ó šxŠ\c @ s‚ddlmZddlZddlmZmZmZmZddl m Z ddl m Z ddl mZddlmZddlmZmZd dded d ddd d „ Zd„Zdddd„Ze ddddƒddddd„ƒZdddd„Ze ddddƒe ddddddƒdddeddeded„ ƒƒZddd„Zdd „ZdS(!i˙˙˙˙(tdivisionN(tlmaptlrangetrangetzip(tdeprecate_kwarg(tnotna(t pprint_thing(t_get_standard_colors(t_set_ticks_propst _subplotsgŕ?thistt.gš™™™™™Š?c # K s7|jƒ} | jj} | | } td| d|d|dtƒ\}}|jddddƒt| ƒ}t|ƒ}|p€i}|pŒi}| jdd ƒg}xu| jD]j}| |j ||j }t j |ƒt j |ƒ}}||| d }|j ||||fƒqŻWxćtt| ƒ| jƒD]Ě\}}x˝tt| ƒ| jƒD]Ł\}}|||f}||kr<| |j ||j }|d krş|j||nn|dkr(ddlm}|}||ƒ}t j|j ƒ|j ƒdƒ}|j||j|ƒ|n|j||ƒnf||||@j }|j| ||| ||d|d|| |j||ƒ|j||ƒ|j|ƒ|j|ƒ|dkrŰ|jjtƒn|| dkr[|jjtƒq[q[Wq6Wt| jƒdkr|d}|ddjjƒ} | |d| k| |dk@} | |d|d|d}!|ddj ƒ}"|!|"d|"d|"d}!|ddjj!|!ƒt j"| | j#t$ƒkƒrö| j#t$ƒ} n|ddjj%| ƒnt&|ddddddddƒ|S(s– Draw a matrix of scatter plots. Parameters ---------- frame : DataFrame alpha : float, optional amount of transparency applied figsize : (float,float), optional a tuple (width, height) in inches ax : Matplotlib axis object, optional grid : bool, optional setting this to True will show the grid diagonal : {'hist', 'kde'} pick between 'kde' and 'hist' for either Kernel Density Estimation or Histogram plot in the diagonal marker : str, optional Matplotlib marker type, default '.' hist_kwds : other plotting keyword arguments To be passed to hist function density_kwds : other plotting keyword arguments To be passed to kernel density estimate plot range_padding : float, optional relative extension of axis range in x and y with respect to (x_max - x_min) or (y_max - y_min), default 0.05 kwds : other plotting keyword arguments To be passed to scatter function Examples -------- >>> df = pd.DataFrame(np.random.randn(1000, 4), columns=['A','B','C','D']) >>> scatter_matrix(df, alpha=0.2) tnaxestfigsizetaxtsqueezetwspaceithspacet edgecolorstnoneg@R tkdetdensityi˙˙˙˙(t gaussian_kdeičtmarkertalphait xlabelsizeitxrotiZt ylabelsizetyrot(RR('t_get_numeric_datatcolumnstsizeR tFalsetsubplots_adjustRt_get_marker_compatt setdefaulttvaluestnptmintmaxtappendRRR t scipy.statsRtlinspacetplottevaluatetset_xlimtscattertset_ylimt set_xlabelt set_ylabeltyaxist set_visibletxaxistlentget_majorticklocstget_ylimt set_tickstalltastypetinttset_ticklabelsR (#tframeRRRtgridtdiagonalRt density_kwdst hist_kwdst range_paddingtkwdstdftnR tfigtaxestmasktboundaries_listtaR%trmin_trmax_t rdelta_exttitjtbRtytgkdetindtcommontlim1tlocstadjtlim0((s4lib/python2.7/site-packages/pandas/plotting/_misc.pytscatter_matrixsn'       %%    !    ""cC s&ddlj}||jkr"dS|S(Ni˙˙˙˙to(tmatplotlib.linestlinest lineMarkers(Rtmlines((s4lib/python2.7/site-packages/pandas/plotting/_misc.pyR#‹sc K sLddlj}ddlj}d„}t|ƒ} ||jƒ} ||} |j|ddƒj|ƒ} |dkrž|j dddgdddgƒ}ni} t dt| ƒd |d d d |ƒ}x| D]}ggg| |`_ describing RadViz. Parameters ---------- frame : `DataFrame` Pandas object holding the data. class_column : str Column name containing the name of the data point category. ax : :class:`matplotlib.axes.Axes`, optional A plot instance to which to add the information. color : list[str] or tuple[str], optional Assign a color to each category. Example: ['blue', 'green']. colormap : str or :class:`matplotlib.colors.Colormap`, default None Colormap to select colors from. If string, load colormap with that name from matplotlib. kwds : optional Options to pass to matplotlib scatter plotting method. Returns ------- axes : :class:`matplotlib.axes.Axes` See Also -------- pandas.plotting.andrews_curves : Plot clustering visualization. Examples -------- .. plot:: :context: close-figs >>> df = pd.DataFrame({ ... 'SepalLength': [6.5, 7.7, 5.1, 5.8, 7.6, 5.0, 5.4, 4.6, ... 6.7, 4.6], ... 'SepalWidth': [3.0, 3.8, 3.8, 2.7, 3.0, 2.3, 3.0, 3.2, ... 3.3, 3.6], ... 'PetalLength': [5.5, 6.7, 1.9, 5.1, 6.6, 3.3, 4.5, 1.4, ... 5.7, 1.0], ... 'PetalWidth': [1.8, 2.2, 0.4, 1.9, 2.1, 1.0, 1.5, 0.2, ... 2.1, 0.2], ... 'Category': ['virginica', 'virginica', 'setosa', ... 'virginica', 'virginica', 'versicolor', ... 'versicolor', 'setosa', 'virginica', ... 'setosa'] ... }) >>> rad_viz = pd.plotting.radviz(df, 'Category') # doctest: +SKIP i˙˙˙˙NcS s(t|ƒ}t|ƒ}||||S(N(R'R((tseriesRKRQ((s4lib/python2.7/site-packages/pandas/plotting/_misc.pyt normalizeÓs  taxisitxlimtylimt num_colorstcolormapt color_typetrandomtcolorg@iitlabelgtradiusgđ?t facecolorRgš™™™™™™?tgraythatrighttvattopR tsmalltbottomtlefttequal(gg(#tmatplotlib.pyplottpyplottmatplotlib.patchestpatchesR6tdrop_duplicatestdroptapplytNonetgcaRRR&tarrayRtpitfloattcostsintilocR%trepeatt expand_dimstsumtiatR)t enumerateR/Rtlegendt add_patchtCircleRttextRb(R>t class_columnRRiRfRDtpltRyRaRFtclassest class_colREtto_plottcolorstklstmROtttstrowtrow_RRtxytname((s4lib/python2.7/site-packages/pandas/plotting/_misc.pytradviz’s\>    '  \'  ) "" " " " " t old_arg_nametdatat new_arg_nameR>iČc sÄddlm‰m}ddlj}‡fd†} t|ƒ} ||} ||jƒ} |j|ddƒ} tj | ||ƒ}t ƒ}t dt| ƒd|d d d |ƒ}t t | |ƒƒ}|dkrň|jd | |fƒ}nxąt| ƒD]Ł}| j|j}| |ƒ}||ƒ}| j|}t|ƒ}||kr…|j|ƒ|j||d ||d ||q˙|j||d |||q˙W|jddƒ|jƒ|S(s> Generates a matplotlib plot of Andrews curves, for visualising clusters of multivariate data. Andrews curves have the functional form: f(t) = x_1/sqrt(2) + x_2 sin(t) + x_3 cos(t) + x_4 sin(2t) + x_5 cos(2t) + ... Where x coefficients correspond to the values of each dimension and t is linearly spaced between -pi and +pi. Each row of frame then corresponds to a single curve. Parameters ---------- frame : DataFrame Data to be plotted, preferably normalized to (0.0, 1.0) class_column : Name of the column containing class names ax : matplotlib axes object, default None samples : Number of points to plot in each curve color : list or tuple, optional Colors to use for the different classes colormap : str or matplotlib colormap object, default None Colormap to select colors from. If string, load colormap with that name from matplotlib. kwds : keywords Options to pass to matplotlib plotting method Returns ------- ax : Matplotlib axis object i˙˙˙˙(tsqrtR€Nc s‡‡fd†}|S(Nc sěˆd}|ˆdƒ}tjtjˆƒdƒ}|jt|jddƒdƒtjd|jdƒd}tj||ƒ}|tj |dd…dtj ftj |ƒ|dd…dtj ftj |ƒddƒ7}|S(Nig@iiRb( R&tdeletetcopytresizeR<R tarangetshapetouterR‡tnewaxisRƒR‚(R–tx1tresulttcoeffst harmonicst trig_args(t amplitudesR (s4lib/python2.7/site-packages/pandas/plotting/_misc.pytf8s !/* ((R­RŽ(R (R­s4lib/python2.7/site-packages/pandas/plotting/_misc.pytfunction7sRbiReRfRgRhRiRcRjtlocs upper right(tmathR R€RvRwR6RzR{R&R+tsetRtdictRR}R~RR„R%RˆRtaddR,RŠR?(R>RŽRtsamplesRiRfRDR€RRŻRFR‘RRER–t used_legendst color_valuesR“ROR˜RŽRRR”Rj((R s4lib/python2.7/site-packages/pandas/plotting/_misc.pytandrews_curvess8$            &! i2iôcK sŘddl}ddlj}t|jƒ}gt|ƒD]}|j||ƒ^q7} tjg| D]} tj | ƒ^qbƒ} tjg| D]} tj | ƒ^qƒ} tjg| D] } t | ƒt | ƒd^q¸ƒ} |dkrü|jƒ}nt|ƒ}g}|jdddƒ}|jdƒ|j|ƒ|j|| ||jdddƒ}|jdƒ|j|ƒ|j|| ||jdddƒ}|jdƒ|j|ƒ|j|| ||jdddƒ}|jd ƒ|j|ƒ|j| ||jddd ƒ}|jd ƒ|j|ƒ|j| ||jddd ƒ}|jd ƒ|j|ƒ|j| |x@|D]8}|j|jƒddƒ|j|jƒddƒq˜W|S(sü Bootstrap plot on mean, median and mid-range statistics. The bootstrap plot is used to estimate the uncertainty of a statistic by relaying on random sampling with replacement [1]_. This function will generate bootstrapping plots for mean, median and mid-range statistics for the given number of samples of the given size. .. [1] "Bootstrapping (statistics)" in https://en.wikipedia.org/wiki/Bootstrapping_%28statistics%29 Parameters ---------- series : pandas.Series Pandas Series from where to get the samplings for the bootstrapping. fig : matplotlib.figure.Figure, default None If given, it will use the `fig` reference for plotting instead of creating a new one with default parameters. size : int, default 50 Number of data points to consider during each sampling. It must be greater or equal than the length of the `series`. samples : int, default 500 Number of times the bootstrap procedure is performed. **kwds : Options to pass to matplotlib plotting method. Returns ------- fig : matplotlib.figure.Figure Matplotlib figure See Also -------- pandas.DataFrame.plot : Basic plotting for DataFrame objects. pandas.Series.plot : Basic plotting for Series objects. Examples -------- .. plot:: :context: close-figs >>> s = pd.Series(np.random.uniform(size=100)) >>> fig = pd.plotting.bootstrap_plot(s) # doctest: +SKIP i˙˙˙˙Ngŕ?iiitSampleitMeanitMedianitMidrangetfontsizei(RhRvRwtlistR%RtsampleR&RtmeantmedianR'R(R}tfigureRt add_subplotR1R)R,R tsetptget_xticklabelstget_yticklabels(R`RGR RľRDRhRRžt_t samplingstsamplingtmeanstmedianst midrangestxRHtax1tax2tax3tax4tax5tax6Rb((s4lib/python2.7/site-packages/pandas/plotting/_misc.pytbootstrap_plotksP. +++ -               R“Rit stacklevelic  K sŕ| dkr#idd6dd6} nddlj} t|ƒ} ||jƒ}||}|dkr||j|ddƒ}n ||}tƒ}t|jƒ}|tkrćt j t j t |jƒƒƒsÚt dƒ‚n|j}ni|dk rCt j t j |ƒƒst d ƒ‚n!t|ƒ|kr:t d ƒ‚n|}n t|ƒ}|dkrj| jƒ}ntd t|ƒd |d dd|ƒ}| r˛t|ƒ}t|ƒ}ntt||ƒƒ}x™t| ƒD]‹}|j|j}|j|}t|ƒ}||krB|j|ƒ|j||d||d|| qÔ|j||d||| qÔW|rx!|D]}|j|| qpWn|j|ƒ|j|jƒ|j|d|dƒ|jddƒ|j ƒ|S(s‹Parallel coordinates plotting. Parameters ---------- frame : DataFrame class_column : str Column name containing class names cols : list, optional A list of column names to use ax : matplotlib.axis, optional matplotlib axis object color : list or tuple, optional Colors to use for the different classes use_columns : bool, optional If true, columns will be used as xticks xticks : list or tuple, optional A list of values to use for xticks colormap : str or matplotlib colormap, default None Colormap to use for line colors. axvlines : bool, optional If true, vertical lines will be added at each xtick axvlines_kwds : keywords, optional Options to be passed to axvline method for vertical lines sort_labels : bool, False Sort class_column labels, useful when assigning colors .. versionadded:: 0.20.0 kwds : keywords Options to pass to matplotlib plotting method Returns ------- ax: matplotlib axis object Examples -------- >>> from matplotlib import pyplot as plt >>> df = pd.read_csv('https://raw.github.com/pandas-dev/pandas/master' '/pandas/tests/data/iris.csv') >>> pd.plotting.parallel_coordinates( df, 'Name', color=('#556270', '#4ECDC4', '#C7F464')) >>> plt.show() it linewidthtblackRii˙˙˙˙NRbs,Columns must be numeric to be used as xtickss xticks specified must be numerics-Length of xticks must match number of columnsReRfRgRhRjiR°s upper right(!R}RvRwR6RzR{R˛RtTrueR&R:tisrealRžt ValueErrorRR~RtsortedRłRRR„R%RˆRR´R,taxvlinet set_xtickstset_xticklabelsR.RŠR?(R>RŽtcolsRRit use_columnstxticksRftaxvlinest axvlines_kwdst sort_labelsRDRRFRR‘RERśtncolsRÍRˇR“RORRR”Rj((s4lib/python2.7/site-packages/pandas/plotting/_misc.pytparallel_coordinatesĆs`3       !            &!   icK sœddlj}|jd|jdƒ|j}|| }||}|dkr_|jƒ}n|jdƒ|jdj d|ƒƒ|j ||||S(s&Lag plot for time series. Parameters ---------- series : Time series lag : lag of the scatter plot, default 1 ax : Matplotlib axis object, optional kwds : Matplotlib scatter method keyword arguments, optional Returns ------- ax: Matplotlib axis object i˙˙˙˙Ntcspatch.facecolorsy(t)s y(t + {lag})tlag( RvRwR$trcParamsR%R}R~R1R2tformatR/(R`RčRRDRRžty1ty2((s4lib/python2.7/site-packages/pandas/plotting/_misc.pytlag_plot:s     c  sŃddlj}t|ƒ‰tj|ƒ‰|dkrW|jddˆfddƒ}ntjˆƒ‰tjˆˆdƒt ˆƒ‰‡‡‡‡fd †}tj ˆƒd}t ||ƒ}d }d }|j d |tj ˆƒd dddƒ|j d |tj ˆƒddƒ|j d dddƒ|j d | tj ˆƒddƒ|j d | tj ˆƒd dddƒ|jdƒ|jdƒ|j|||d|krĂ|jƒn|jƒ|S(sAutocorrelation plot for time series. Parameters: ----------- series: Time series ax: Matplotlib axis object, optional kwds : keywords Options to pass to matplotlib plotting method Returns: ----------- ax: Matplotlib axis object i˙˙˙˙NRciRdgđżgđ?ic s0ˆˆ| ˆˆ|ˆjƒtˆƒˆS(N(R‡R(th(tc0RžRŔRF(s4lib/python2.7/site-packages/pandas/plotting/_misc.pytrnsg„˙î1\˙?g`‘ÖdL›@RRt linestyles--RitgreygR×tLagtAutocorrelationRj(gđżgđ?(RvRwR6R&tasarrayR}R~RŔR‡RR¤RtaxhlineR R1R2R,RŠR?( R`RRDRRđRÍRRtz95tz99((RďRžRŔRFs4lib/python2.7/site-packages/pandas/plotting/_misc.pytautocorrelation_plotXs0  !!)#$*     (t __future__RtnumpyR&t pandas.compatRRRRtpandas.util._decoratorsRtpandas.core.dtypes.missingRtpandas.io.formats.printingRtpandas.plotting._styleRtpandas.plotting._toolsR R R}R!RZR#RœR¸RÔRŘRćRíRů(((s4lib/python2.7/site-packages/pandas/plotting/_misc.pyts. "  x ~ Y[  p