def test_coarsen_chunks(self):
"""Just basic testing for now"""
chunks = [1,1,2,2,3,3,4,4]
ds = dataset_wizard(samples=np.arange(len(chunks)).reshape(
(len(chunks),1)), targets=[1]*8, chunks=chunks)
coarsen_chunks(ds, nchunks=2)
chunks1 = coarsen_chunks(chunks, nchunks=2)
self.failUnless((chunks1 == ds.chunks).all())
self.failUnless((chunks1 == np.asarray([0,0,0,0,1,1,1,1])).all())
ds2 = dataset_wizard(samples=np.arange(len(chunks)).reshape(
(len(chunks),1)), targets=[1]*8, chunks=range(len(chunks)))
coarsen_chunks(ds2, nchunks=2)
self.failUnless((chunks1 == ds.chunks).all())
def test_coarsen_chunks(self):
"""Just basic testing for now"""
chunks = [1, 1, 2, 2, 3, 3, 4, 4]
ds = dataset_wizard(samples=np.arange(len(chunks)).reshape(
(len(chunks), 1)),
targets=[1] * 8,
chunks=chunks)
coarsen_chunks(ds, nchunks=2)
chunks1 = coarsen_chunks(chunks, nchunks=2)
self.failUnless((chunks1 == ds.chunks).all())
self.failUnless((chunks1 == np.asarray([0, 0, 0, 0, 1, 1, 1,
1])).all())
ds2 = dataset_wizard(samples=np.arange(len(chunks)).reshape(
(len(chunks), 1)),
targets=[1] * 8,
chunks=range(len(chunks)))
coarsen_chunks(ds2, nchunks=2)
self.failUnless((chunks1 == ds.chunks).all())
def _get_split_config(self, uniqueattrs):
"""
Returns
-------
list of tuples (None, list of int)
Indices for splitting
"""
# make sure there are more of attributes than desired groups
if len(uniqueattrs) < self.__ngroups:
raise ValueError, "Number of groups (%d) " % (self.__ngroups) + \
"must be less than " + \
"or equal to the number of unique attributes (%d)" % \
(len(uniqueattrs))
# use coarsen_chunks to get the split indices
split_ind = coarsen_chunks(uniqueattrs, nchunks=self.__ngroups)
split_ind = np.asarray(split_ind)
# loop and create splits
split_list = [(None, uniqueattrs[split_ind == i])
for i in range(self.__ngroups)]
return split_list
def _get_partition_specs(self, uniqueattrs):
"""
Returns
-------
list of tuples (None, list of int)
Indices for splitting
"""
# make sure there are more of attributes than desired groups
if len(uniqueattrs) < self.__ngroups:
raise ValueError("Number of groups (%d) " % (self.__ngroups) + \
"must be less than " + \
"or equal to the number of unique attributes (%d)" % \
(len(uniqueattrs)))
# use coarsen_chunks to get the split indices
split_ind = coarsen_chunks(uniqueattrs, nchunks=self.__ngroups)
split_ind = np.asarray(split_ind)
# loop and create splits
split_list = [(None, uniqueattrs[split_ind==i])
for i in range(self.__ngroups)]
return split_list
