B x\Q @sddlmZddlZddlmZmZmZmZddl m Z ddl m Z ddl mZddlmZddlmZmZd*ddZddZd+ddZe dddd,ddZd-ddZe ddde ddd d!d.d#d$Zd/d&d'Zd0d(d)ZdS)1)divisionN)lmaplrangerangezip)deprecate_kwarg)notna) pprint_thing)_get_standard_colors)_set_ticks_props _subplots?Fhist.皙?c #Ks6|} | jj} | | } t| ||dd\}}|jdddt| }t|}|pPi}|pXi}| ddg}x^| jD]T}| |j||j}t |t |}}||| d}| ||||fqrWx|t t| | jD]f\}}xZt t| | jD]D\}}|||f}||kr| |j||j}|dkrJ|j|f|nN|d krdd lm}|}||}t | | d }|j|||f||||nX||||@j}|j| ||| ||f||d | |||||||||||dkr*|jd|| d kr|jdqWqWt| jd kr |d}|dd j} | |d| k| |d k@} | |d|d |d}!|dd}"|!|"d |"d|"d}!|ddj |!t !| | "t#kr | "t#} |ddj$| t%|ddddd|S)a 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) F)naxesfigsizeaxZsqueezer)ZwspaceZhspaceZ edgecolorsnoneg@r)ZkdeZdensity) gaussian_kdei)markeralphaZ)Z xlabelsizeZxrotZ ylabelsizeZyrot)&Z_get_numeric_datacolumnssizer Zsubplots_adjustr_get_marker_compat setdefaultvaluesnpminmaxappendrrrZ scipy.statsrlinspaceplotZevaluateset_xlimscatterZset_ylim set_xlabel set_ylabelZyaxisZ set_visibleZxaxislenZget_majorticklocsZget_ylimZ set_ticksallZastypeintZset_ticklabelsr )#framerrrgridZdiagonalrZ density_kwdsZ hist_kwdsZ range_paddingkwdsdfnrfigaxesmaskZboundaries_listarZrmin_Zrmax_Z rdelta_extijbryZgkdeZindcommonZlim1ZlocsZadjZlim0r;4lib/python3.7/site-packages/pandas/plotting/_misc.pyscatter_matrixsn'              r=cCsddlm}||jkrdS|S)Nro)Zmatplotlib.lineslinesZ lineMarkers)rZmlinesr;r;r<rs  rc sddlm}ddlm}dd}t|} ||} ||} |j|dd|} |dkrn|jddgddgd}i} t t| |d |d }x| D]}ggg| |<qWt|j dt d d fd d t DD}xt | D]x}| j|j}t jt j|ddddd}||jdd|}| j|}| |d|d| |d|dqWxHt| D]<\}}|j| |d| |df||t|d|qdW|||jddddx@t|| j D].\}}||j|ddd|ddkr6|ddkr6|j|dd|dd|ddddn|ddkrz|ddkrz|j|dd|dd|ddddn|ddkr|ddkr|j|dd|dd|ddddnB|ddkr|ddkr|j|dd|dd|ddddqW|d|S)as Plot a multidimensional dataset in 2D. Each Series in the DataFrame is represented as a evenly distributed slice on a circle. Each data point is rendered in the circle according to the value on each Series. Highly correlated `Series` in the `DataFrame` are placed closer on the unit circle. RadViz allow to project a N-dimensional data set into a 2D space where the influence of each dimension can be interpreted as a balance between the influence of all dimensions. More info available at the `original article `_ 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 rNcSs t|}t|}||||S)N)r!r")seriesr5r8r;r;r< normalizeszradviz..normalizer)axis)xlimylimrandom) num_colorscolormap color_typecolorcSs g|]}t|t|fqSr;)r cossin).0tr;r;r< szradviz..cs"g|]}dtj|tqS)g@)r pifloat)rMr6)mr;r<rOs)rJlabel)ggg?r)ZradiusZ facecolorg?ZgraygrighttopZsmall)ZhaZvarZbottomleftZequal)matplotlib.pyplotpyplotZmatplotlib.patchespatchesr*drop_duplicatesdropZapplygcar rr arrayrilocrrepeatZ expand_dimssumiatr# enumerater'r legendZ add_patchZCirclertextrB)r- class_columnrrJrHr/pltrZrAr1classes class_colr0Zto_plotcolorsklssr6rowZrow_r9Zxynamer;)rRr<radvizs\>            rodatar-) old_arg_name new_arg_namec sLddlmm}ddlm}fdd} t|} ||} ||} |j|dd} t | ||}t }t t| |d|d }t t | |}|dkr|j| |fd }xt| D]}| j|j}| |}||}| j|}t|}||kr|||j||f|||d |q|j||fd ||i|qW|jd d||S)a> 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 r)sqrtrPNcsfdd}|S)Ncsd}|d}ttd}|t|jdddtd|jdd}t||}|tj |dddtj ft ||dddtj ft |dd7}|S)Nrg@rrS)rB) r deletecopyZresizer,rarangeshapeZouterraZnewaxisrLrK)rNZx1resultZcoeffsZ harmonicsZ trig_args) amplitudesrtr;r<f8s  " z+andrews_curves..function..fr;)rzr{)rt)rzr<function7sz andrews_curves..functionr)rBrF)rGrHrIrJ)rD)rJrTrJz upper right)loc)ZmathrtrPrXrYr*r[r\r r$setr dictrr]rr_rrbr addr%rdr.)r-rfrsamplesrJrHr/rPrgr|r1rirhr0rN used_legends color_valuesrjr6rmr{r9rkrTr;)rtr<andrews_curvess8$          r2c sddlddlm}t|jfddt|D}tdd|D}tdd|D}tdd|D} |dkr|}t |} g} | dd d } | d | | | j | |f|| dd d} | d | | | j | |f|| dd d }| d | ||j | | f|| dd d }| d | ||j|f|| dd d}| d| ||j|f|| dd d}| d| ||j| f|x2| D]*}|j|dd|j|ddqW|S)a 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 rNcsg|]}qSr;)Zsample)rM_)rprFrr;r<rOsz"bootstrap_plot..cSsg|]}t|qSr;)r mean)rMsamplingr;r;r<rOscSsg|]}t|qSr;)r Zmedian)rMrr;r;r<rOscSs g|]}t|t|dqS)g?)r!r")rMrr;r;r<rOsrSrZSampleZMeanZMedianZMidranger)Zfontsize)rFrXrYlistrrr r^ZfigurerZ add_subplotr(r#r%rZsetpZget_xticklabelsZget_yticklabels)r@r2rrr/rgZ samplingsZmeansZmediansZ midrangesxr3Zax1Zax2Zax3Zax4Zax5Zax6rBr;)rprFrr<bootstrap_plotksP.                 rrjrJr)rqrr stacklevelTc Ks | dkrddd} ddlm} t|} ||}||}|dkrR|j|dd}n||}t}t|j}|dkrtt t |jst d|j}nD|dk rtt |st d nt||krt d |}nt |}|dkr| }tt||d |d }| rt|}t|}tt||}xt| D]t}|j|j}|j|}t|}||kr|||j||f|||d | n|j||fd||i| q.W|rx|D]}|j|f| qW||||j||d|d|jdd||S)aParallel 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() Nrblack)Z linewidthrJr)rBTz,Columns must be numeric to be used as xticksz xticks specified must be numericz-Length of xticks must match number of columnsrF)rGrHrIrJ)rJrTrJrCz upper right)r})rXrYr*r[r\r~rr r+Zisrealr ValueErrorrr]r sortedrrrr_rrbr rr%ZaxvlineZ set_xticksZset_xticklabelsr&rdr.)r-rfZcolsrrJZ use_columnsZxticksrHZaxvlinesZ axvlines_kwdsZ sort_labelsr/rgr1rhrir0rZncolsrrrjr6r9rkrTr;r;r<parallel_coordinatess`3           "    rrcKs~ddlm}|d|jd|j}|d| }||d}|dkrN|}|d|dj|d|j ||f||S)a&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 rNczpatch.facecolorzy(t)z y(t + {lag}))lag) rXrYrZrcParamsrr]r(r)formatr')r@rrr/rgrpZy1Zy2r;r;r<lag_plot:s   rc  sFddlm}t|t||dkr8|jdfdd}ttdtfdd}t d}t ||}d }d }|j |t d d d |j |t d d|j ddd|j | t d d|j | t d d d | d|d|j||f|d|kr:|||S)aAutocorrelation 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 rNr)gg?)rDrErScs4d||dtS)N)rarQ)h)c0rprr1r;r<rnszautocorrelation_plot..rg1\?g`dL@z--Zgrey)r9Z linestylerJ)r9rJgrZLagZAutocorrelationrT)rXrYr*r Zasarrayr]rrarQrwrZaxhlinertr(r)r%rdr.) r@rr/rgrrr9Zz95Zz99r;)rrprr1r<autocorrelation_plotXs0       r) r NNFrrNNr)NNN)NrsNN)Nrr) NNNFNNTNF)rN)N)Z __future__rZnumpyr Z pandas.compatrrrrZpandas.util._decoratorsrZpandas.core.dtypes.missingrZpandas.io.formats.printingr Zpandas.plotting._styler Zpandas.plotting._toolsr r r=rrorrrrrr;r;r;r<s.      x ~  Y [  p