data.py 文件源码

def is_not_uniform(idx, nbins=10, allowed_gap=0.75):
        idx_bins = pd.cut(idx, bins=nbins, labels=False)
        idx_bin_size = np.bincount(idx_bins)

        diff = idx_bin_size[:-1] - idx_bin_size[1:]
        monotonic = (diff < 0).all() or (diff > 0).all()
        huge_gap = (idx_bin_size.min()*1.0 / idx_bin_size.max()) < allowed_gap
        return monotonic or huge_gap