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(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_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 sample_by_state(self, nsample, subset=None, replace=True):
"""Generates samples of the connected states.
For each state in the active set of states, generates nsample samples with trajectory/time indexes.
This information can be used in order to generate a trajectory of length nsample * nconnected using
:func:`pyemma.coordinates.save_traj` or nconnected trajectories of length nsample each using
:func:`pyemma.coordinates.save_traj`
Parameters
----------
N : int
Number of time steps in the output trajectory. The total simulation time is stride * lag time * N
nsample : int
Number of samples per state. If replace = False, the number of returned samples per state could be smaller
if less than nsample indexes are available for a state.
subset : ndarray((n)), optional, default = None
array of states to be indexed. By default all states in the connected set will be used
replace : boolean, optional
Whether the sample is with or without replacement
start : int, optional, default = None
starting state. If not given, will sample from the stationary distribution of P
Returns
-------
indexes : list of ndarray( (N, 2) )
list of trajectory/time index arrays with an array for each state.
Within each index array, each row consist of a tuple (i, t), where i is
the index of the trajectory and t is the time index within the trajectory.
See also
--------
pyemma.coordinates.save_traj
in order to save the sampled frames sequentially in a trajectory file with molecular structures
pyemma.coordinates.save_trajs
in order to save the sampled frames in nconnected trajectory files with molecular structures
"""
self._check_is_estimated()
# generate connected state indexes
import pyemma.util.discrete_trajectories as dt
return dt.sample_indexes_by_state(self.active_state_indexes,
nsample,
subset=subset,
replace=replace)
