def _estimate(self, dtrajs): import bhmm # ensure right format dtrajs = _types.ensure_dtraj_list(dtrajs) # CHECK LAG trajlengths = [_np.size(dtraj) for dtraj in dtrajs] if self.lag >= _np.max(trajlengths): raise ValueError('Illegal lag time ' + str(self.lag) + ' exceeds longest trajectory length') if self.lag > _np.mean(trajlengths): self.logger.warning('Lag time ' + str(self.lag) + ' is on the order of mean trajectory length ' + str(_np.mean(trajlengths)) + '. It is recommended to fit four lag times in each ' + 'trajectory. HMM might be inaccurate.') # EVALUATE STRIDE if self.stride == 'effective': # by default use lag as stride (=lag sampling), because we currently have no better theory for deciding # how many uncorrelated counts we can make self.stride = self.lag # get a quick estimate from the spectral radius of the nonreversible from pyemma.msm import estimate_markov_model msm_nr = estimate_markov_model(dtrajs, lag=self.lag, reversible=False, sparse=False, connectivity='largest', dt_traj=self.timestep_traj) # if we have more than nstates timescales in our MSM, we use the next (neglected) timescale as an # estimate of the decorrelation time if msm_nr.nstates > self.nstates: corrtime = max(1, msm_nr.timescales()[self.nstates-1]) # use the smaller of these two pessimistic estimates self.stride = int(min(self.lag, 2*corrtime)) # LAG AND STRIDE DATA dtrajs_lagged_strided = bhmm.lag_observations(dtrajs, self.lag, stride=self.stride) # OBSERVATION SET if self.observe_nonempty: observe_subset = 'nonempty' else: observe_subset = None # INIT HMM from bhmm import init_discrete_hmm from pyemma.msm.estimators import MaximumLikelihoodMSM if self.msm_init=='largest-strong': hmm_init = init_discrete_hmm(dtrajs_lagged_strided, self.nstates, lag=1, reversible=self.reversible, stationary=True, regularize=True, method='lcs-spectral', separate=self.separate) elif self.msm_init=='all': hmm_init = init_discrete_hmm(dtrajs_lagged_strided, self.nstates, lag=1, reversible=self.reversible, stationary=True, regularize=True, method='spectral', separate=self.separate) elif issubclass(self.msm_init.__class__, MaximumLikelihoodMSM): # initial MSM given. from bhmm.init.discrete import init_discrete_hmm_spectral p0, P0, pobs0 = init_discrete_hmm_spectral(self.msm_init.count_matrix_full, self.nstates, reversible=self.reversible, stationary=True, active_set=self.msm_init.active_set, P=self.msm_init.transition_matrix, separate=self.separate) hmm_init = bhmm.discrete_hmm(p0, P0, pobs0) observe_subset = self.msm_init.active_set # override observe_subset. else: raise ValueError('Unknown MSM initialization option: ' + str(self.msm_init)) # --------------------------------------------------------------------------------------- # Estimate discrete HMM # --------------------------------------------------------------------------------------- # run EM from bhmm.estimators.maximum_likelihood import MaximumLikelihoodEstimator as _MaximumLikelihoodEstimator hmm_est = _MaximumLikelihoodEstimator(dtrajs_lagged_strided, self.nstates, initial_model=hmm_init, output='discrete', reversible=self.reversible, stationary=self.stationary, accuracy=self.accuracy, maxit=self.maxit) # run hmm_est.fit() # package in discrete HMM self.hmm = bhmm.DiscreteHMM(hmm_est.hmm) # get model parameters self.initial_distribution = self.hmm.initial_distribution transition_matrix = self.hmm.transition_matrix observation_probabilities = self.hmm.output_probabilities # get estimation parameters self.likelihoods = hmm_est.likelihoods # Likelihood history self.likelihood = self.likelihoods[-1] self.hidden_state_probabilities = hmm_est.hidden_state_probabilities # gamma variables self.hidden_state_trajectories = hmm_est.hmm.hidden_state_trajectories # Viterbi path self.count_matrix = hmm_est.count_matrix # hidden count matrix self.initial_count = hmm_est.initial_count # hidden init count self._active_set = _np.arange(self.nstates) # TODO: it can happen that we loose states due to striding. Should we lift the output probabilities afterwards? # parametrize self self._dtrajs_full = dtrajs self._dtrajs_lagged = dtrajs_lagged_strided self._nstates_obs_full = msmest.number_of_states(dtrajs) self._nstates_obs = msmest.number_of_states(dtrajs_lagged_strided) self._observable_set = _np.arange(self._nstates_obs) self._dtrajs_obs = dtrajs self.set_model_params(P=transition_matrix, pobs=observation_probabilities, reversible=self.reversible, dt_model=self.timestep_traj.get_scaled(self.lag)) # TODO: perhaps remove connectivity and just rely on .submodel()? # deal with connectivity states_subset = None if self.connectivity == 'largest': states_subset = 'largest-strong' elif self.connectivity == 'populous': states_subset = 'populous-strong' # return submodel (will return self if all None) return self.submodel(states=states_subset, obs=observe_subset, mincount_connectivity=self.mincount_connectivity)
def _estimate(self, dtrajs): """ Parameters ---------- Return ------ hmsm : :class:`EstimatedHMSM <pyemma.msm.estimators.hmsm_estimated.EstimatedHMSM>` Estimated Hidden Markov state model """ # ensure right format dtrajs = _types.ensure_dtraj_list(dtrajs) # if no initial MSM is given, estimate it now if self.msm_init is None: # estimate with sparse=False, because we need to do PCCA which is currently not implemented for sparse # estimate with store_data=True, because we need an EstimatedMSM msm_estimator = _MSMEstimator(lag=self.lag, reversible=self.reversible, sparse=False, connectivity=self.connectivity, dt_traj=self.timestep_traj) msm_init = msm_estimator.estimate(dtrajs) else: assert isinstance(self.msm_init, _EstimatedMSM), 'msm_init must be of type EstimatedMSM' msm_init = self.msm_init self.reversible = msm_init.is_reversible # print 'Connected set: ', msm_init.active_set # generate lagged observations if self.stride == 'effective': # by default use lag as stride (=lag sampling), because we currently have no better theory for deciding # how many uncorrelated counts we can make self.stride = self.lag # if we have more than nstates timescales in our MSM, we use the next (neglected) timescale as an # estimate of the decorrelation time if msm_init.nstates > self.nstates: corrtime = int(max(1, msm_init.timescales()[self.nstates-1])) # use the smaller of these two pessimistic estimates self.stride = min(self.stride, 2*corrtime) # TODO: Here we always use the full observation state space for the estimation. dtrajs_lagged = _lag_observations(dtrajs, self.lag, stride=self.stride) # check input assert _types.is_int(self.nstates) and self.nstates > 1 and self.nstates <= msm_init.nstates, \ 'nstates must be an int in [2,msmobj.nstates]' # if hmm.nstates = msm.nstates there is no problem. Otherwise, check spectral gap if msm_init.nstates > self.nstates: timescale_ratios = msm_init.timescales()[:-1] / msm_init.timescales()[1:] if timescale_ratios[self.nstates-2] < 2.0: self.logger.warn('Requested coarse-grained model with ' + str(self.nstates) + ' metastable states at ' + 'lag=' + str(self.lag) + '.' + 'The ratio of relaxation timescales between ' + str(self.nstates) + ' and ' + str(self.nstates+1) + ' states is only ' + str(timescale_ratios[self.nstates-2]) + ' while we recommend at least 2. ' + ' It is possible that the resulting HMM is inaccurate. Handle with caution.') # set things from MSM # TODO: dtrajs_obs is set here, but not used in estimation. Estimation is alwas done with # TODO: respect to full observation (see above). This is confusing. Define how we want to do this in gen. # TODO: observable set is also not used, it is just saved. nstates_obs_full = msm_init.nstates_full if self.observe_active: nstates_obs = msm_init.nstates observable_set = msm_init.active_set dtrajs_obs = msm_init.discrete_trajectories_active else: nstates_obs = msm_init.nstates_full observable_set = np.arange(nstates_obs_full) dtrajs_obs = msm_init.discrete_trajectories_full # TODO: this is redundant with BHMM code because that code is currently not easily accessible and # TODO: we don't want to re-estimate. Should be reengineered in bhmm. # --------------------------------------------------------------------------------------- # PCCA-based coarse-graining # --------------------------------------------------------------------------------------- # pcca- to number of metastable states pcca = msm_init.pcca(self.nstates) # HMM output matrix eps = 0.01 * (1.0/nstates_obs_full) # default output probability, in order to avoid zero columns # Use PCCA distributions, but at least eps to avoid 100% assignment to any state (breaks convergence) B_conn = np.maximum(msm_init.metastable_distributions, eps) # full state space output matrix B = eps * np.ones((self.nstates, nstates_obs_full), dtype=np.float64) # expand B_conn to full state space # TODO: here we always select the active set, no matter if observe_active=True or False. B[:, msm_init.active_set] = B_conn[:, :] # TODO: at this point we will have zero observation probabilities for states that are not in the active # TODO: set. If these occur in the trajectory, that will mean zero columns in the output probabilities # TODO: and crash of forward-backward and sampling algorithms. # renormalize B to make it row-stochastic B /= B.sum(axis=1)[:, None] # coarse-grained transition matrix P_coarse = pcca.coarse_grained_transition_matrix # take care of unphysical values. First symmetrize X = np.dot(np.diag(pcca.coarse_grained_stationary_probability), P_coarse) X = 0.5*(X + X.T) # if there are values < 0, set to eps X = np.maximum(X, eps) # turn into coarse-grained transition matrix A = X / X.sum(axis=1)[:, None] # --------------------------------------------------------------------------------------- # Estimate discrete HMM # --------------------------------------------------------------------------------------- # lazy import bhmm here in order to avoid dependency loops import bhmm # initialize discrete HMM hmm_init = bhmm.discrete_hmm(A, B, stationary=True, reversible=self.reversible) # run EM hmm = bhmm.estimate_hmm(dtrajs_lagged, self.nstates, lag=1, initial_model=hmm_init, accuracy=self.accuracy, maxit=self.maxit) self.hmm = bhmm.DiscreteHMM(hmm) # find observable set transition_matrix = self.hmm.transition_matrix observation_probabilities = self.hmm.output_probabilities # TODO: Cutting down... OK, this can be done if self.observe_active: # cut down observation probabilities to active set observation_probabilities = observation_probabilities[:, msm_init.active_set] observation_probabilities /= observation_probabilities.sum(axis=1)[:,None] # renormalize # parametrize self self._dtrajs_full = dtrajs self._dtrajs_lagged = dtrajs_lagged self._observable_set = observable_set self._dtrajs_obs = dtrajs_obs self.set_model_params(P=transition_matrix, pobs=observation_probabilities, reversible=self.reversible, dt_model=self.timestep_traj.get_scaled(self.lag)) return self