Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[ENH] Feature Statistics: Add median #5325

Merged
merged 1 commit into from
Mar 19, 2021

Conversation

janezd
Copy link
Contributor

@janezd janezd commented Mar 10, 2021

Issue

Resolves #5317.

Description of changes
  • Add a column with median
  • Show the most frequent value of discrete values in column with medians rather than with means,
  • Rename column "Center" to "Mean"
Includes
  • Code changes
  • Tests
  • Documentation

@janezd janezd force-pushed the featurestatistics-add-median branch from 90271ac to 395f2e4 Compare March 12, 2021 09:58
@codecov
Copy link

codecov bot commented Mar 12, 2021

Codecov Report

Merging #5325 (395f2e4) into master (69e580d) will decrease coverage by 0.01%.
The diff coverage is 54.54%.

@@            Coverage Diff             @@
##           master    #5325      +/-   ##
==========================================
- Coverage   85.35%   85.34%   -0.02%     
==========================================
  Files         301      301              
  Lines       62035    62043       +8     
==========================================
- Hits        52950    52948       -2     
- Misses       9085     9095      +10     

@janezd
Copy link
Contributor Author

janezd commented Mar 12, 2021

That's it - tests don't cover sorting, but that's also the case for most other scores, and there's also not much to test, so I won't add them.

@irgolic
Copy link
Member

irgolic commented Mar 19, 2021

This is cool. I think mean/median is much more transparent and easy to understand than center.

Sidenote:

Dispersion is confusing too, similarly as center was. I had to open the documentation to understand what the values meant. This information could easily be in a tooltip when hovering over the column/column header. Also, the docs show a really old screenshot, which still has a controlArea/mainArea split. Having docs is great, but having out-of-date docs is not. However, keeping them up-to-date by hand is a three-man full-time-job. Let's talk about this over tea.

@irgolic irgolic merged commit 3660237 into biolab:master Mar 19, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Add median to Feature Statistics
2 participants