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

distance and linkage problem #5

Open
finnp opened this issue Dec 12, 2014 · 2 comments
Open

distance and linkage problem #5

finnp opened this issue Dec 12, 2014 · 2 comments

Comments

@finnp
Copy link
Member

finnp commented Dec 12, 2014

Hey,

right now the module requires specifying a distance and a linkage function, whereas distance compares two elements. The linkage function then takes all these elements and returns the closest match.

This works well for single, complete and average link functions as cluster distance measures.

However it doesn't work for Centroids or Ward's method, because they compare clusters without individual element distances.

For example the Centroids cluster distance measure calculates the centroid of a cluster of points and then uses this as a measure. There is no element distance required at all.

I'm not sure how to solve this best api-wise. Maybe have a third parameter clusterDistance that could be used instead of distance and linkage.

Best,
Finn

@jonathanong
Copy link
Contributor

yeah i thought about different methods. it makes the API way too complicated. might be easier just to create another module for those. lol

@finnp
Copy link
Member Author

finnp commented Dec 12, 2014

@jonathanong Yeah that's what I thought. The API now simplifies and restricts to those linkage measures. I think that's okay though, since they are the most used anyway.

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

No branches or pull requests

2 participants