g} |dkrt|j |j} t t d|g|t |dg} | |ddg} |t| f| |d||j|dk|dkd dS) z*Draw a rugplot along one axis of the plot.rr/Nr-rrr.)r&r)scalexscaley)rrrorr3rItxblended_transform_factoryr% transAxes column_stackrepeattilereshapeadd_collectionrr!) r6rrr|r)r_vectorrrtransZxy_pairsZ line_segsr9r9r:r{-s4   z%_DistributionPlotter._plot_single_rug)T)__name__ __module__ __qualname__ semanticswide_structureflat_structurer5propertyr?rCrDrarKr|rrrrrFrdrfrrrxrr{ __classcell__r9r9r7r:r,ds@    #  N No;E"r,c@seZdZejdZdS)_DistributionFacetPlotter)rrN)rrrr,rr9r9r9r:rUsrrrFTrrb) r-r.r/r0rrrbinrangerrr1rrrXrWr2r)r3r4r^r_r`r"r#r$palette hue_orderhue_normrFr r!r)c %Kst|ttd}"|"j|||d| dur4t} |"j| |d|"jrv|rb|dkrZ| jn| j }#n| j }#t |#|||!}|"j s| S| dur|" } t||||| | d}$|"jr|"jf| |||| | |||||$|d |!n(|"jf| | |||||||||$d |!| S)Nr1rordernormr rb)rrrrrr) rrXrWr2rr1r)r3rFr!rr4) r1rr^r_r`rFr!r"r#r$r)r, get_semanticslocalsmap_huepltgca_attachr?rrrrrDrrQrFrd)%r2r-r.r/r0rrrrrrr1rrrXrWr2r)r3r4r^r_r`r"r#r$rrrrFr r!r)kwargspmethodrr9r9r:r^st    raJPlot univariate or bivariate histograms to show distributions of datasets. A histogram is a classic visualization tool that represents the distribution of one or more variables by counting the number of observations that fall within discrete bins. This function can normalize the statistic computed within each bin to estimate frequency, density or probability mass, and it can add a smooth curve obtained using a kernel density estimate, similar to :func:`kdeplot`. More information is provided in the :ref:`user guide `. Parameters ---------- {params.core.data} {params.core.xy} {params.core.hue} weights : vector or key in ``data`` If provided, weight the contribution of the corresponding data points towards the count in each bin by these factors. {params.hist.stat} {params.hist.bins} {params.hist.binwidth} {params.hist.binrange} discrete : bool If True, default to ``binwidth=1`` and draw the bars so that they are centered on their corresponding data points. This avoids "gaps" that may otherwise appear when using discrete (integer) data. cumulative : bool If True, plot the cumulative counts as bins increase. common_bins : bool If True, use the same bins when semantic variables produce multiple plots. If using a reference rule to determine the bins, it will be computed with the full dataset. common_norm : bool If True and using a normalized statistic, the normalization will apply over the full dataset. Otherwise, normalize each histogram independently. multiple : {{"layer", "dodge", "stack", "fill"}} Approach to resolving multiple elements when semantic mapping creates subsets. Only relevant with univariate data. element : {{"bars", "step", "poly"}} Visual representation of the histogram statistic. Only relevant with univariate data. fill : bool If True, fill in the space under the histogram. Only relevant with univariate data. shrink : number Scale the width of each bar relative to the binwidth by this factor. Only relevant with univariate data. kde : bool If True, compute a kernel density estimate to smooth the distribution and show on the plot as (one or more) line(s). Only relevant with univariate data. kde_kws : dict Parameters that control the KDE computation, as in :func:`kdeplot`. line_kws : dict Parameters that control the KDE visualization, passed to :meth:`matplotlib.axes.Axes.plot`. thresh : number or None Cells with a statistic less than or equal to this value will be transparent. Only relevant with bivariate data. pthresh : number or None Like ``thresh``, but a value in [0, 1] such that cells with aggregate counts (or other statistics, when used) up to this proportion of the total will be transparent. pmax : number or None A value in [0, 1] that sets that saturation point for the colormap at a value such that cells below constitute this proportion of the total count (or other statistic, when used). {params.dist.cbar} {params.dist.cbar_ax} {params.dist.cbar_kws} {params.core.palette} {params.core.hue_order} {params.core.hue_norm} {params.core.color} {params.dist.log_scale} {params.dist.legend} {params.core.ax} kwargs Other keyword arguments are passed to one of the following matplotlib functions: - :meth:`matplotlib.axes.Axes.bar` (univariate, element="bars") - :meth:`matplotlib.axes.Axes.fill_between` (univariate, other element, fill=True) - :meth:`matplotlib.axes.Axes.plot` (univariate, other element, fill=False) - :meth:`matplotlib.axes.Axes.pcolormesh` (bivariate) Returns ------- {returns.ax} See Also -------- {seealso.displot} {seealso.kdeplot} {seealso.rugplot} {seealso.ecdfplot} {seealso.jointplot} Notes ----- The choice of bins for computing and plotting a histogram can exert substantial influence on the insights that one is able to draw from the visualization. If the bins are too large, they may erase important features. On the other hand, bins that are too small may be dominated by random variability, obscuring the shape of the true underlying distribution. The default bin size is determined using a reference rule that depends on the sample size and variance. This works well in many cases, (i.e., with "well-behaved" data) but it fails in others. It is always a good to try different bin sizes to be sure that you are not missing something important. This function allows you to specify bins in several different ways, such as by setting the total number of bins to use, the width of each bin, or the specific locations where the bins should break. Examples -------- .. include:: ../docstrings/histplot.rst returnsseealso)r%rrscottrg?r~)r-r.r/r0rrrrFrWrrrr bw_method bw_adjustrr rJr^gridsizerrmr!r"r#r$r)c'KsLd|vrd}t||dd}|durv|rPd}|durD||}}qT||}}nd}td|d}tj|tdd |d d} | durtd | d }tj|tdd | }|d ddurtd}tj|tdd |dd}!|!dur|!rd}td|d}tj|tdd |dd}"|"durV|"} td|"d}tj|tdd |d|}t|t t d}#|#j |||d|durt }|#j|ddg|d| r|jn|j}$t|$|||}|#js|St|||||| d}%|#jr |}&|#jf| | | | ||||%d|&n(|#jf| | |||||||||%d ||S)Ndata2zD`data2` has been removed (replaced by `y`); please update your code.verticalassigning data to `y`.assigning data to `x`.2 The `vertical` parameter is deprecated; X This will become an error in seaborn v0.13.0; please update your code. rrbwzo The `bw` parameter is deprecated in favor of `bw_method` and `bw_adjust`. Setting `bw_method=z`, but please see the docs for the new parameters and update your code. This will become an error in seaborn v0.13.0. kernelz Support for alternate kernels has been removed; using Gaussian kernel. This will become an error in seaborn v0.13.0; please update your code. shade_lowestrzH `shade_lowest` has been replaced by `thresh`; setting `thresh=zY. This will become an error in seaborn v0.13.0; please update your code. shadezF `shade` is now deprecated in favor of `fill`; setting `fill=zZ`. This will become an error in seaborn v0.14.0; please update your code. n_levelsr1rnumericdatetime allowed_typesr )rrrrrmr)rrrrWrFr!rr) rrWrJr^r!rFrr"r#r$r) TypeErrorrBtextwrapdedentrrr FutureWarningr,rrrrrrrrrrDrQr?rgrfrr)'r2r-r.r/r0rrrrFrWrrrrrrrr rJr^rrrmr!r"r#r$r)rrr action_takenrrrrrrr5r9r9r:r=s                    raPlot univariate or bivariate distributions using kernel density estimation. A kernel density estimate (KDE) plot is a method for visualizing the distribution of observations in a dataset, analogous to a histogram. KDE represents the data using a continuous probability density curve in one or more dimensions. The approach is explained further in the :ref:`user guide `. Relative to a histogram, KDE can produce a plot that is less cluttered and more interpretable, especially when drawing multiple distributions. But it has the potential to introduce distortions if the underlying distribution is bounded or not smooth. Like a histogram, the quality of the representation also depends on the selection of good smoothing parameters. Parameters ---------- {params.core.data} {params.core.xy} {params.core.hue} weights : vector or key in ``data`` If provided, weight the kernel density estimation using these values. {params.core.palette} {params.core.hue_order} {params.core.hue_norm} {params.core.color} fill : bool or None If True, fill in the area under univariate density curves or between bivariate contours. If None, the default depends on ``multiple``. {params.dist.multiple} common_norm : bool If True, scale each conditional density by the number of observations such that the total area under all densities sums to 1. Otherwise, normalize each density independently. common_grid : bool If True, use the same evaluation grid for each kernel density estimate. Only relevant with univariate data. {params.kde.cumulative} {params.kde.bw_method} {params.kde.bw_adjust} warn_singular : bool If True, issue a warning when trying to estimate the density of data with zero variance. {params.dist.log_scale} levels : int or vector Number of contour levels or values to draw contours at. A vector argument must have increasing values in [0, 1]. Levels correspond to iso-proportions of the density: e.g., 20% of the probability mass will lie below the contour drawn for 0.2. Only relevant with bivariate data. thresh : number in [0, 1] Lowest iso-proportion level at which to draw a contour line. Ignored when ``levels`` is a vector. Only relevant with bivariate data. gridsize : int Number of points on each dimension of the evaluation grid. {params.kde.cut} {params.kde.clip} {params.dist.legend} {params.dist.cbar} {params.dist.cbar_ax} {params.dist.cbar_kws} {params.core.ax} kwargs Other keyword arguments are passed to one of the following matplotlib functions: - :meth:`matplotlib.axes.Axes.plot` (univariate, ``fill=False``), - :meth:`matplotlib.axes.Axes.fill_between` (univariate, ``fill=True``), - :meth:`matplotlib.axes.Axes.contour` (bivariate, ``fill=False``), - :meth:`matplotlib.axes.contourf` (bivariate, ``fill=True``). Returns ------- {returns.ax} See Also -------- {seealso.displot} {seealso.histplot} {seealso.ecdfplot} {seealso.jointplot} {seealso.violinplot} Notes ----- The *bandwidth*, or standard deviation of the smoothing kernel, is an important parameter. Misspecification of the bandwidth can produce a distorted representation of the data. Much like the choice of bin width in a histogram, an over-smoothed curve can erase true features of a distribution, while an under-smoothed curve can create false features out of random variability. The rule-of-thumb that sets the default bandwidth works best when the true distribution is smooth, unimodal, and roughly bell-shaped. It is always a good idea to check the default behavior by using ``bw_adjust`` to increase or decrease the amount of smoothing. Because the smoothing algorithm uses a Gaussian kernel, the estimated density curve can extend to values that do not make sense for a particular dataset. For example, the curve may be drawn over negative values when smoothing data that are naturally positive. The ``cut`` and ``clip`` parameters can be used to control the extent of the curve, but datasets that have many observations close to a natural boundary may be better served by a different visualization method. Similar considerations apply when a dataset is naturally discrete or "spiky" (containing many repeated observations of the same value). Kernel density estimation will always produce a smooth curve, which would be misleading in these situations. The units on the density axis are a common source of confusion. While kernel density estimation produces a probability distribution, the height of the curve at each point gives a density, not a probability. A probability can be obtained only by integrating the density across a range. The curve is normalized so that the integral over all possible values is 1, meaning that the scale of the density axis depends on the data values. Examples -------- .. include:: ../docstrings/kdeplot.rst proportion) r-r.r/r0r complementaryrrrr r!r)c Kst|ttd}|j||| d| dur4t} |j| | d| d| dd}t| j ||| | d<|j st| S|j st dt ||d}|jf|| d| | S) Nr1rrrFry(Bivariate ECDF plots are not implemented)rr)rr!)r,rrrrrrrBrrrDr?NotImplementedErrorrQrx)r2r-r.r/r0rrrrrr r!r)rrrFrr9r9r:rUs2 rarPlot empirical cumulative distribution functions. An ECDF represents the proportion or count of observations falling below each unique value in a dataset. Compared to a histogram or density plot, it has the advantage that each observation is visualized directly, meaning that there are no binning or smoothing parameters that need to be adjusted. It also aids direct comparisons between multiple distributions. A downside is that the relationship between the appearance of the plot and the basic properties of the distribution (such as its central tendency, variance, and the presence of any bimodality) may not be as intuitive. More information is provided in the :ref:`user guide `. Parameters ---------- {params.core.data} {params.core.xy} {params.core.hue} weights : vector or key in ``data`` If provided, weight the contribution of the corresponding data points towards the cumulative distribution using these values. {params.ecdf.stat} {params.ecdf.complementary} {params.core.palette} {params.core.hue_order} {params.core.hue_norm} {params.dist.log_scale} {params.dist.legend} {params.core.ax} kwargs Other keyword arguments are passed to :meth:`matplotlib.axes.Axes.plot`. Returns ------- {returns.ax} See Also -------- {seealso.displot} {seealso.histplot} {seealso.kdeplot} {seealso.rugplot} Examples -------- .. include:: ../docstrings/ecdfplot.rst g?) r-r.r/r|r}rrrr!r)c Ksv| dd} | dd} | dur>| }td}tj|tdd| dur| dkrT|}n | dkr`|}td| d }tj|tdd| d d}|dur|rd }|dur||}}q||}}nd }td |d}tj|tddd}t|ttd}|j |||d| durt } | | | d| dd}t | j||| | d<|js\| S|j||| fi| | S)Narz The `a` parameter has been replaced; use `x`, `y`, and/or `data` instead. Please update your code; This will become an error in seaborn v0.13.0. rrr-r.z= The `axis` parameter has been deprecated; use the `zl` parameter instead. Please update your code; this will become an error in seaborn v0.13.0. rrrrrr1rrFry)rBrrrrrr,rrrrrrrrrDr)r2r-r.r/r|r}rrrr!r)rrrrrrr0rrFr9r9r:rsT           raGPlot marginal distributions by drawing ticks along the x and y axes. This function is intended to complement other plots by showing the location of individual observations in an unobtrusive way. Parameters ---------- {params.core.data} {params.core.xy} {params.core.hue} height : float Proportion of axes extent covered by each rug element. Can be negative. expand_margins : bool If True, increase the axes margins by the height of the rug to avoid overlap with other elements. {params.core.palette} {params.core.hue_order} {params.core.hue_norm} legend : bool If False, do not add a legend for semantic variables. {params.core.ax} kwargs Other keyword arguments are passed to :meth:`matplotlib.collections.LineCollection` Returns ------- {returns.ax} Examples -------- .. include:: ../docstrings/rugplot.rst r*)r-r.r/rrr0kindrugrug_kwsr r!rrrrFcol_wrap row_order col_orderr|aspect facet_kwsc' Ksbt|ttd}|j| | |dtdgd|d|vr\d|}t|t| ddD].}||j vr`|j |dur`d|d|j |<q`|j j |j d }|j dd|jf}|j d }|j d }|duri}tf||||||||d |}|d krddg}nd}|j||| d|js2|S|durJ|durJd}| |d<|dkr|}i} t| tjti}!| D]\}"}#| |"|#|!|"<q|!ddur||!d<|!|d<|d||jrt||jt|jfi|nt||jt|jfi|n0|d kr|}$i} t| tjt i}!| D]\}"}#|$ |"|#|!|"<qF|!|$d<||$d<|jrt|$|j!t |j!fi|$nt|$|j"t |j"fi|$n|dkrF|}%i}!i} t| t#jt$| D]\}"}#|% |"|#|!|"<q|!|%d<||%d<|jr>t|%|j%t$|j%fi|%nt&d|r| durZi} t| |j't(d| d<|dur|| d<|j'fi| |j)|j d|j*j+d,|j d|j*j+d-d|.|/|dur:|dus|dur:t0|t1j2st12|}t1j3||j4|j4j5|jddd|_4n$d d!|j D}&|j j |&d |_4|S)"Nr1rr)r*r)r+r)zg`displot` is a figure-level function and does not accept the ax= parameter. You may wish to try {}plot.)rrr)rrr)r2rrrrrr|rr)rrrrIr!r*rrrFr+rFr-rr.)x_vary_varT) left_index right_indexcSs*i|]"\}}||dur"d|dn|qS)Nrr9rr9r9r:rszdisplot..)6rrrrrformatrrrrBr3rrrr duplicatedrr rrDrgrr r5rrrrjr?rFrdr rrfrrrrrxrrrset_axis_labelsrOr* get_xlabel get_ylabel set_titles tight_layoutrMrrmerger2 difference)'r2r-r.r/rrr0rrrr r!rrrrFrrrr|rrrrrr grid_datacol_namerow_namerrhist_kwsZestimate_defaultsrr default_valr3Zecdf_kwsZ wide_colsr9r9r:r?s                ra/ Figure-level interface for drawing distribution plots onto a FacetGrid. This function provides access to several approaches for visualizing the univariate or bivariate distribution of data, including subsets of data defined by semantic mapping and faceting across multiple subplots. The ``kind`` parameter selects the approach to use: - :func:`histplot` (with ``kind="hist"``; the default) - :func:`kdeplot` (with ``kind="kde"``) - :func:`ecdfplot` (with ``kind="ecdf"``; univariate-only) Additionally, a :func:`rugplot` can be added to any kind of plot to show individual observations. Extra keyword arguments are passed to the underlying function, so you should refer to the documentation for each to understand the complete set of options for making plots with this interface. See the :doc:`distribution plots tutorial <../tutorial/distributions>` for a more in-depth discussion of the relative strengths and weaknesses of each approach. The distinction between figure-level and axes-level functions is explained further in the :doc:`user guide <../tutorial/function_overview>`. Parameters ---------- {params.core.data} {params.core.xy} {params.core.hue} {params.facets.rowcol} kind : {{"hist", "kde", "ecdf"}} Approach for visualizing the data. Selects the underlying plotting function and determines the additional set of valid parameters. rug : bool If True, show each observation with marginal ticks (as in :func:`rugplot`). rug_kws : dict Parameters to control the appearance of the rug plot. {params.dist.log_scale} {params.dist.legend} {params.core.palette} {params.core.hue_order} {params.core.hue_norm} {params.core.color} {params.facets.col_wrap} {params.facets.rowcol_order} {params.facets.height} {params.facets.aspect} {params.facets.facet_kws} kwargs Other keyword arguments are documented with the relevant axes-level function: - :func:`histplot` (with ``kind="hist"``) - :func:`kdeplot` (with ``kind="kde"``) - :func:`ecdfplot` (with ``kind="ecdf"``) Returns ------- {returns.facetgrid} See Also -------- {seealso.histplot} {seealso.kdeplot} {seealso.rugplot} {seealso.ecdfplot} {seealso.jointplot} Examples -------- See the API documentation for the axes-level functions for more details about the breadth of options available for each plot kind. .. include:: ../docstrings/displot.rst cCst|}t|dkrdStjt|ddg}d|t|d}|dkr^tt|jStt | | |SdS)z;Calculate number of hist bins using Freedman-Diaconis rule.rrKgUUUUUU?rN) rorprsubtractreduce nanpercentilersqrtsizeceilr r)riqrrr9r9r:_freedman_diaconis_binsV s  rc!s|r|sd}nd}td|d}tj|tdd|durDt}t| }| durpt|drp|j } | durpd }|dur||}t |t }|j d kr|}t|}| p|pdu} |durin|}|durin|}|durin|}| durin| } | durH| r&|d |\}n||d \}|} ||dur|rb||d <n.|rr||d <n|r||d <nr|| d <|r |durtt|d }|dd|d| | rdnd}|d| }|j||f||d||| kr ||d<| rdnd}|r^|d| }tfi||i||d||| kr^||d<|r|d| }tfi||i||d||| kr||d<durhfdd}| dd}| dd}| dd}| dt j t jf}t||jd d }t |||||}!|||} | r>| |}} |j|| fd|i| |dkrh|| d<|r| r|"| n |#| |S)!ad DEPRECATED This function has been deprecated and will be removed in seaborn v0.14.0. It has been replaced by :func:`histplot` and :func:`displot`, two functions with a modern API and many more capabilities. For a guide to updating, please see this notebook: https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751 z;`kdeplot` (an axes-level function for kernel density plots)z2`histplot` (an axes-level function for histograms)z `distplot` is a deprecated function and will be removed in seaborn v0.14.0. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or z. For a guide to updating your code to use the new functions, please see https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751 rrNrTrrri2rYg?r horizontalrrF) orientationrFr.r-)r)rFcsj|gRS)N)pdf)r-fitr%r9r:r szdistplot..pdfz#282828rrrr~rm)ddof)$rrrrrrrr<hasattrrrorpfloatndimsqueezerrgrmean get_colorremoverrrjrBr*rrrr scotts_factorstdrr set_ylabel set_xlabel)!rrr*r)rrrr3rfit_kwsrFrZ norm_histaxlabelrir)r-Zaxes_level_suggestionrZlabel_axrArZ hist_colorrZ kde_colorZ rug_colorrZ fit_colorrrrmrr.r9rr:re s                             r)N)N)N)N)N)NNTTFNNNNNNFFNNNN)D__doc__numbersr functoolsrrrrnumpyropandasr matplotlibrNmatplotlib.pyplotpyplotrmatplotlib.transforms transformsrmatplotlib.colorsrmatplotlib.collectionsr_oldcorer _statisticsrr r Z_stats.countingr axisgridr r utilsrrrrrrpalettesrexternalrZ external.kder _docstringsrr__all__rQZ _dist_paramsfrom_nested_componentsfrom_function_paramsr5 _param_docsr,rrrrrrrrrr9r9r9r:s            !   z   ^{   z 829  P$+   ALW