K-Means Clustering ================== .. moduleauthor:: Chris Diesch This is a toolset for performing k-means clustering on a library for the purpose of improving our classification engines and library quality using python scripts. This toolset has intentionally separated much of the functionality into small easy to use and understand 'chunks'. The next step is to create a 'k-means setup' script which will handle setting up the clusters and a separate 'k-means classify' script which will be responsible for classifying a document based on those clusters. .. toctree:: :maxdepth: 2 Dictionary.rst DoctypeCenter.rst GetDoctypeCenters.rst GetClosestCenter.rst DocumentDistance.rst