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] Correlations: fixes and enhancements #3591

Merged
merged 6 commits into from
Feb 22, 2019

Conversation

VesnaT
Copy link
Contributor

@VesnaT VesnaT commented Feb 11, 2019

Issue

Fixes #3504
Heuristic will be updates in a following PR.

Description of changes
  • Send outputs when feed data
  • Split attribute pairs into two columns
  • Output p-values
  • Compute correlations with chosen feature
Includes
  • Code changes
  • Tests
  • Documentation

@VesnaT VesnaT changed the title Correlations: fixes and enhancements [ENH] Correlations: fixes and enhancements Feb 11, 2019
Orange/widgets/data/owcorrelations.py Show resolved Hide resolved
Orange/widgets/data/owcorrelations.py Outdated Show resolved Hide resolved
metas = [StringVariable("Feature 1"), StringVariable("Feature 2")]
domain = Domain([ContinuousVariable("Correlation")], metas=metas)
metas = list(map(StringVariable, ["Feature 1", "Feature 2"]))
attrs = list(map(ContinuousVariable, ["Correlation", "p-Value"]))
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I object to calling this a "p-value". I hope I haven't written https://blog.biolab.si/2019/01/04/how-to-abuse-p-values-in-correlations/ in vain. :)

As soon as we call this a p-value, people will call the top 5% correlations (or more, if the data is not random) statistically significant.

@BlazZupan, any ideas how to call this?

@@ -91,6 +91,7 @@ class CorrelationRank(VizRankDialogAttrPair):
POSITIVE_COLOR = QColor(170, 242, 43)

threadStopped = Signal()
pValRole = next(gui.OrangeUserRole)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'd prefer go with the naming style (not statistics) and call this PValRole.

Well, I'd sure prefer calling this role something completely else, as noted in another comment.

Orange/widgets/data/owcorrelations.py Outdated Show resolved Hide resolved
Orange/widgets/data/owcorrelations.py Show resolved Hide resolved
@janezd janezd self-assigned this Feb 14, 2019
@janezd janezd added the needs discussion Core developers need to discuss the issue label Feb 15, 2019
@janezd janezd removed their assignment Feb 15, 2019
@codecov
Copy link

codecov bot commented Feb 18, 2019

Codecov Report

❗ No coverage uploaded for pull request base (master@2056481). Click here to learn what that means.
The diff coverage is 97.82%.

@@            Coverage Diff            @@
##             master    #3591   +/-   ##
=========================================
  Coverage          ?   84.03%           
=========================================
  Files             ?      370           
  Lines             ?    67080           
  Branches          ?        0           
=========================================
  Hits              ?    56368           
  Misses            ?    10712           
  Partials          ?        0

@codecov
Copy link

codecov bot commented Feb 18, 2019

Codecov Report

Merging #3591 into master will increase coverage by 0.04%.
The diff coverage is 94.7%.

@@            Coverage Diff             @@
##           master    #3591      +/-   ##
==========================================
+ Coverage   84.07%   84.11%   +0.04%     
==========================================
  Files         370      370              
  Lines       67268    67364      +96     
==========================================
+ Hits        56554    56664     +110     
+ Misses      10714    10700      -14

@janezd
Copy link
Contributor

janezd commented Feb 22, 2019

We decided to replace p-Value with False discovery rate.

@janezd janezd removed the needs discussion Core developers need to discuss the issue label Feb 22, 2019
@janezd janezd merged commit cbfcbca into biolab:master Feb 22, 2019
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.

2 participants