def testApplyMapper(self):
"""Test creation of new dataset by applying a mapper"""
mapper = MaskMapper(N.array([1, 0, 1]))
dataset = Dataset(samples=N.arange(12).reshape((4, 3)), labels=1, chunks=1)
seldataset = dataset.applyMapper(featuresmapper=mapper)
self.failUnless((dataset.selectFeatures([0, 2]).samples == seldataset.samples).all())
# Lets do simple test on maskmapper reverse since it seems to
# do evil things. Those checks are done only in __debug__
if __debug__:
# should fail since in mask we have just 2 features now
self.failUnlessRaises(ValueError, mapper.reverse, [10, 20, 30])
self.failUnlessRaises(ValueError, mapper.forward, [10, 20])
def testSimple(self):
data = N.arange(24).reshape(8,3)
labels = [0, 1] * 4
chunks = N.repeat(N.array((0,1)),4)
# correct results
csamples = [[3, 4, 5], [6, 7, 8], [15, 16, 17], [18, 19, 20]]
clabels = [0, 1, 0, 1]
cchunks = [0, 0, 1, 1]
ds = Dataset(samples=data, labels=labels, chunks=chunks)
# default behavior
m = SampleGroupMapper()
# error if not trained
self.failUnlessRaises(RuntimeError, m, data)
# train mapper first
m.train(ds)
self.failUnless((m.forward(ds.samples) == csamples).all())
self.failUnless((m.forward(ds.labels) == clabels).all())
self.failUnless((m.forward(ds.chunks) == cchunks).all())
# directly apply to dataset
# using untrained mapper!
mapped = ds.applyMapper(samplesmapper=SampleGroupMapper())
self.failUnless(mapped.nsamples == 4)
self.failUnless(mapped.nfeatures == 3)
self.failUnless((mapped.samples == csamples).all())
self.failUnless((mapped.labels == clabels).all())
self.failUnless((mapped.chunks == cchunks).all())
# make sure origids get regenerated
self.failUnless((mapped.origids == range(4)).all())
