An example of using the API to cluster the documents in the well-known 20
news groups data. See the classification example above for more details
about the corpus.
Example command line to get 10 clusters using euclidean distance and
requiring each word/feature to have been seen 20 times or more.
$ nak run nak.example.TwentyNewsGroupsKmeansExample -k 20 -d e -c 20 20news/20news-bydate-train
An example of using the API to cluster the documents in the well-known 20 news groups data. See the classification example above for more details about the corpus.
Example command line to get 10 clusters using euclidean distance and requiring each word/feature to have been seen 20 times or more.
$ nak run nak.example.TwentyNewsGroupsKmeansExample -k 20 -d e -c 20 20news/20news-bydate-train