R help - Feb 2005 - algorithms for matching and Hungarian method

Hi all,

I would like to match two partitions. That is, if I have exactly the 
same objects grouped
together for the two partitions, the labels may be arbitrarly permuted. 
and so, i would like
to know the correspondances of the groups between the two clusterings.

In the e1701 pachage, it is possible to use the function  matchClasses() 
for this problem. The problem is that
for k greater than 10 (k number of classes), I have a memory problem. So 
I would like to know
if this function explicitly examine all k! possible matches, or if it 
uses the Hungarian
method (or an other optimal algorithm).  If not, do you know if I can 
find one.

Best regards

>>>>> Martin Olivier writes:
> Hi all,
> I would like to match two partitions. That is, if I have exactly the
> same objects grouped together for the two partitions, the labels may
> be arbitrarly permuted.  and so, i would like to know the
> correspondances of the groups between the two clusterings.
> In the e1701 pachage, it is possible to use the function
> matchClasses() for this problem. The problem is that for k greater
> than 10 (k number of classes), I have a memory problem. So I would
> like to know if this function explicitly examine all k! possible
> matches, or if it uses the Hungarian method (or an other optimal
> algorithm).  If not, do you know if I can find one.
e1071::matchClasses() does not.

However, clue::solve_LSAP() provides an implementation of the Hungarian
method for solving the LSAP.

Of course, you can also use the Simplex algorithm for solving the LSAP,
and in fact lpSolve::lp.assign() does that for you.

Hth
-k