def sample_indexes_by_cluster(self, clusters, nsample, replace=True):
"""Samples trajectory/time indexes according to the given sequence of states.
Parameters
----------
clusters : iterable of integers
It contains the cluster indexes to be sampled
nsample : int
Number of samples per cluster. If replace = False, the number of returned samples per cluster could be smaller
if less than nsample indexes are available for a cluster.
replace : boolean, optional
Whether the sample is with or without replacement
Returns
-------
indexes : list of ndarray( (N, 2) )
List of the sampled indices by cluster.
Each element is an index array with a number of rows equal to N=len(sequence), with rows consisting of a
tuple (i, t), where i is the index of the trajectory and t is the time index within the trajectory.
"""
# Check if the catalogue (index_states)
if len(self._index_states) == 0: # has never been run
self._index_states = index_states(self.dtrajs)
return sample_indexes_by_state(self._index_states[clusters], nsample, replace=replace)
def test_sample_by_state_replace(self):
dtraj = [0, 1, 2, 3, 2, 1, 0]
idx = dt.index_states(dtraj)
sidx = dt.sample_indexes_by_state(idx, 5)
for i in range(4):
assert (sidx[i].shape[0] == 5)
for t in range(sidx[i].shape[0]):
assert (dtraj[sidx[i][t, 1]] == i)
def test_sample_by_state_replace_subset(self):
dtraj = [0, 1, 2, 3, 2, 1, 0]
idx = dt.index_states(dtraj)
subset = [1, 2]
sidx = dt.sample_indexes_by_state(idx, 5, subset=subset)
for i in range(len(subset)):
assert (sidx[i].shape[0] == 5)
for t in range(sidx[i].shape[0]):
assert (dtraj[sidx[i][t, 1]] == subset[i])
def test_onetraj_sub(self):
dtraj = [0, 1, 2, 3, 2, 1, 0]
# should be a ValueError because this is not a subset
res = dt.index_states(dtraj, subset=[2, 3])
expected = [np.array([[0, 2], [0, 4]]), np.array([[0, 3]])]
assert (len(res) == len(expected))
for i in range(len(res)):
assert (res[i].shape == expected[i].shape)
assert (np.alltrue(res[i] == expected[i]))
def test_sample_by_sequence(self):
dtraj = [0, 1, 2, 3, 2, 1, 0]
idx = dt.index_states(dtraj)
seq = [0, 1, 1, 1, 0, 0, 0, 0, 1, 1]
sidx = dt.sample_indexes_by_sequence(idx, seq)
assert (np.alltrue(sidx.shape == (len(seq), 2)))
for t in range(sidx.shape[0]):
assert (sidx[t, 0] == 0) # did we pick the right traj?
assert (dtraj[sidx[t,
1]] == seq[t]) # did we pick the right states?
def active_state_indexes(self):
"""
Ensures that the connected states are indexed and returns the indices
"""
self._check_is_estimated()
if not hasattr(self, '_active_state_indexes'):
from pyerna.util.discrete_trajectories import index_states
self._active_state_indexes = index_states(
self.discrete_trajectories_active)
return self._active_state_indexes
def observable_state_indexes(self):
"""
Ensures that the observable states are indexed and returns the indices
"""
try: # if we have this attribute, return it
return self._observable_state_indexes
except AttributeError: # didn't exist? then create it.
import pyerna.util.discrete_trajectories as dt
self._observable_state_indexes = dt.index_states(
self.discrete_trajectories_obs)
return self._observable_state_indexes
def test_twotraj(self):
dtrajs = [[0, 1, 2, 3, 2, 1, 0], [3, 4, 5]]
# should be a ValueError because this is not a subset
res = dt.index_states(dtrajs)
expected = [
np.array([[0, 0], [0, 6]]),
np.array([[0, 1], [0, 5]]),
np.array([[0, 2], [0, 4]]),
np.array([[0, 3], [1, 0]]),
np.array([[1, 1]]),
np.array([[1, 2]])
]
assert (len(res) == len(expected))
for i in range(len(res)):
assert (res[i].shape == expected[i].shape)
assert (np.alltrue(res[i] == expected[i]))
def index_clusters(self):
"""Returns trajectory/time indexes for all the clusters
Returns
-------
indexes : list of ndarray( (N_i, 2) )
For each state, all trajectory and time indexes where this cluster occurs.
Each matrix has a number of rows equal to the number of occurrences of the corresponding state,
with rows consisting of a tuple (i, t), where i is the index of the trajectory and t is the time index
within the trajectory.
"""
if len(self._dtrajs) == 0: # nothing assigned yet, doing that now
self._dtrajs = self.assign()
if len(self._index_states) == 0: # has never been run
self._index_states = index_states(self._dtrajs)
return self._index_states
def test_big(self):
import pyerna.datasets
dtraj = pyerna.datasets.load_2well_discrete().dtraj_T100K_dt10
# just run these to see if there's any exception
dt.index_states(dtraj)
def test_subset_error(self):
dtraj = [0, 1, 2, 3, 2, 1, 0]
# should be a ValueError because this is not a subset
with self.assertRaises(ValueError):
dt.index_states(dtraj, subset=[3, 4, 5])