def test_with_data_in_mem(self):
import pyemma.coordinates as api
data = [
np.random.random((100, 50)),
np.random.random((103, 50)),
np.random.random((33, 50))
]
reader = source(data)
assert isinstance(reader, DataInMemory)
tpca = api.pca(dim=2)
n_centers = 10
km = api.cluster_kmeans(k=n_centers)
disc = api.discretizer(reader, tpca, km)
disc.parametrize()
dtrajs = disc.dtrajs
for dtraj in dtrajs:
n_states = np.max((np.unique(dtraj)))
self.assertGreaterEqual(
n_centers - 1, n_states,
"dtraj has more states than cluster centers")
def test_with_data_in_mem(self):
import pyemma.coordinates as api
data = [np.random.random((100, 50)),
np.random.random((103, 50)),
np.random.random((33, 50))]
reader = api.memory_reader(data)
tpca = api.pca(dim=2)
n_centers = 10
km = api.kmeans(k=n_centers)
disc = api.discretizer(reader, tpca, km)
disc.parametrize()
dtrajs = disc.dtrajs
for dtraj in dtrajs:
n_states = np.max((np.unique(dtraj)))
self.assertGreaterEqual(n_centers - 1, n_states,
"dtraj has more states than cluster centers")
#number of PCCA clusters
n_sets = 3
print 'feat dimension'
print feat.dimension()
dataset = []
nlist = []
if 1:
n_clusters = 200
tica_obj = coor.tica(dim=2, lag=tica_lagtime, kinetic_map=True)
input_data = coor.cluster_kmeans(k=n_clusters, max_iter=50)
disc = coor.discretizer(inp, tica_obj, input_data, stride=1, chunksize=10)
disc.parametrize()
print tica_obj.cumvar
#TICA output is Y
Y = tica_obj.get_output()
print np.shape(Y)
#print 'Y[0]'
#print Y[0]
print 'number of trajetories = ', np.shape(Y)[0]
#
#mapped_data is the TICA clustered data mapped to the microstates (so integer valued)
mapped_data = input_data.dtrajs
#plot tica free energy histogram plot
if 1:
print 'feat dimension'
print feat.dimension()
dataset = []
nlist = []
if 1:
n_clusters = 200
tica_obj = coor.tica( dim=2, lag=tica_lagtime, kinetic_map=True)
input_data = coor.cluster_kmeans( k=n_clusters, max_iter=50)
disc = coor.discretizer(inp, tica_obj, input_data, stride=1, chunksize=10)
disc.parametrize()
print tica_obj.cumvar
#TICA output is Y
Y = tica_obj.get_output()
print np.shape(Y)
#print 'Y[0]'
#print Y[0]
print 'number of trajetories = ', np.shape(Y)[0]
#
#mapped_data is the TICA clustered data mapped to the microstates (so integer valued)
mapped_data =input_data.dtrajs
#plot tica free energy histogram plot
if 1: