U SZfP @sddlmZddlmZmZddlmZddlm Z ddl m Z e dZ e dZe dZd d Zd*d dZd+ddZddZddZddZddZddZd,ddZddZd d!Zd"d#Zd-d(d)ZdS).)Number) exceptionsoptional_importsN) graph_objs) make_subplotsZpandasZnumpyz scipy.statsc Cst|t}t|}t|}tj|ddd}tj|ddd}tj|ddd}||}d|}t||||k} t||||k} |||||| | d S) z6 Calculate statistics for use in violin plot. 2Zlinear) interpolationlowerKZhigher?)minmaxq1q2q3d1d2)npasarrayfloatr rZ percentile) dataxvals_minvals_maxrrrZiqrZ whisker_distrrrA/tmp/pip-unpacked-wheel-5ksk5baj/plotly/figure_factory/_violin.py calc_stats s$   r#1f77b4 rgb(0, 0, 0)c sHfddttD}tjdd|d|tjjd|ddd dd S) zG Produces a sideways probability distribution fig violin plot. cs4g|],}dd|dd|dqS)z (pdf(y), y)=({:0.2f}z, ))format).0iryrr -sz$make_half_violin..linesZtonextxg?Zspline)widthcolorshapetext) rr&modenamer-fill fillcolorline hoverinfoZopacity)rangelenrScatterscatterLine)rr&r1Z linecolorr-rr%rmake_half_violin)s  r9c Cs4tj|| |gt|tjj|dddddddS)z2 Returns a rugplot fig for a violin plot. z line-ew-open)r+symbolmarkersr)Fr&)r&rmarkerr.r/ showlegendr3)rr6r5r7Marker)valsZpdf_maxdistancer+rrrmake_violin_rugplot@srAc Cs(tjddg||gddtjjddddS)z? Returns the scatterplot fig of most of a violin plot. rr)r(r rgb(0,0,0)r*r+)rr&r/r.r2)rr6r7r8)rrrrrmake_non_outlier_intervalOsrDc CsBtjddg||gdd|dd|gdtjjdddd d S) z@ Makes the upper and lower quartiles for a violin plot. rzlower-quartile: r zupper-quartile: r(rBrCr-)rr&r-r.r2r3)rr6r"r7r8)rrrrrmake_quartiles\s  rFc Cs.tjdg|gdd|gdtddddd S) z; Formats the 'median' hovertext for a violin plot. rzmedian: r r;Zsquarezrgb(255,255,255))r:r+r-)rr&r-r.r<r3)rr6r"dict)rrrr make_medianms rHc Cs tjj||ddddddd}|S)z- Makes the x-axis for a violin plot. Fr))titler4showgridzerolineshowlinemirrorticksshowticklabels)rlayoutZXAxis)Z xaxis_titleZ xaxis_rangexaxisrrr make_XAxis{s rRc Cs tjj|dddddddd}|S)z- Makes the y-axis for a violin plot. TrEF)rIrOZ autorangeZticklenrLrKrJrM)rrPZYAxis)Z yaxis_titleyaxisrrr make_YAxiss rTTcCs t|t}t|d}t|d}t|d}t|d}t|d}t|d}t|d} t|} t||d} | | } t| } |rd | d nd }| |d | d g}t| | |d t| | |d t || t ||t |g}|r| t || ||d||fS)z? Refer to FigureFactory.create_violin() for docstring. r rrrrrrdg@ rg?)r1)r@r+)rrrr scipy_statsZ gaussian_kdeZlinspacerr9rDrFrHappendrA)r?r1rugplotrrrrrrrZpdfZxxyyZmax_pdfr@ plot_xrange plot_datarrr violinplots2           r]c Cs4g} ||D]} | | kr | | q |r0| ||g} t| }td|dddd}d}t| D]\}}t| ||t }|t|krd}t ||||d\}}t }|D]}| |d|dq|d7}|dd |dt| ||iqb|dd dtd i|dj| dd d|| d |S)u Refer to FigureFactory.create_violin() for docstring. Returns fig for violin plot without colorscale. T皙?FZrowscolsZ shared_yaxesZhorizontal_spacingZ print_gridrr1rYrPxaxis{}yaxis{}r)closestrIr= hovermodeautosizeheightr*)rXsortgroupbyr5r enumeraterr get_grouprr]rLayout append_traceupdater"rRrT)r data_header group_headercolorsuse_colorscale group_statsrYrkrjr*rI group_namer/gbLfigZ color_indexkgrr?r\r[rPitemrrrviolin_no_colorscalesT      r~c ! Csg} ||D]} | | kr | | q |r0| | D]} | |kr4tdq4||g}t| }td|dddd}t|dtj }t|dtj }g}|D]}|||qt |}t |}t | D]\}}t |||t}|||||}t|||}t|d||d \}}t}|D]}||d|dq.|d d |dt| ||iqtjdgdgd td ||d|dgd|dggdddd} || d||d ddtdi|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_Tr`Frarzrgb{}rcrPrdr;)sizeZcminZcmaxZ colorscaleZ showscale)rr&r.r<r=rer)rfrg)rXrkr PlotlyErrorrlr5rclrsZ color_parserZ unlabel_rgbrr rmrrrnrZfind_intermediate_colorr]r"rrorprqrRr6rGrT)!rrrrsrtrurvrYrkrjr*rIrwr/grouprxryrzZlowcolorZ highcolorZgroup_stats_valueskeyZ max_valueZ min_valuer{r|r?ZintermedZintermed_colorr\r[rPr}Z trace_dummyrrrviolin_colorscales      rc Cs4g} ||D]} | | kr | | q |r0| | D]} | |kr4tdq4||g}t| }td|dddd}t| D]~\}}t | ||t }t ||||d\}}t }|D]}||d|dq|dd |dt| ||iqz|dd dtd i|dj| dd d|| d |S)r^zMIf colors is a dictionary, all the group names must appear as keys in colors.r_Tr`FrarcrPrdrer)rfrg)rXrkrrrlr5rrmrrrnrr]rrorprqr"rRrT)rrrrsrtrurvrYrkrjr*rIrwr/rrxryrzr{r|r?r\r[rPr}rrr violin_dictnsN    rFXViolin and Rug Plotc  Cst|trt|d} n t|d} |dkrt|trjt|dkrNtdt dd|Dsjtdt rt|t j j j r|dkrtd||j}t|| d|d \} } tj| d tjjd d |d | td | td dd }|dtd d d dtj| |d}|St|t j j j s*td|dkr>td|d krt| trtt|||| |||||| | }|St|||| |||||| | }|Sndt| trtdt| dkrtdt|tstdt|||| |||||| | }|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 dictionary 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() ZrgbNrzRIf data is a list, it must be nonempty and contain either numbers or dictionaries.css|]}t|tVqdS)N) isinstancer)r#elementrrr Psz 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.rcF )rr)rf) rIrifontrjr=r*rQrSrhrS)rLrOrN)rrPzGError. 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.rzHcolors must be a list with at least 2 colors. A Plotly scale is allowed.z,Your group_stats param must be a dictionary.)rrGrZvalidate_colors_dictZvalidate_colorslistr5rrallpdcoreframeZ DataFramevaluestolistr]rrorPZFontrRrTrqZFigurerr~r)rrrrsrtrurvrYrkrjr*rIZ valid_colorsr\r[rPrzrrr create_violins                r)rr)r)rT) NNNFNTFrrr)ZnumbersrZplotlyrrZ plotly.colorsrtrZplotly.graph_objsrZplotly.subplotsrZ get_modulerrrWrr9rArDrFrHrRrTr]r~rrrrrrrs<           'CgJ