Improve test case for KMeans clustering

[skekre98]

Description of feature/enhancement Currently the test for the KMeans algorithm is just making sure the number of clusters created is accurate. https://github.com/skekre98/NBA-Search/blob/7583cb5224c2f741121d6e59d92b580e83809a06/test.py#L24

This is not an ideal way of checking the accuracy of the algorithm. The test case needs improvement.

Description of implementation This test should ideally check other features such as similarity between clusters as well as average distance from other clusters.

Why this is a good feature/enhancement This algorithm will probably play a big role in identifying niches and groups of talent amongst players. Ideally this should be a well built out function and this test will help in that.

Additional context Not in the scope of this issue, but might be good to start thinking about how to make clustering more uniform and reduce bias.

[araetoro]

Hi skekre98, sounds fun, I would like to work on this issue.

[skekre98]

@araetoro thanks! I will go ahead and assign it to you.

[skekre98]

@araetoro any update on this issue?

[araetoro]

Sorry I'm slammed with work and school projects so if someone else would like to take this ticket go for it!

On Thu, Nov 12, 2020, 11:53 AM Aaron Kelley [email protected] wrote:

Hi @skekre98 https://github.com/skekre98, is this issue up for grabs? I'd like to work on it if possible.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/skekre98/NBA-Search/issues/33#issuecomment-726270969, or unsubscribe https://github.com/notifications/unsubscribe-auth/AJ42NDGFHQXKI2UPAFRPCGDSPQVJDANCNFSM4SCI6AUA .

[shivangigujar23]

Hey, Is this issue up for grab? If yes, I would like to do enhancement.

[skekre98]

Yes, please feel free to take it up 😄, Thanks!

[pragyasrivastava0805]

Hi is this issue still open?I would like to work on this

[khanhak]

Is this issue still open? I'd like to work on it if it is