-
Notifications
You must be signed in to change notification settings - Fork 177
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
Improve the prediction technique #222
Conversation
…exemplars as noise, rather than requiring points to be close to noise point exemplars. Signed-off-by: Geoffrey Stewart <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you add a test loading in a 4.2 model and asserting that the predictions are the same as they are in 4.2? We've done this before in cases where the on-disk format changed and it's a useful check to make sure nothing broke. Otherwise it looks good.
Clustering/Hdbscan/src/main/java/org/tribuo/clustering/hdbscan/HdbscanModel.java
Show resolved
Hide resolved
Clustering/Hdbscan/src/main/java/org/tribuo/clustering/hdbscan/HdbscanTrainer.java
Show resolved
Hide resolved
Clustering/Hdbscan/src/main/java/org/tribuo/clustering/hdbscan/HdbscanTrainer.java
Outdated
Show resolved
Hide resolved
…dictions made using outlier points
…tions are correct
Clustering/Hdbscan/src/test/java/org/tribuo/clustering/hdbscan/TestHdbscan.java
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good apart from the small note about keeping the comments up to date.
Clustering/Hdbscan/src/main/java/org/tribuo/clustering/hdbscan/HdbscanTrainer.java
Outdated
Show resolved
Hide resolved
Clustering/Hdbscan/src/test/java/org/tribuo/clustering/hdbscan/TestHdbscan.java
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM.
Improve the prediction technique by identifying points far away from exemplars as noise, rather than requiring such points to be close to noise point exemplars.
In addition to the unit tests, the quality of these prediction technique changes have been verified using existing notebooks available in this repo/branch.