def _discretize_by_width(col, num_bins, labels):
maxvalue = col.max()
minvalue = col.min()
width = float((maxvalue-minvalue))/num_bins
bins = [minvalue + x*width for x in range(num_bins)]+[maxvalue]
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)
评论列表
文章目录