def __init__(self, sklearn_cv_obj, **kwargs):
splitrule = []
for _, test in sklearn_cv_obj:
splitrule+=[(None, test)]
CustomPartitioner.__init__(self, splitrule, **kwargs)
def test_gnbsearghlight_exclude_partition(self):
# just a smoke test with a custom partitioner
ds1 = datasets['3dsmall'].copy(deep=True)
gnb_sl = GNBSearchlight(GNB(),
generator=CustomPartitioner([([0], [1])]),
qe=IndexQueryEngine(myspace=Sphere(2)),
errorfx=None)
res = gnb_sl(ds1)
def test_splitter_gnbsearghlight(self):
ds1 = datasets['3dsmall'].copy(deep=True)
gnb_sl = GNBSearchlight(GNB(),
generator=CustomPartitioner([([0], [1])]),
qe=IndexQueryEngine(myspace=Sphere(2)),
splitter=Splitter(attr='partitions',
attr_values=[1, 2]),
errorfx=None)
res = gnb_sl(ds1)
assert_equal(res.nsamples, (ds1.chunks == 1).sum())
def test_gnbsearchlight_3partitions_and_splitter(self):
ds = self.dataset[:, :20]
# custom partitioner which provides 3 partitions
part = CustomPartitioner([([2], [3], [1])])
gnb_sl = sphere_gnbsearchlight(GNB(), part)
res_gnb_sl = gnb_sl(ds)
# compare results to full blown searchlight
sl = sphere_searchlight(CrossValidation(GNB(), part))
res_sl = sl(ds)
assert_datasets_equal(res_gnb_sl, res_sl)
# and theoretically for this simple single cross-validation we could
# just use Splitter
splitter = Splitter('chunks', [2, 3])
# we have to put explicit None since can't become a kwarg in 1 day any
# longer here
gnb_sl_ = sphere_gnbsearchlight(GNB(), None, splitter=splitter)
res_gnb_sl_ = gnb_sl_(ds)
assert_datasets_equal(res_gnb_sl, res_gnb_sl_)
def get_partitioner(split_attr='group_split'):
splitter = Splitter(attr='partitions', attr_values=(2, 3))
if split_attr == 'group_split':
splitrule = [
# (leave, training, testing)
(['3', '4'], ['1'], ['2']),
(['3', '4'], ['2'], ['1']),
(['1'], ['2'], ['3', '4']),
(['2'], ['1'], ['3', '4']),
(['1', '2'], ['3'], ['4']),
(['1', '2'], ['4'], ['3']),
(['3'], ['4'], ['1', '2']),
(['4'], ['3'], ['1', '2']),
]
partitioner = CustomPartitioner(splitrule=splitrule, attr=split_attr)
elif split_attr == 'subject':
partitioner = MemoryGroupSubjectPartitioner(group_attr='group_split',
subject_attr=split_attr,
attr=split_attr)
elif split_attr == "group_mdm":
partitioner = LeaveOneSubjectPerGroupPartitioner(
group_attr='group', subject_attr="subject", attr="subject")
elif split_attr == "subject_ofp":
partitioner = partitioner = NFoldPartitioner(attr="subject")
splitter = Splitter(attr="partitions")
elif split_attr == 'group':
partitioner = NFoldPartitioner(attr=split_attr)
splitter = Splitter(attr='partitions')
return partitioner, splitter