def test_discretizer(self):
reader_gen = DataInMemory(data=self.generated_data)
# check if exception safe
api.discretizer(reader_gen)._chain[-1].get_output()
api.discretizer(reader_gen, transform=api.tica())._chain[-1].get_output()
api.discretizer(reader_gen, cluster=api.cluster_uniform_time())._chain[-1].get_output()
api.discretizer(reader_gen, transform=api.pca(), cluster=api.cluster_regspace(dmin=10))._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(self):
reader = source(self.trajfiles, top=self.topfile)
pcat = pca(dim=2)
n_clusters = 2
clustering = UniformTimeClustering(n_clusters=n_clusters)
D = Discretizer(reader, transform=pcat, cluster=clustering)
D.parametrize()
self.assertEqual(len(D.dtrajs), len(self.trajfiles))
for dtraj in clustering.dtrajs:
unique = np.unique(dtraj)
self.assertEqual(unique.shape[0], n_clusters)
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_parametrized())
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_parametrized(), "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.")
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_parametrized(), "If run=false, the pipeline should not be parametrized.")
p.parametrize()
self.assertTrue(p._is_parametrized(), "If parametrized was called, the pipeline should be parametrized.")
def test(self):
reader = feature_reader(self.trajfiles, self.topfile)
# select all possible distances
pairs = np.array(
[x for x in itertools.combinations(range(self.n_residues), 2)])
#reader.featurizer.distances(pairs)
pcat = pca(dim=2)
n_clusters = 2
clustering = UniformTimeClustering(k=n_clusters)
D = Discretizer(reader, transform=pcat, cluster=clustering)
D.parametrize()
self.assertEqual(len(D.dtrajs), len(self.trajfiles))
for dtraj in clustering.dtrajs:
unique = np.unique(dtraj)
self.assertEqual(unique.shape[0], n_clusters)
