Just curious, has anyone tried to use Lucene to do "frequent itemset"
computation for auto-clustering. For a given pair of items/words we can use
lucene and do a conjunctive search from those items. Only if we can figure out
a way to minimize the number of possible itemsets.
Thanks,
Prasen
-
Hi folks,
I have a requirement where I want to keep adding deltas (incremental
terms) to a particular document in a lucene index, and get these
additional terms indexed to the SAME document in the index. Is there an
easy/smart way to do it without changing much of lucene ? Deleting and
addi