kennedyCzar / HIGH-DIMENSIONAL-DATA-CLUSTERING

Implementation of hierarchical clustering on small n-sample dataset with very high dimension. Together with the visualization results implemented in R and python

HIGH-DIMENSIONAL-DATA-CLUSTERING

Implementation of hierarchical clustering on small n-sample dataset with very high dimension

1. Basically a good visual representation of the data with easily viewable outliers and differently trending data.

2. five subgroups and how they compare to each other in a cluster of devices. Any device that is trending differently or higher compared to others.

3. And device clusters among like kind (device names are similar across the 5 subgroups) that display those out of the pack - outliers.   
   

Clustering results

Optimized cluster value k is 4 in most cases.