HIERDENC
    
            
                
                    Clustering of categorical data sets with locality-sensitive hashing
                
            
             
            
             
            
        
            This is a tool for retrieving nearest neighbors and clustering of large categorical data sets repesented in transactional form.
The clustering is achieved via a locality-sensitive hashing of categorical datasets for speed and scalability.
The locality-sensitive hashing method implemented is described in the video lectures under www.mmds.org (Chapter 3).
Information needed for LSH, such as shingles/tokens, MinHash signatures, band hashes to buckets
are stored in several database tables...