I am trying to cluster some text documents. I am using TfIdfTransformer and DBSCAN. I get the result in array format with some array groups with score numbers. What i like is to map this output with the actual samples, to find out which actual documents are clustered together, is there any easy way to map it ?
I am trying to cluster some text documents. I am using TfIdfTransformer and DBSCAN. I get the result in array format with some array groups with score numbers. What i like is to map this output with the actual samples, to find out which actual documents are clustered together, is there any easy way to map it ?