ó —W[c@ sèdZddlmZddlZddlmZddlZddl Z ddl j Z ddljZddlmZddlZddlmZddlmZyddljjZeZWnek rÙeZnXdd l m!Z!m"Z"dd l#m$Z$m%Z%m&Z&m'Z'd d d gZ(d„Z)deeeddddddeedddd„Z+ed„Z,ed„Z-d„Z.d„Z/d„Z0d„Z1deedddddeeeedddd„Z2dddd„Z3dS(s1Plotting functions for visualizing distributions.iÿÿÿÿ(tdivisionN(tstats(tLineCollection(t LooseVersion(t string_typesi(tiqrt _kde_support(t color_palettet light_palettet dark_palettet blend_palettetdistplottkdeplottrugplotcC stj|ƒ}t|ƒdkr%dSdt|ƒt|ƒd}|dkrettj|jƒƒSttj|jƒ|j ƒ|ƒƒSdS(s;Calculate number of hist bins using Freedman-Diaconis rule.iiiiNgUUUUUUÕ?( tnptasarraytlenRtinttsqrttsizetceiltmaxtmin(tath((s4lib/python2.7/site-packages/seaborn/distributions.pyt_freedman_diaconis_binss c  sœ|dkrtjƒ}nt| ƒ}| dkrct|dƒrc|j} | dk rct}qcntj|ƒ}|j dkr|j ƒ}n| p¥|p¥ˆdk } |dkrÀt ƒ}n|dkrØt ƒ}n|dkrðt ƒ}n| dkrt ƒ} n| dkrl| r8|j d|j ƒƒ\}n|j |j ƒdƒ\}|jƒ} |jƒn|dk rÇ|r‹||d>> import seaborn as sns, numpy as np >>> sns.set(); np.random.seed(0) >>> x = np.random.randn(100) >>> ax = sns.distplot(x) Use Pandas objects to get an informative axis label: .. plot:: :context: close-figs >>> import pandas as pd >>> x = pd.Series(x, name="x variable") >>> ax = sns.distplot(x) Plot the distribution with a kernel density estimate and rug plot: .. plot:: :context: close-figs >>> ax = sns.distplot(x, rug=True, hist=False) Plot the distribution with a histogram and maximum likelihood gaussian distribution fit: .. plot:: :context: close-figs >>> from scipy.stats import norm >>> ax = sns.distplot(x, fit=norm, kde=False) Plot the distribution on the vertical axis: .. plot:: :context: close-figs >>> ax = sns.distplot(x, vertical=True) Change the color of all the plot elements: .. plot:: :context: close-figs >>> sns.set_color_codes() >>> ax = sns.distplot(x, color="y") Pass specific parameters to the underlying plot functions: .. plot:: :context: close-figs >>> ax = sns.distplot(x, rug=True, rug_kws={"color": "g"}, ... kde_kws={"color": "k", "lw": 3, "label": "KDE"}, ... hist_kws={"histtype": "step", "linewidth": 3, ... "alpha": 1, "color": "g"}) tnameiitlabeli2talphagš™™™™™Ù?s2.2tnormedtdensityt horizontaltverticaltcolort orientationtaxtytxtaxisc sˆj|ˆŒS(N(tpdf(R%(tfittparams(s4lib/python2.7/site-packages/seaborn/distributions.pyR'ôss#282828tgridsizeiÈtcutitcliptddofN(#tNonetplttgcatboolthasattrRtTrueRRtndimtsqueezetdicttplottmeant get_colortremoveRRt setdefaultRtmplt __version__tpopthistR R tinfRt gaussian_kdet scotts_factortstdRR(t set_ylabelt set_xlabel(RtbinsR?tkdetrugR(thist_kwstkde_kwstrug_kwstfit_kwsR!R t norm_histtaxlabelRR#tlabel_axtlineR"t hist_colort kde_colort rug_colorR&R't fit_colorR*R+R,tbwR%R$((R(R)s4lib/python2.7/site-packages/seaborn/distributions.pyR *sœ{                          %  c  K sÂ|dkr"tj tjf}ntrRt||||||d| ƒ\} } n^|dkr}d}d}tj|tƒn| r’tdƒ‚nt |||||ƒ\} } tj tj tj | ƒ| fddƒ} |rñ| | } } n| j ddƒ}|dkr*t|dƒr*|j}n|dk o9|}|dkrNd n|}| j d dƒ}| j| | | \}|jƒ}|jƒ| j d dƒ|dkr¶|n|}| j| | d |d|| td |d | jd d ƒd| jdtƒd| jddƒƒ}|r^|rE| j| d| |q^| j| d| |n|rz| jdddƒn| jdddƒ| jƒ\}}|r¾|r¾| jddƒn| S(s=Plot a univariate kernel density estimate on one of the axes.t cumulativetgaus-Kernel other than `gau` requires statsmodels.saCumulative distributions are currentlyonly implemented in statsmodels.Please install statsmodels.R&iRRt _nolegend_t facecolorR!RgÐ?tclip_ontzorderitautotloctbestN(R.RR@t_has_statsmodelst_statsmodels_univariate_kdetwarningstwarnt UserWarningt ImportErrort_scipy_univariate_kdetamaxtc_t zeros_likeR>R2RR7R9R:R6tgetR3t fill_betweenxt fill_betweentset_xlimtset_ylimtget_legend_handles_labelstlegend(tdatatshadeR tkernelRUR*R+R,RoR#RVtkwargsR%R$tmsgRRYRPR!t shade_kwsthandlestlabels((s4lib/python2.7/site-packages/seaborn/distributions.pyt_univariate_kdeplotsX    +    c C sy|dk}tj|ƒ}|j|||d|d|d|ƒ|r\|j|j} } n|j|j} } | | fS(s?Compute a univariate kernel density estimate using statsmodels.RWR*R+R,(tsmnpt KDEUnivariateR(tsupporttcdfR( RpRrRUR*R+R,RVtfftRGtgridR$((s4lib/python2.7/site-packages/seaborn/distributions.pyR`^s %c C sÜytj|d|ƒ}WnEtk r`tj|ƒ}|dkrad}tj|tƒqanXt|tƒr®|dkr‚dn|}t|d|ƒƒt j |ƒ}nt |||||ƒ}||ƒ}||fS(s9Compute a univariate kernel density estimate using scipy.t bw_methodtscottsMIgnoring bandwidth choice, please upgrade scipy to use a different bandwidth.tscottss %s_factor( RRAt TypeErrorRaRbRct isinstanceRtgetattrRRCR( RpRUR*R+R,RGRtR~R$((s4lib/python2.7/site-packages/seaborn/distributions.pyReks  & cK s0|dkr5tj tjftj tjfg}n$tj|ƒdkrY||g}ntr†t||||||ƒ\}}}n$t||||||ƒ\}}}|jddƒ}| jggƒ\}|j ƒ}|j ƒ|jd|ƒ}|jddƒ}|dkrG|r2t |dt ƒ}qGt |dt ƒ}nt|tƒrº|jdƒr¥dg}|jt|jdd ƒd ƒƒt|dt ƒ}qºtjj|ƒ}n|jd dƒ}||d<|rå| jn| j}||||||}|r*| r*|jd jd ƒn||d<| rn| dkrLin| } | jj|| | | nt|d ƒr–| r–| j|j ƒnt|d ƒr¾| r¾| j!|j ƒn|dk r,|dkrâ|dƒn|}|r | j"ggd|d |ƒq,| jggd|d |ƒn| S(s6Plot a joint KDE estimate as a bivariate contour plot.itn_levelsi R!tcmaptas_cmapt_ds#333333t_riRiRgffffffî?N(#R.RR@R4R_t_statsmodels_bivariate_kdet_scipy_bivariate_kdeR>R7R9R:RR3R RƒRtendswithtextendRtreplaceR R<tcmtget_cmaptcontourftcontourt collectionst set_alphatfiguretcolorbarR2RERRDRk(R%R$tfilledt fill_lowestRrRUR*R+R,RNtcbartcbar_axtcbar_kwsR#RstxxtyytzR…tscoutt default_colorR!R†tpalRt contour_functcsett legend_color((s4lib/python2.7/site-packages/seaborn/distributions.pyt_bivariate_kdeplot}sV )'$    "    cC sYt|tƒrLttjd|ƒ}||ƒ}||ƒ}||g}ntj|ƒrj||g}nt|tjƒrˆ|j }nt|tjƒr¦|j }ntj ||gd|ƒ} t || j d|||dƒ} t || j d|||dƒ} tj | | ƒ\} } | j| jƒ| jƒgƒj| jƒ}| | |fS(s*Compute a bivariate kde using statsmodels.tbw_tccii(RƒRR„Ryt bandwidthsRtisscalartpdtSeriestvaluestKDEMultivariateRRUtmeshgridR'traveltreshapetshape(R%R$RUR*R+R,tbw_functx_bwty_bwRGt x_supportt y_supportRœRRž((s4lib/python2.7/site-packages/seaborn/distributions.pyRŠÀs"    ##-cC stj||f}tj|jd|ƒ}|jddddƒ}t|tƒr©|dkrddn|}t|d|ƒƒ|d} t|d|ƒƒ|d} n1tj |ƒrÈ||} } nd } t | ƒ‚t |d d …df| |||dƒ} t |d d …df| |||dƒ} tj | | ƒ\}}||j ƒ|j ƒgƒj|jƒ}|||fS( s$Compute a bivariate kde using scipy.RR&iR-iR€Rs %s_factorsoCannot specify a different bandwidth for each dimension with the scipy backend. You should install statsmodels.N(RRgRRAtTRCRƒRR„R©t ValueErrorRR®R¯R°R±(R%R$RUR*R+R,RpRGtdata_stdtbw_xtbw_yRtRµR¶RœRRž((s4lib/python2.7/site-packages/seaborn/distributions.pyR‹×s ! ,,*RWR€idicK s3|dkrtjƒ}nt|tƒr<tj|ƒ}nt|ƒdkrR|S|jtj ƒ}|dk r¦t|tƒr‘tj|ƒ}n|jtj ƒ}nt }t }t|tj ƒr÷tj |ƒdkr÷t }t }|j\}}nt|tjƒretj |ƒdkret }t }|jdd…dfj}|jdd…dfj}n!|dk r†t }|}|}n|r¥d}tj|tƒn|rÀ| rÀtdƒ‚n|rÿt|||| |||||| | | |||}n0t||||||||| |d| | }|S(sÎFit and plot a univariate or bivariate kernel density estimate. Parameters ---------- data : 1d array-like Input data. data2: 1d array-like, optional Second input data. If present, a bivariate KDE will be estimated. shade : bool, optional If True, shade in the area under the KDE curve (or draw with filled contours when data is bivariate). vertical : bool, optional If True, density is on x-axis. kernel : {'gau' | 'cos' | 'biw' | 'epa' | 'tri' | 'triw' }, optional Code for shape of kernel to fit with. Bivariate KDE can only use gaussian kernel. bw : {'scott' | 'silverman' | scalar | pair of scalars }, optional Name of reference method to determine kernel size, scalar factor, or scalar for each dimension of the bivariate plot. Note that the underlying computational libraries have different interperetations for this parameter: ``statsmodels`` uses it directly, but ``scipy`` treats it as a scaling factor for the standard deviation of the data. gridsize : int, optional Number of discrete points in the evaluation grid. cut : scalar, optional Draw the estimate to cut * bw from the extreme data points. clip : pair of scalars, or pair of pair of scalars, optional Lower and upper bounds for datapoints used to fit KDE. Can provide a pair of (low, high) bounds for bivariate plots. legend : bool, optional If True, add a legend or label the axes when possible. cumulative : bool, optional If True, draw the cumulative distribution estimated by the kde. shade_lowest : bool, optional If True, shade the lowest contour of a bivariate KDE plot. Not relevant when drawing a univariate plot or when ``shade=False``. Setting this to ``False`` can be useful when you want multiple densities on the same Axes. cbar : bool, optional If True and drawing a bivariate KDE plot, add a colorbar. cbar_ax : matplotlib axes, optional Existing axes to draw the colorbar onto, otherwise space is taken from the main axes. cbar_kws : dict, optional Keyword arguments for ``fig.colorbar()``. ax : matplotlib axes, optional Axes to plot on, otherwise uses current axes. kwargs : key, value pairings Other keyword arguments are passed to ``plt.plot()`` or ``plt.contour{f}`` depending on whether a univariate or bivariate plot is being drawn. Returns ------- ax : matplotlib Axes Axes with plot. See Also -------- distplot: Flexibly plot a univariate distribution of observations. jointplot: Plot a joint dataset with bivariate and marginal distributions. Examples -------- Plot a basic univariate density: .. plot:: :context: close-figs >>> import numpy as np; np.random.seed(10) >>> import seaborn as sns; sns.set(color_codes=True) >>> mean, cov = [0, 2], [(1, .5), (.5, 1)] >>> x, y = np.random.multivariate_normal(mean, cov, size=50).T >>> ax = sns.kdeplot(x) Shade under the density curve and use a different color: .. plot:: :context: close-figs >>> ax = sns.kdeplot(x, shade=True, color="r") Plot a bivariate density: .. plot:: :context: close-figs >>> ax = sns.kdeplot(x, y) Use filled contours: .. plot:: :context: close-figs >>> ax = sns.kdeplot(x, y, shade=True) Use more contour levels and a different color palette: .. plot:: :context: close-figs >>> ax = sns.kdeplot(x, y, n_levels=30, cmap="Purples_d") Use a narrower bandwith: .. plot:: :context: close-figs >>> ax = sns.kdeplot(x, bw=.15) Plot the density on the vertical axis: .. plot:: :context: close-figs >>> ax = sns.kdeplot(y, vertical=True) Limit the density curve within the range of the data: .. plot:: :context: close-figs >>> ax = sns.kdeplot(x, cut=0) Add a colorbar for the contours: .. plot:: :context: close-figs >>> ax = sns.kdeplot(x, y, cbar=True) Plot two shaded bivariate densities: .. plot:: :context: close-figs >>> iris = sns.load_dataset("iris") >>> setosa = iris.loc[iris.species == "setosa"] >>> virginica = iris.loc[iris.species == "virginica"] >>> ax = sns.kdeplot(setosa.sepal_width, setosa.sepal_length, ... cmap="Reds", shade=True, shade_lowest=False) >>> ax = sns.kdeplot(virginica.sepal_width, virginica.sepal_length, ... cmap="Blues", shade=True, shade_lowest=False) iiNsšPassing a 2D dataset for a bivariate plot is deprecated in favor of kdeplot(x, y), and it will cause an error in future versions. Please update your code.sKCumulative distribution plots are notsupported for bivariate distributions.RV(R.R/R0RƒtlistRRRtastypetfloat64tFalsetndarrayR4R3R·Rªt DataFrametilocR¬RaRbRcR‚R¥Rx(Rptdata2RqR RrRUR*R+R,RoRVt shade_lowestR™RšR›R#RsRbt bivariateR%R$twarn_msg((s4lib/python2.7/site-packages/seaborn/distributions.pyR ísN—  ''    gš™™™™™©?R%c K s¬|dkrtjƒ}ntj|ƒ}|jd|dkƒ}tddddddƒ}x<|jƒD].\}}||krj|j|ƒ||R6titemsR;ttxtblended_transform_factoryt transAxest transDatat column_stackttileRtrepeatR°tadd_collectionRtautoscale_view( RtheightR&R#RsR t alias_maptattrtaliasttranstxy_pairst line_segs((s4lib/python2.7/site-packages/seaborn/distributions.pyR ¸s(  !$(4t__doc__t __future__RtnumpyRtscipyRtpandasRªt matplotlibR<tmatplotlib.pyplottpyplotR/tmatplotlib.transformst transformsRÐtmatplotlib.collectionsRRatdistutils.versionRtsixRtstatsmodels.nonparametric.apit nonparametrictapiRyR3R_RdR¿tutilsRRtpalettesRRR R t__all__RR.R RxR`ReR¥RŠR‹R R (((s4lib/python2.7/site-packages/seaborn/distributions.pytsF       "   â P  C    È