stat_summary_bin.py 文件源码

def compute_group(cls, data, scales, **params):
        bins = params['bins']
        breaks = params['breaks']
        binwidth = params['binwidth']
        boundary = params['boundary']

        func = make_summary_fun(params['fun_data'], params['fun_y'],
                                params['fun_ymin'], params['fun_ymax'],
                                params['fun_args'])

        breaks = fuzzybreaks(scales.x, breaks, boundary, binwidth, bins)
        data['bin'] = pd.cut(data['x'], bins=breaks, labels=False,
                             include_lowest=True)

        def func_wrapper(data):
            """
            Add `bin` column to each summary result.
            """
            result = func(data)
            result['bin'] = data['bin'].iloc[0]
            return result

        # This is a plyr::ddply
        out = groupby_apply(data, 'bin', func_wrapper)
        centers = (breaks[:-1] + breaks[1:]) * 0.5
        bin_centers = centers[out['bin'].values]
        out['x'] = bin_centers
        out['bin'] += 1
        if isinstance(scales.x, scale_discrete):
            out['width'] = 0.9
        else:
            out['width'] = np.diff(breaks)[bins-1]

        return out