DBSTREAM: multiple issues #1324
Assignees
Comments
|
Hey @hoanganhngo610, do you have time to take a look at this issue? :) |
|
@MaxHalford I will have a look at the issues by the end of this week. Also, thank you @donny741 for raising the issues! |
|
@donny741 @MaxHalford I have just made a PR to fix the points that @donny741 proposed within this issue. Hope that the changes are satisfactory. If you have some time, please do not hesitate to have a look through the PR and leave comments wherever necessary! |
|
Good job! Just merged the PR. @donny741 I'll let you close the issue if you're satisfied |
MaxHalford
pushed a commit
that referenced
this issue
Oct 9, 2023
* Adding negative signs before fading_factor for steps within Algoritjm 2 of the paper by Hashler and Bolanos to allow clusters with low weight removed. * Change clustering_is_up_to_date to True after every time the function recluster is called. * initiate new micro cluster based on the maximum key of the existing micro clusters, or indexed as 0 if the list of micro clusters is still empty. * Add description to the UNRELEASED.md file
|
Looks good! Thank you! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi, I'm new to Python and data science, and I'm currently exploring the clustering algorithms. When comparing the DBSTREAM algorithm implementation with the original paper I noticed some inconsistencies:
-signs before thefading_factorare missing here and here what prevents the clusters with low weight from being removedmicro_clusterslist is used as an index key when creating the new cluster (here) what can override the existing clusters because the length is decremented when clusters are removed from the list (here)clustering_is_up_to_datevariable introduced with this PR is never being set toTrueThe text was updated successfully, but these errors were encountered: