Kyle Beauchamp
Kyle Beauchamp
Also: IMHO eliminate the ProjectInfo.yaml inputs to scripts, as they get set by default. I think that will help people stay focused on the tICA-specific details.
If you do end up merging the theory + applications into a single sphinx file, could you move the link to sit under the "Documentation" section on the main docs...
Again, let me know if you run out of time and I can file a PR for some of this stuff.
So should I use k-centers or k-medoids when clustering my tICA results? Because we're working in the eigenvector space, I imagine that either one of the following is true: 1....
Thanks. Have you ever done k-means? E.g. do I have to update Cluster.py?
I think I answered my own question ``` Cluster.py tica atompairs: error: argument alg: invalid choice: 'kmeans' (choose from 'kcenters', 'hybrid', 'clarans', 'sclarans', 'hierarchical') ```
We do have a commented-out KMeans class in `clustering.py`...
IMHO it looks _highly_ suspicious.
If we want kmeans, we should definitely just wrap sklearn.
Hey our tICA pipeline is 100% streaming, which is a huge memory advantage over the previous RMSD-based pipeline. This is a huge win that we should advertise.