Method for quickly interpreting clusters
Closed this issue · 1 comments
elliottash commented
It would be good to add a method for showing the (e.g.) top 20 words in each embedding cluster. Right now that has to be done manually.
-- we have Counters in the narrative model class, make it easy to access those and use the .most_common() method.
PinchOfData commented
Implemented in the branch relatio-v0.3 (method self.inspect_cluster() of the NarrativeModel())