This same dataset works fine outside of hadoop, with the non-hadoop versions
of logliklihood, slopeone, etc
However, it could be that this code is more sensitive to issues.
When I get a few minutes I think I'm gonna need to look more closely at
these lines:
String[] tokens = TasteHadoopUtils.splitPrefTokens(value.toString());
long itemID = Long.parseLong(tokens[transpose ? 0 : 1]);
...and how data without preferences works
I'll also run on my data with preference values.
Stay tuned!!
S.
On Tue, Aug 10, 2010 at 10:48 AM, Sean Owen <[email protected]> wrote:
> You sure you don't have a blank line or something in there somewhere?
>
> On Tue, Aug 10, 2010 at 8:45 AM, Simon Reavely <[email protected]>
> wrote:
> > My input is csv, of the form
> > userid, itemid
> >
>
--
Simon Reavely
[email protected]
