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_np_reader_in_pipeline(self):
with TemporaryDirectory() as td:
file_name = os.path.join(td, "test.npy")
data = np.random.random((100, 3))
np.save(file_name, data)
reader = api.source(file_name)
p = api.pipeline(reader, run=False, stride=2, chunksize=5)
p.parametrize()
def test_chunksize(self):
reader_xtc = api.source(self.traj_files, top=self.pdb_file)
chunksize = 1001
chain = [
reader_xtc,
api.tica(),
api.cluster_mini_batch_kmeans(batch_size=0.3, k=3)
]
p = api.pipeline(chain, chunksize=chunksize, run=False)
assert p.chunksize == chunksize
for e in p._chain:
assert e.chunksize == chunksize
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_no_cluster(self):
reader_xtc = api.source(self.traj_files, top=self.pdb_file)
# only reader
api.pipeline(reader_xtc)
reader_xtc.get_output()
# reader + pca / tica
tica = api.tica()
pca = api.pca()
api.pipeline([reader_xtc, tica])._chain[-1].get_output()
api.pipeline([reader_xtc, pca])._chain[-1].get_output()
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.")
def test_set_element(self):
reader = api.source(self.traj_files, top=self.pdb_file)
pca = api.pca()
p = api.pipeline([reader, pca])
self.assertTrue(p._is_estimated())
pca_out = pca.get_output()
tica = api.tica(lag=self.generated_lag)
# replace pca with tica
p.set_element(1, tica)
self.assertFalse(
p._is_estimated(),
"After replacing an element, the pipeline should not be parametrized."
)
p.parametrize()
tica_out = tica.get_output()
# check if replacement actually happened
self.assertFalse(
np.array_equal(pca_out[0], tica_out[0]),
"The output should not be the same when the method got replaced.")