B =Œ¶cQPã @sÞddlmZddlmZddlmZmZddlmZ ddl m Z ddl m Z e d¡Ze d¡Ze d ¡Zd d „Zd+dd„Zd,dd„Zdd„Zdd„Zdd„Zdd„Zdd„Zd-dd„Zdd „Zd!d"„Zd#d$„Zd.d)d*„ZdS)/é)Úabsolute_import)ÚNumber)Ú exceptionsÚoptional_importsN)Ú graph_objs)Ú make_subplotsZpandasÚnumpyz scipy.statsc Cs¢t |tj¡}t |¡}t |¡}tj|ddd}tj|ddd}tj|ddd}||}d|}t ||||k¡} t ||||k¡} |||||| | d œS) z6 Calculate statistics for use in violin plot. é2Zlinear)Ú interpolationéÚloweréKZhighergø?)ÚminÚmaxÚq1Úq2Úq3Úd1Úd2)ÚnpÚasarrayÚfloatrrZ percentile) ÚdataÚxÚvals_minÚvals_maxrrrZiqrZ whisker_distrr©rúN/var/www/cleansys/lib/python3.7/site-packages/plotly/figure_factory/_violin.pyÚ calc_statss"  rú#1f77b4ú rgb(0, 0, 0)c sH‡‡fdd„ttˆƒƒDƒ}tjˆˆdd|d|tjjd|ddd dd S) zG Produces a sideways probability distribution fig violin plot. cs4g|],}dd ˆ|¡dd ˆ|¡d‘qS)z (pdf(y), y)=(z{:0.2f}z, ú))Úformat)Ú.0Úi)rÚyrrú 0sz$make_half_violin..ÚlinesÚZtonextxgà?Zspline)ÚwidthÚcolorÚshapeÚtext) rr%ÚmodeÚnamer,ÚfillÚ fillcolorÚlineÚ hoverinfoZopacity)ÚrangeÚlenrÚScatterÚscatterÚLine)rr%r0Z linecolorr,r)rr%rÚmake_half_violin+s r8c Cs4tj|| |gt|ƒtjj|dddddddS)z2 Returns a rugplot fig for a violin plot. z line-ew-open)r*ÚsymbolÚmarkersr(Fr%)r%rÚmarkerr-r.Ú showlegendr2)rr5r4r6ÚMarker)ÚvalsZpdf_maxÚdistancer*rrrÚmake_violin_rugplotBsr@c Cs(tjddg||gddtjjddddS)z? Returns the scatterplot fig of most of a violin plot. rr(r'gø?z rgb(0,0,0))r)r*)rr%r.r-r1)rr5r6r7)rrrrrÚmake_non_outlier_intervalQs rAc CsBtjddg||gdd |¡dd |¡gdtjjdddd d S) z@ Makes the upper and lower quartiles for a violin plot. rzlower-quartile: z{:0.2f}zupper-quartile: r'éz rgb(0,0,0))r)r*r,)rr%r,r-r1r2)rr5r"r6r7)rrrrrÚmake_quartiles^s rCc Cs.tjdg|gdd |¡gdtddddd S) z; Formats the 'median' hovertext for a violin plot. rzmedian: z{:0.2f}r:Zsquarezrgb(255,255,255))r9r*r,)rr%r,r-r;r2)rr5r"Údict)rrrrÚ make_medianos rEc Cs tjj||ddddddd}|S)z- Makes the x-axis for a violin plot. Fr()Útitler3ÚshowgridÚzerolineÚshowlineÚmirrorÚticksÚshowticklabels)rÚlayoutZXAxis)Z xaxis_titleZ xaxis_rangeÚxaxisrrrÚ make_XAxis}srOc Cs tjj|dddddddd}|S)z- Makes the y-axis for a violin plot. TrBF)rFrLZ autorangeZticklenrIrHrGrJ)rrMZYAxis)Z yaxis_titleÚyaxisrrrÚ make_YAxisŽsrQTcCst |tj¡}t|ƒd}t|ƒd}t|ƒd}t|ƒd}t|ƒd}t|ƒd}t|ƒd} t |¡} t ||d¡} | | ƒ} t | ¡} |rœd | d nd }| |d | d g}t| | |d t| | |d t || ƒt ||ƒt |ƒg}|r|  t || ||d¡||fS)z? Refer to FigureFactory.create_violin() for docstring. rrrrrrrédg@é rgš™™™™™¹?)r0)r?r*)rrrrÚ scipy_statsZ gaussian_kdeZlinspacerr8rArCrEÚappendr@)r>r0ÚrugplotrrrrrrrZpdfZxxÚyyZmax_pdfr?Ú plot_xrangeÚ plot_datarrrÚ violinplotŸs.           rZc CsBg} x"||D]} | | kr|  | ¡qW|r4|  ¡| |g¡} t| ƒ}td|dddd}d}x¨t| ƒD]œ\}}t |  |¡|tj ¡}|t|ƒkr˜d}t ||||d\}}t   ¡}x|D]}|  |d|d¡q¼W|d7}|d d  |d¡t| ||ƒi¡qhW|d d  d¡td ƒi¡|dj| dd d|| d |S)zu Refer to FigureFactory.create_violin() for docstring. Returns fig for violin plot without colorscale. éTgš™™™™™™?F)ÚrowsÚcolsÚ shared_yaxesÚhorizontal_spacingÚ print_gridr)r0rVrMzxaxis{}zyaxis{}r(Úclosest)rFr<Ú hovermodeÚautosizeÚheightr))rUÚsortÚgroupbyr4rÚ enumeraterrÚ get_grouprrZrÚLayoutÚ append_traceÚupdater"rOrQ)rÚ data_headerÚ group_headerÚcolorsÚuse_colorscaleÚ group_statsrVrerdr)rFÚ group_namer.ÚgbÚLÚfigZ color_indexÚkÚgrr>rYrXrMÚitemrrrÚviolin_no_colorscaleÆs@   "rxc ! Csg} x"||D]} | | kr|  | ¡qW|r4|  ¡x| D]} | |kr:t d¡‚q:W| |g¡}t| ƒ}td|dddd}t |dtj ¡}t |dtj ¡}g}x|D]}| ||¡q¨Wt |ƒ}t |ƒ}x¶t | ƒD]ª\}}t  | |¡|t j¡}|||||}t |||¡}t|d |¡|d \}}t ¡}x |D]}| |d|d¡q@W|d  d  |d¡t| ||ƒi¡qØWtjdgdgd td ||d|dgd|dggdddd} | | d|¡|d  d d¡tdƒi¡|d j| ddd|| d|S)zr Refer to FigureFactory.create_violin() for docstring. Returns fig for violin plot with colorscale. zRAll values/groups in the index column must be represented as a key in group_stats.r[Tgš™™™™™™?F)r\r]r^r_r`rzrgb{})r0rVrMzxaxis{}r:é)ÚsizeZcminZcmaxZ colorscaleZ showscale)rr%r-r;r<zyaxis{}r(ra)rFr<rbrcrdr))rUrerÚ PlotlyErrorrfr4rÚclrsZ color_parserZ unlabel_rgbrrrgrrrhrZfind_intermediate_colorrZr"rrirjrkrOr5rDrQ)!rrlrmrnrorprVrerdr)rFrqr.ÚgrouprrrsrtZlowcolorZ highcolorZgroup_stats_valuesÚkeyZ max_valueZ min_valuerurvr>ZintermedZintermed_colorrYrXrMrwZ trace_dummyrrrÚviolin_colorscale sj     "rc CsFg} x"||D]} | | kr|  | ¡qW|r4|  ¡x| D]} | |kr:t d¡‚q:W| |g¡}t| ƒ}td|dddd}xt| ƒD]„\}}t  |  |¡|tj ¡}t ||||d\}}t  ¡}x|D]}| |d|d¡qÈW|d d  |d¡t| ||ƒi¡q„W|d d  d¡td ƒi¡|dj| dd d|| d |S)zu Refer to FigureFactory.create_violin() for docstring. Returns fig for violin plot without colorscale. zMIf colors is a dictionary, all the group names must appear as keys in colors.r[Tgš™™™™™™?F)r\r]r^r_r`)r0rVrMzxaxis{}zyaxis{}r(ra)rFr<rbrcrdr))rUrerr{rfr4rrgrrrhrrZrrirjrkr"rOrQ)rrlrmrnrorprVrerdr)rFrqr.r}rrrsrtrurvr>rYrXrMrwrrrÚ violin_dictps>    "r€FéÂéXúViolin and Rug Plotc  Csþt|tƒrt |d¡} n t |d¡} |dkrt|tƒrjt|ƒdkrNt d¡‚t dd„|Dƒƒsjt d¡‚t ržt|t j j j ƒrž|dkrt d¡‚||j ¡}t|| d|d \} } tj| d tjjd d |d | td | ƒtd ƒdd }|d td d d d¡tj| |d}|St|t j j j ƒs*t d¡‚|dkr>t d¡‚|d kr–t| tƒrtt|||| |||||| | ƒ }|St|||| |||||| | ƒ }|Sndt| tƒr¬t d¡‚t| ƒdkrÄt d¡‚t|tƒsÚt d¡‚t|||| |||||| | ƒ }|SdS)a} **deprecated**, use instead the plotly.graph_objects trace :class:`plotly.graph_objects.Violin`. :param (list|array) data: accepts either a list of numerical values, a list of dictionaries all with identical keys and at least one column of numeric values, or a pandas dataframe with at least one column of numbers. :param (str) data_header: the header of the data column to be used from an inputted pandas dataframe. Not applicable if 'data' is a list of numeric values. :param (str) group_header: applicable if grouping data by a variable. 'group_header' must be set to the name of the grouping variable. :param (str|tuple|list|dict) colors: either a plotly scale name, an rgb or hex color, a color tuple, a list of colors or a dictionary. An rgb color is of the form 'rgb(x, y, z)' where x, y and z belong to the interval [0, 255] and a color tuple is a tuple of the form (a, b, c) where a, b and c belong to [0, 1]. If colors is a list, it must contain valid color types as its members. :param (bool) use_colorscale: only applicable if grouping by another variable. Will implement a colorscale based on the first 2 colors of param colors. This means colors must be a list with at least 2 colors in it (Plotly colorscales are accepted since they map to a list of two rgb colors). Default = False :param (dict) group_stats: a dictioanry where each key is a unique value from the group_header column in data. Each value must be a number and will be used to color the violin plots if a colorscale is being used. :param (bool) rugplot: determines if a rugplot is draw on violin plot. Default = True :param (bool) sort: determines if violins are sorted alphabetically (True) or by input order (False). Default = False :param (float) height: the height of the violin plot. :param (float) width: the width of the violin plot. :param (str) title: the title of the violin plot. Example 1: Single Violin Plot >>> from plotly.figure_factory import create_violin >>> import plotly.graph_objs as graph_objects >>> import numpy as np >>> from scipy import stats >>> # create list of random values >>> data_list = np.random.randn(100) >>> # create violin fig >>> fig = create_violin(data_list, colors='#604d9e') >>> # plot >>> fig.show() Example 2: Multiple Violin Plots with Qualitative Coloring >>> from plotly.figure_factory import create_violin >>> import plotly.graph_objs as graph_objects >>> import numpy as np >>> import pandas as pd >>> from scipy import stats >>> # create dataframe >>> np.random.seed(619517) >>> Nr=250 >>> y = np.random.randn(Nr) >>> gr = np.random.choice(list("ABCDE"), Nr) >>> norm_params=[(0, 1.2), (0.7, 1), (-0.5, 1.4), (0.3, 1), (0.8, 0.9)] >>> for i, letter in enumerate("ABCDE"): ... y[gr == letter] *=norm_params[i][1]+ norm_params[i][0] >>> df = pd.DataFrame(dict(Score=y, Group=gr)) >>> # create violin fig >>> fig = create_violin(df, data_header='Score', group_header='Group', ... sort=True, height=600, width=1000) >>> # plot >>> fig.show() Example 3: Violin Plots with Colorscale >>> from plotly.figure_factory import create_violin >>> import plotly.graph_objs as graph_objects >>> import numpy as np >>> import pandas as pd >>> from scipy import stats >>> # create dataframe >>> np.random.seed(619517) >>> Nr=250 >>> y = np.random.randn(Nr) >>> gr = np.random.choice(list("ABCDE"), Nr) >>> norm_params=[(0, 1.2), (0.7, 1), (-0.5, 1.4), (0.3, 1), (0.8, 0.9)] >>> for i, letter in enumerate("ABCDE"): ... y[gr == letter] *=norm_params[i][1]+ norm_params[i][0] >>> df = pd.DataFrame(dict(Score=y, Group=gr)) >>> # define header params >>> data_header = 'Score' >>> group_header = 'Group' >>> # make groupby object with pandas >>> group_stats = {} >>> groupby_data = df.groupby([group_header]) >>> for group in "ABCDE": ... data_from_group = groupby_data.get_group(group)[data_header] ... # take a stat of the grouped data ... stat = np.median(data_from_group) ... # add to dictionary ... group_stats[group] = stat >>> # create violin fig >>> fig = create_violin(df, data_header='Score', group_header='Group', ... height=600, width=1000, use_colorscale=True, ... group_stats=group_stats) >>> # plot >>> fig.show() ÚrgbNrzRIf data is a list, it must be nonempty and contain either numbers or dictionaries.css|]}t|tƒVqdS)N)Ú isinstancer)r#Úelementrrrú Rsz create_violin..z0If data is a list, it must contain only numbers.zVdata_header must be the column name with the desired numeric data for the violin plot.)r0rVFé )rzr(ra) rFrcZfontrdr<r)rNrPrbrP)rIrLrK)rrMzGError. You must use a pandas DataFrame if you are using a group header.zFThe colors param cannot be a dictionary if you are using a colorscale.ryzHcolors must be a list with at least 2 colors. A Plotly scale is allowed.z,Your group_stats param must be a dictionary.)r…rDr|Zvalidate_colors_dictZvalidate_colorsÚlistr4rr{ÚallÚpdÚcoreÚframeZ DataFrameÚvaluesÚtolistrZrrirMZFontrOrQrkZFigurer€rxr)rrlrmrnrorprVrerdr)rFZ valid_colorsrYrXrMrtrrrÚ create_violin¸s°           r)rr )r)rT) NNNFNTFrr‚rƒ)Ú __future__rÚnumbersrZplotlyrrZ plotly.colorsrnr|Zplotly.graph_objsrZplotly.subplotsrZ get_moduler‹rrTrr8r@rArCrErOrQrZrxrr€rrrrrÚs<            'CgJ