Skip to content

minor fixes to the Compas example - #82

Open
LiFaytheGoblin wants to merge 2 commits into
dssg:masterfrom
LiFaytheGoblin:master
Open

minor fixes to the Compas example#82
LiFaytheGoblin wants to merge 2 commits into
dssg:masterfrom
LiFaytheGoblin:master

Conversation

@LiFaytheGoblin

@LiFaytheGoblin LiFaytheGoblin commented Jun 19, 2020

Copy link
Copy Markdown

I intent to fix
#79
#80
#81

  • I switched the variable names that got mixed up
  • I reworded "equally likely to predict" to "equally likely to incorrectly predict"
  • I reworded "We can see from the longer bars" to "We can see from the absolute number of occurances given next to a bar"

@lorenh516 lorenh516 left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Thanks for these notes Linda, good eye! Two changes look good, but re: #79 group size is a secondary notation. It'd be best to instead highlight what the bars are showing, so "We can see from the longer bars that across 'age_cat', 'sex', and 'race' attributes, the groups COMPAS incorrectly predicts as 'low' or 'medium' risk most often are 25-45, Male, and African American." --> "We can see from the longer bars that across 'age_cat', 'sex', and 'race' attributes, the groups COMPAS incorrectly predicts as 'low' or 'medium' risk most often are Greater than 45, Female, and Other race.". If you make that change I will do another quick pass and then should be able to merge, or if you prefer, you can revert this part and I'll make that edit.

@LiFaytheGoblin

Copy link
Copy Markdown
Author

Thanks for the feedback @lorenh516 and you're welcome. See my updated changes.

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