How outliers are detected ? #1733
Unanswered
rgodet2000
asked this question in
Q&A
Replies: 1 comment
-
|
Hello! If you're talking about the outliers in the TableReport, values that are past the 20- and 80-quantile (on either side) are considered as outliers and will be shown as such in the distribution tab. It's intended to be a rough metric to detect outliers and improve the readability of the plot, rather than being a full-on outlier detection method, and as such there are no plans to expose the parameters so that they can be tweaked. If you're interested in the specific code that does that, you can find it in Does that answer your question? |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hello,
I tried skrub for the first time and I try to understand how the outliers detection works.
Thanks in advance for your help :)
Beta Was this translation helpful? Give feedback.
All reactions