def test_add_element(self):
# start with empty pipeline without auto-parametrization
p = api.pipeline([], run=False)
# add some reader
reader = api.source(self.traj_files, top=self.pdb_file)
p.add_element(reader)
p.parametrize()
# get the result immediately
out1 = reader.get_output()
# add some kmeans
kmeans = api.cluster_kmeans(k=15)
p.add_element(kmeans)
p.parametrize()
# get the result immediately
kmeans1 = kmeans.get_output()
# get reader output again
out2 = reader.get_output()
p.add_element(api.cluster_kmeans(k=2))
p.parametrize()
# get kmeans output again
kmeans2 = kmeans.get_output()
# check if add_element changes the intermediate results
np.testing.assert_array_equal(out1[0], out2[0])
np.testing.assert_array_equal(out1[1], out2[1])
np.testing.assert_array_equal(kmeans1[0], kmeans2[0])
np.testing.assert_array_equal(kmeans1[1], kmeans2[1])
def test_save_dtrajs(self):
reader = source(self.trajfiles, top=self.topfile)
cluster = cluster_kmeans(k=2)
d = Discretizer(reader, cluster=cluster)
d.parametrize()
d.save_dtrajs(output_dir=self.dest_dir)
dtrajs = os.listdir(self.dest_dir)
def test_no_transform(self):
reader_xtc = api.source(self.traj_files, top=self.pdb_file)
api.pipeline([reader_xtc,
api.cluster_kmeans(k=10)])._chain[-1].get_output()
api.pipeline([reader_xtc,
api.cluster_regspace(dmin=10)])._chain[-1].get_output()
api.pipeline([reader_xtc,
api.cluster_uniform_time()])._chain[-1].get_output()
def test_transformer_iterator_random_access(self):
kmeans = coor.cluster_kmeans(self.data, k=2)
kmeans.in_memory = True
for cs in range(0, 5):
kmeans.chunksize = cs
ref_stride = {0: 0, 1: 0, 2: 0}
it = kmeans.iterator(stride=self.stride)
for x in it:
ref_stride[x[0]] += len(x[1])
for key in list(ref_stride.keys()):
expected = len(it.ra_indices_for_traj(key))
assert ref_stride[key] == expected, \
"Expected to get exactly %s elements of trajectory %s, but got %s for chunksize=%s" \
% (expected, key, ref_stride[key], cs)
def test_replace_data_source(self):
reader_xtc = api.source(self.traj_files, top=self.pdb_file)
reader_gen = DataInMemory(data=self.generated_data)
kmeans = api.cluster_kmeans(k=10)
assert hasattr(kmeans, '_chunks')
p = api.pipeline([reader_xtc, kmeans])
out1 = kmeans.get_output()
# replace source
print(reader_gen)
p.set_element(0, reader_gen)
assert hasattr(kmeans, '_chunks')
p.parametrize()
out2 = kmeans.get_output()
self.assertFalse(
np.array_equal(out1, out2),
"Data source changed, so should the resulting clusters.")
def test_is_parametrized(self):
# construct pipeline with all possible transformers
p = api.pipeline([
api.source(self.traj_files, top=self.pdb_file),
api.tica(),
api.pca(),
api.cluster_kmeans(k=50),
api.cluster_regspace(dmin=50),
api.cluster_uniform_time(k=20)
],
run=False)
self.assertFalse(
p._is_estimated(),
"If run=false, the pipeline should not be parametrized.")
p.parametrize()
self.assertTrue(
p._is_estimated(),
"If parametrized was called, the pipeline should be parametrized.")