def register_progress_callback(self, call_back, stage=0):
""" Registers the progress reporter.
Parameters
----------
call_back : function
This function will be called with the following arguments:
1. stage (int)
2. instance of pyemma.utils.progressbar.ProgressBar
3. optional \*args and named keywords (\*\*kw), for future changes
stage: int, optional, default=0
The stage you want the given call back function to be fired.
"""
if not self.show_progress:
return
assert callable(call_back)
# check we have the desired function signature
from pyemma.util.reflection import getargspec_no_self
argspec = getargspec_no_self(call_back)
assert len(argspec.args) == 2
assert argspec.varargs is not None
assert argspec.keywords is not None
if stage not in self._prog_rep_callbacks:
self._prog_rep_callbacks[stage] = []
self._prog_rep_callbacks[stage].append(call_back)
def _get_model_param_names(cls):
r"""Get parameter names for the model"""
# fetch model parameters
if hasattr(cls, 'set_model_params'):
# introspect the constructor arguments to find the model parameters
# to represent
args, varargs, kw, default = getargspec_no_self(
cls.set_model_params)
if varargs is not None:
raise RuntimeError(
"PyEMMA models should always specify their parameters in the signature"
" of their set_model_params (no varargs). %s doesn't follow this convention."
% (cls, ))
return args
else:
# No parameters known
return []
def _get_param_names(cls):
"""Get parameter names for the estimator"""
# fetch the constructor or the original constructor before
# deprecation wrapping if any
init = getattr(cls.__init__, 'deprecated_original', cls.__init__)
if init is object.__init__:
# No explicit constructor to introspect
return []
# introspect the constructor arguments to find the model parameters
# to represent
args, varargs, kw, default = getargspec_no_self(init)
if varargs is not None:
raise RuntimeError("scikit-learn estimators should always "
"specify their parameters in the signature"
" of their __init__ (no varargs)."
" %s doesn't follow this convention." % (cls, ))
args.sort()
return args
def _get_model_param_names(self):
r"""Get parameter names for the model"""
# fetch model parameters
if hasattr(self, 'set_model_params'):
set_model_param_method = getattr(self, 'set_model_params')
# introspect the constructor arguments to find the model parameters
# to represent
args, varargs, kw, default = getargspec_no_self(
set_model_param_method)
if varargs is not None:
raise RuntimeError(
"pyEMMA models should always specify their parameters in the signature"
" of their set_model_params (no varargs). %s doesn't follow this convention."
% (self, ))
# Remove 'self'
# XXX: This is going to fail if the init is a staticmethod, but
# who would do this?
args.pop(0)
args.sort()
return args
else:
# No parameters known
return []
def count_lagged(self,
lag,
count_mode='sliding',
mincount_connectivity='1/n',
show_progress=True):
r""" Counts transitions at given lag time
Parameters
----------
lag : int
lagtime in trajectory steps
count_mode : str, optional, default='sliding'
mode to obtain count matrices from discrete trajectories. Should be one of:
* 'sliding' : A trajectory of length T will have :math:`T-\tau` counts
at time indexes
.. math:: (0 \rightarray \tau), (1 \rightarray \tau+1), ..., (T-\tau-1 \rightarray T-1)
* 'effective' : Uses an estimate of the transition counts that are
statistically uncorrelated. Recommended when used with a
Bayesian MSM.
* 'sample' : A trajectory of length T will have :math:`T / \tau` counts
at time indexes
.. math:: (0 \rightarray \tau), (\tau \rightarray 2 \tau), ..., (((T/tau)-1) \tau \rightarray T)
show_progress: bool, default=True
show the progress for the expensive effective count mode computation.
"""
# store lag time
self._lag = lag
# Compute count matrix
count_mode = count_mode.lower()
if count_mode == 'sliding':
self._C = msmest.count_matrix(self._dtrajs, lag, sliding=True)
elif count_mode == 'sample':
self._C = msmest.count_matrix(self._dtrajs, lag, sliding=False)
elif count_mode == 'effective':
from pyemma.util.reflection import getargspec_no_self
argspec = getargspec_no_self(msmest.effective_count_matrix)
kw = {}
if show_progress and 'callback' in argspec.args:
from pyemma._base.progress import ProgressReporter
from pyemma._base.parallel import get_n_jobs
pg = ProgressReporter()
# this is a fast operation
C_temp = msmest.count_matrix(self._dtrajs, lag, sliding=True)
pg.register(C_temp.nnz, 'compute statistical inefficiencies')
del C_temp
callback = lambda: pg.update(1)
kw['callback'] = callback
kw['n_jobs'] = get_n_jobs()
self._C = msmest.effective_count_matrix(self._dtrajs, lag, **kw)
else:
raise ValueError('Count mode ' + count_mode + ' is unknown.')
# store mincount_connectivity
if mincount_connectivity == '1/n':
mincount_connectivity = 1.0 / np.shape(self._C)[0]
self._mincount_connectivity = mincount_connectivity
# Compute reversibly connected sets
if self._mincount_connectivity > 0:
self._connected_sets = \
self._compute_connected_sets(self._C, mincount_connectivity=self._mincount_connectivity)
else:
self._connected_sets = msmest.connected_sets(self._C)
# set sizes and count matrices on reversibly connected sets
self._connected_set_sizes = np.zeros((len(self._connected_sets)))
self._C_sub = np.empty((len(self._connected_sets)), dtype=np.object)
for i in range(len(self._connected_sets)):
# set size
self._connected_set_sizes[i] = len(self._connected_sets[i])
# submatrix
# self._C_sub[i] = submatrix(self._C, self._connected_sets[i])
# largest connected set
self._lcs = self._connected_sets[0]
# if lcs has no counts, make lcs empty
if submatrix(self._C, self._lcs).sum() == 0:
self._lcs = np.array([], dtype=int)
# mapping from full to lcs
self._full2lcs = -1 * np.ones((self._nstates), dtype=int)
self._full2lcs[self._lcs] = np.arange(len(self._lcs))
# remember that this function was called
self._counted_at_lag = True
def count_lagged(self, lag, count_mode='sliding', mincount_connectivity='1/n',
show_progress=True, n_jobs=None, name='', core_set=None, milestoning_method='last_core'):
r""" Counts transitions at given lag time
Parameters
----------
lag : int
lagtime in trajectory steps
count_mode : str, optional, default='sliding'
mode to obtain count matrices from discrete trajectories. Should be one of:
* 'sliding' : A trajectory of length T will have :math:`T-\tau` counts
at time indexes
.. math:: (0 \rightarray \tau), (1 \rightarray \tau+1), ..., (T-\tau-1 \rightarray T-1)
* 'effective' : Uses an estimate of the transition counts that are
statistically uncorrelated. Recommended when used with a
Bayesian MSM.
* 'sample' : A trajectory of length T will have :math:`T / \tau` counts
at time indexes
.. math:: (0 \rightarray \tau), (\tau \rightarray 2 \tau), ..., (((T/tau)-1) \tau \rightarray T)
show_progress: bool, default=True
show the progress for the expensive effective count mode computation.
n_jobs: int or None
"""
# store lag time
self._lag = lag
# Compute count matrix
count_mode = count_mode.lower()
if core_set is not None and count_mode in ('sliding', 'sample'):
if milestoning_method == 'last_core':
# assign -1 frames to last visited core
for d in self._dtrajs:
assert d[0] != -1
while -1 in d:
mask = (d == -1)
d[mask] = d[np.roll(mask, -1)]
self._C = msmest.count_matrix(self._dtrajs, lag, sliding=count_mode == 'sliding')
else:
raise NotImplementedError('Milestoning method {} not implemented.'.format(milestoning_method))
elif count_mode == 'sliding':
self._C = msmest.count_matrix(self._dtrajs, lag, sliding=True)
elif count_mode == 'sample':
self._C = msmest.count_matrix(self._dtrajs, lag, sliding=False)
elif count_mode == 'effective':
if core_set is not None:
raise RuntimeError('Cannot estimate core set MSM with effective counting.')
from pyemma.util.reflection import getargspec_no_self
argspec = getargspec_no_self(msmest.effective_count_matrix)
kw = {}
from pyemma.util.contexts import nullcontext
ctx = nullcontext()
if 'callback' in argspec.args: # msmtools effective cmatrix ready for multiprocessing?
from pyemma._base.progress import ProgressReporter
from pyemma._base.parallel import get_n_jobs
kw['n_jobs'] = get_n_jobs() if n_jobs is None else n_jobs
if show_progress:
pg = ProgressReporter()
# this is a fast operation
C_temp = msmest.count_matrix(self._dtrajs, lag, sliding=True)
pg.register(C_temp.nnz, '{}: compute stat. inefficiencies'.format(name), stage=0)
del C_temp
kw['callback'] = pg.update
ctx = pg.context(stage=0)
with ctx:
self._C = msmest.effective_count_matrix(self._dtrajs, lag, **kw)
else:
raise ValueError('Count mode ' + count_mode + ' is unknown.')
# store mincount_connectivity
if mincount_connectivity == '1/n':
mincount_connectivity = 1.0 / np.shape(self._C)[0]
self._mincount_connectivity = mincount_connectivity
# Compute reversibly connected sets
if self._mincount_connectivity > 0:
self._connected_sets = \
self._compute_connected_sets(self._C, mincount_connectivity=self._mincount_connectivity)
else:
self._connected_sets = msmest.connected_sets(self._C)
# set sizes and count matrices on reversibly connected sets
self._connected_set_sizes = np.zeros((len(self._connected_sets)))
self._C_sub = np.empty((len(self._connected_sets)), dtype=np.object)
for i in range(len(self._connected_sets)):
# set size
self._connected_set_sizes[i] = len(self._connected_sets[i])
# submatrix
# self._C_sub[i] = submatrix(self._C, self._connected_sets[i])
# largest connected set
self._lcs = self._connected_sets[0]
# if lcs has no counts, make lcs empty
if submatrix(self._C, self._lcs).sum() == 0:
self._lcs = np.array([], dtype=int)
# mapping from full to lcs
self._full2lcs = -1 * np.ones((self._nstates), dtype=int)
self._full2lcs[self._lcs] = np.arange(len(self._lcs))
# remember that this function was called
self._counted_at_lag = True
