public override int Id(int i)
{
return(_ds.Id(i));
}
public override int Id(int i)
{
return(_ds.Id(_samples[i]));
}
public override void TrainDense(IDataset ds)
{
//PSet("%nsamples", ds.nSamples());
float split = PGetf("cv_split");
int mlp_cv_max = PGeti("cv_max");
if (crossvalidate)
{
// perform a split for cross-validation, making sure
// that we don't have the same sample in both the
// test and the training set (even if the data set
// is the result of resampling)
Intarray test_ids = new Intarray();
Intarray ids = new Intarray();
for (int i = 0; i < ds.nSamples(); i++)
ids.Push(ds.Id(i));
NarrayUtil.Uniq(ids);
Global.Debugf("cvdetail", "reduced {0} ids to {1} ids", ds.nSamples(), ids.Length());
NarrayUtil.Shuffle(ids);
int nids = (int)((1.0 - split) * ids.Length());
nids = Math.Min(nids, mlp_cv_max);
for (int i = 0; i < nids; i++)
test_ids.Push(ids[i]);
NarrayUtil.Quicksort(test_ids);
Intarray training = new Intarray();
Intarray testing = new Intarray();
for (int i = 0; i < ds.nSamples(); i++)
{
int id = ds.Id(i);
if (ClassifierUtil.Bincontains(test_ids, id))
testing.Push(i);
else
training.Push(i);
}
Global.Debugf("cvdetail", "#training {0} #testing {1}",
training.Length(), testing.Length());
PSet("%ntraining", training.Length());
PSet("%ntesting", testing.Length());
Datasubset trs = new Datasubset(ds, training);
Datasubset tss = new Datasubset(ds, testing);
TrainBatch(trs, tss);
}
else
{
TrainBatch(ds, ds);
}
}
