On 03/18/2012 01:07 PM, Lars Buitinck wrote: > Op 18 maart 2012 08:00 heeft Shankar Satish<[email protected]> > het volgende geschreven: > >> The first thing to decide would be how to represent the DAG. For that, i >> could either use something like py_graph, or roll my own, like so: >> >> dag = {'A': ['B', 'C'], >> 'B': ['C', 'D']} >> > I don't think such a representation will scale up nicely. Usually, we > represent graphs as adjacency matrices using scipy.sparse. > >
The idea was to give each node potential manually. So there will be a dict of marginal distributions that is as big as the graph. Given that, I don't think that the DAG representation will play such a big role. ------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
