RedHatInsights / aiops-insights-clustering

Clustering of systems
GNU General Public License v3.0
1 stars 14 forks source link

Cluster200 #23

Closed TreeinRandomForest closed 5 years ago

TreeinRandomForest commented 5 years ago

Change Log:

  1. Cleaned up internal APIs of clustering.train.Cluster class so the pipeline is more rigid and every preprocessing step has to be run.
  2. Added clustering/config.py that contains problem-specific attributes like columns to drop, range of n_clusters for scanning, storage locations etc.
  3. clustering.inference has been fixed to match the new API in train
  4. test script showcasing usage added in tests/
  5. added multiprocessing option for scanning n_clusters

@durandom could you please review changes and merge if it looks good?