discretizer.py 文件源码

def _discretize_by_frequency(col, num_bins, labels):
    percent = 1.0/num_bins
    bins = sorted(list(set(col.quantile([x*percent for x in range(num_bins+1)]))))
    if len(bins)-1 < num_bins:
        num_bins = len(bins)-1
        print('...Only %d bins (unbalanced) generated due to overlapping percentile boundaries.'%num_bins)
    if labels:
        if len(labels)!=num_bins:
            raise ValueError('Length of assigned labels not consistent with num_bins!')
        else:
            group_names = labels
    else:
        group_names = range(num_bins)
    return pd.cut(col, bins,labels=group_names, include_lowest=True)