Custom binning boundary to approach Gaussian histogram
发布于2024-10-31 20:32 阅读(526) 评论(0) 点赞(12) 收藏(4)
I'd like to compute custom bin edges so that the new histogram shape will approach Gaussian. Think of the shape you'll get after Box-Cox transformation, but I want to keep the original values.
These new bin edges will be fed into histplot or distplot in python. I've read of qcut
but that will make the shape approaching uniform distribution.
Example in chart below :
- Bins could be 0-2, 2-30, 30-50, etc.
- Or keep 0 apart as it's outlier. Bins then could be 0, 1-10, 10-25, etc. How would you modify approach to skip 0 in the calculation of new bin edges ?
Surprisingly I have not been able to find a solution for python.
The closest question is in Matlab Specifying bin edges when fitting a normal distribution using histfit
解决方案
暂无回答
所属网站分类: 技术文章 > 问答
作者：黑洞官方问答小能手
链接：https://www.pythonheidong.com/blog/article/2040404/1c0e9868b8a85bbc285c/
来源：python黑洞网
任何形式的转载都请注明出处,如有侵权 一经发现 必将追究其法律责任
昵称:
评论内容：(最多支持255个字符)
---无人问津也好，技不如人也罢，你都要试着安静下来，去做自己该做的事，而不是让内心的烦躁、焦虑，坏掉你本来就不多的热情和定力