Skip to content
This repository has been archived by the owner on Sep 8, 2021. It is now read-only.

Numerical Columns splitting is not correct #2

Open
keckelt opened this issue Jan 4, 2018 · 1 comment
Open

Numerical Columns splitting is not correct #2

keckelt opened this issue Jan 4, 2018 · 1 comment
Labels
status: wontfix This will not be worked on type: bug Something isn't working

Comments

@keckelt
Copy link
Member

keckelt commented Jan 4, 2018

If there a value is present multiple times, the current algorithm may split at one of these values

The current algorithm does not conider values that occur multiple times and thus may split like:

  • Value: 70 Group A
  • Value: 72 Group A
  • Value: 72 Group A
  • Value: 72 Group A -------------------------
  • Value: 72 Group B
  • Value: 75 Group B

values should be binned like i did in matlab: https://gist.github.com/keckelt/f268ad0d99217c8a77fc7edd24ede461

@keckelt
Copy link
Member Author

keckelt commented Mar 26, 2018

Count missing values as seperate group, as Ordino also makes a group for missing values.

@keckelt keckelt self-assigned this Mar 26, 2018
@keckelt keckelt added the type: bug Something isn't working label Mar 26, 2018
@keckelt keckelt added the status: wontfix This will not be worked on label Feb 24, 2020
@keckelt keckelt removed their assignment Feb 24, 2020
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
status: wontfix This will not be worked on type: bug Something isn't working
Projects
None yet
Development

No branches or pull requests

1 participant