Fields doc_id = new Fields( "doc_id" );
Fields tally = new Fields( "tally" );
Fields rhs_join = new Fields( "rhs_join" );
Fields n_docs = new Fields( "n_docs" );
Pipe dPipe = new Unique( "D", tokenPipe, doc_id );
dPipe = new Each( dPipe, new Insert( tally, 1 ), Fields.ALL );
dPipe = new Each( dPipe, new Insert( rhs_join, 1 ), Fields.ALL );
dPipe = new SumBy( dPipe, rhs_join, tally, n_docs, long.class );
// one branch tallies the token counts for document frequency (DF)
Pipe dfPipe = new Unique( "DF", tokenPipe, Fields.ALL );
Fields df_count = new Fields( "df_count" );
dfPipe = new CountBy( dfPipe, token, df_count );
Fields df_token = new Fields( "df_token" );
Fields lhs_join = new Fields( "lhs_join" );
dfPipe = new Rename( dfPipe, token, df_token );
dfPipe = new Each( dfPipe, new Insert( lhs_join, 1 ), Fields.ALL );
// join to bring together all the components for calculating TF-IDF
// the D side of the join is smaller, so it goes on the RHS
Pipe idfPipe = new HashJoin( dfPipe, lhs_join, dPipe, rhs_join );