ClusterDimensionReductionPlot (CDRP)
A script for making a ClusterDimensionReductionPlot of documents with bokeh. This is a scatterplot in which documents are colored according to their cluster according to a k-means cluster analyses. The positions of the documents in the plot are determiend via pca.
example.py gives an example on how the script can be used.
Full code and documentation can be found in CDRP.py
Python packages that you need that are not in the standard library:
bokeh nltk numpy sklearn textwrap