U Kv f @sLdZddlmZddlZddlmZddlmm Z d dd Z d d Z dS) z@ Authors: Josef Perktold, Skipper Seabold, Denis A. Engemann )lrangeN)rainbowmeanbbestc Ks,ddlm}t|\}}|p(t|dd}t|dt|}d||f}|pTt|dd}| pdt|dd} ||||d }}t|dtrd d t |D}t t |}t |tt||}|t|||d }|d dg|}t |d  }| d krdg|n| } | d kr*dg|n| } |d kr@t|n|}t | |krZtdt | |krptdt ||krtd|dks|dkrt|d D]R\}\}}t|d jd}|j|d|df||| ||| |d| qn|dks|dkrpt|d D]L\}\}}t|d jd}|j|d|df|||| |d| q n~|dks|dkrt|d D]L\}\}}t|d jd}|j|d|df|||| |d| qn td||j| | d|dt||gr(|||||S) a Interaction plot for factor level statistics. Note. If categorial factors are supplied levels will be internally recoded to integers. This ensures matplotlib compatibility. Uses a DataFrame to calculate an `aggregate` statistic for each level of the factor or group given by `trace`. Parameters ---------- x : array_like The `x` factor levels constitute the x-axis. If a `pandas.Series` is given its name will be used in `xlabel` if `xlabel` is None. trace : array_like The `trace` factor levels will be drawn as lines in the plot. If `trace` is a `pandas.Series` its name will be used as the `legendtitle` if `legendtitle` is None. response : array_like The reponse or dependent variable. If a `pandas.Series` is given its name will be used in `ylabel` if `ylabel` is None. func : function Anything accepted by `pandas.DataFrame.aggregate`. This is applied to the response variable grouped by the trace levels. ax : axes, optional Matplotlib axes instance plottype : str {'line', 'scatter', 'both'}, optional The type of plot to return. Can be 'l', 's', or 'b' xlabel : str, optional Label to use for `x`. Default is 'X'. If `x` is a `pandas.Series` it will use the series names. ylabel : str, optional Label to use for `response`. Default is 'func of response'. If `response` is a `pandas.Series` it will use the series names. colors : list, optional If given, must have length == number of levels in trace. markers : list, optional If given, must have length == number of levels in trace linestyles : list, optional If given, must have length == number of levels in trace. legendloc : {None, str, int} Location passed to the legend command. legendtitle : {None, str} Title of the legend. **kwargs These will be passed to the plot command used either plot or scatter. If you want to control the overall plotting options, use kwargs. Returns ------- Figure The figure given by `ax.figure` or a new instance. Examples -------- >>> import numpy as np >>> np.random.seed(12345) >>> weight = np.random.randint(1,4,size=60) >>> duration = np.random.randint(1,3,size=60) >>> days = np.log(np.random.randint(1,30, size=60)) >>> fig = interaction_plot(weight, duration, days, ... colors=['red','blue'], markers=['D','^'], ms=10) >>> import matplotlib.pyplot as plt >>> plt.show() .. plot:: import numpy as np from statsmodels.graphics.factorplots import interaction_plot np.random.seed(12345) weight = np.random.randint(1,4,size=60) duration = np.random.randint(1,3,size=60) days = np.log(np.random.randint(1,30, size=60)) fig = interaction_plot(weight, duration, days, colors=['red','blue'], markers=['D','^'], ms=10) import matplotlib.pyplot as plt #plt.show() r) DataFramenameresponse__name__z%s of %sXZTraceNcSsg|]}|qSr ).0lr r D/tmp/pip-unpacked-wheel-2v6byqio/statsmodels/graphics/factorplots.py msz$interaction_plot..)xtracer rr-.z(Must be a linestyle for each trace levelz%Must be a marker for each trace levelz$Must be a color for each trace levelZbothr)colormarkerlabel linestyleliner)rrrscatters)rrrzPlot type %s not understood)loctitleg?)pandasrutilsZ create_mpl_axgetattrstrZ set_ylabelZ set_xlabel isinstancenpuniquerlen_recodedictzipgroupbyZ aggregateZ reset_indexr ValueError enumeratevaluesZplotrZlegendZmarginsallZ set_xticksZset_xticklabels)rrr funcZaxZplottypeZxlabelZylabelcolorsmarkersZ linestylesZ legendlocZ legendtitlekwargsrZfigZ response_name func_nameZx_valuesZx_levelsdataZ plot_dataZn_traceir,grouprr r rinteraction_plot szR            r6cCsddlm}d}d}t||r0|j}|j}|j}|jjtj tj fkrNt dnt|t sbt dnrt |t t|kst dnHtj|jdtd}|D]\}}||||k<q|r||||d}|SdS) a8 Recode categorial data to int factor. Parameters ---------- x : array_like array like object supporting with numpy array methods of categorially coded data. levels : dict mapping of labels to integer-codings Returns ------- out : instance numpy.ndarray r)SeriesNzs