Ooops, my mistake, I was looking at older movies.dat file :P


On Wed, Feb 3, 2010 at 10:54 PM, Sean Owen <[email protected]> wrote:

> That really shouldn't be possible, are you sure?
> The movie IDs go up to 65133 (see movies.dat), not 10000.
>
> On Thu, Feb 4, 2010 at 12:48 AM, Vinicius Carvalho
> <[email protected]> wrote:
> > Hi there! I'm trying the item recomender, but it seems that the
> > RecommendedItem returned by recommender.recommend(uid,howmany) is a user
> not
> > an item.
> >
> > using the ratings.dat provided by movie lens, the GroupLensDataModel
> > provided in the example:
> >
> > //datamodel is the GroupLensDataModel
> > ItemSimilarity similarity = new PearsonCorrelationSimilarity(datamodel);
> > Recommender r  = new GenericItemBasedRecommender(datamodel, similarity);
> > r.recommend(1234,10);
> >
> > The values do not appear to be items as some ids are really high (above
> the
> > 10k movie limit of the dataset)
> >
> > Is anything wrong with this code?
> >
> > --
> > The intuitive mind is a sacred gift and the
> > rational mind is a faithful servant. We have
> > created a society that honors the servant and
> > has forgotten the gift.
> >
>



-- 
The intuitive mind is a sacred gift and the
rational mind is a faithful servant. We have
created a society that honors the servant and
has forgotten the gift.

Reply via email to