check core set msm estimator compatibility

pyemma/msm/estimators/_msm_estimator_base.py

@@ -191,8 +191,8 @@ def _get_dtraj_stats(self, dtrajs):
                                         'Defining core set automatically; check correctness by calling self.core_set.')
                 else:
                     if set(_np.sort(_np.unique(_np.concatenate(dtrajs)))[1:]) != set(self.core_set):
-                        raise RuntimeError('Core set definition does not match states in dtraj while'
-                                           'dtraj already contains unassigned states.')
+                        self.logger.warning('dtraj containts states that are not in core set definition. '
+                                            'These states will be treated as unassigned.')
 
             if self.core_set is not None:
                 self._dtrajs_original = dtrajs

pyemma/msm/estimators/augmented_msm.py

@@ -329,9 +329,6 @@ def _estimate(self, dtrajs):
         if _np.size(self.active_set) == 0:
             raise RuntimeError('Active set is empty. Cannot estimate AMM.')
 
-        from pyemma.util.discrete_trajectories import index_states
-        self._active_state_indexes = index_states(dtrajs, subset=self.active_set)
-
         # active count matrix and number of states
         self._C_active = dtrajstats.count_matrix(subset=self.active_set)
         self._nstates = self._C_active.shape[0]
@@ -342,7 +339,7 @@ def _estimate(self, dtrajs):
         self._full2active[self.active_set] = _np.arange(len(self.active_set))
 
         # slice out active states from E matrix
-        _dset = list(set(_np.concatenate(dtrajs)))
+        _dset = list(set(_np.concatenate(self._dtrajs_full)))
         _rras = [_dset.index(s) for s in self.active_set]
         self.E_active = self.E[_rras]
 
@@ -474,7 +471,6 @@ def _estimate(self, dtrajs):
 
         _P = msmest.tmatrix(self._C_active, reversible=True, mu=self._pihat)
 
-        self._dtrajs_full = dtrajs
         self._connected_sets = msmest.connected_sets(self._C_full)
         self.set_model_params(P=_P, pi=self._pihat, reversible=True,
                               dt_model=self.timestep_traj.get_scaled(self.lag))

pyemma/msm/estimators/bayesian_msm.py

@@ -174,6 +174,10 @@ def estimate(self, dtrajs, **kw):
         return super(BayesianMSM, self).estimate(dtrajs, **kw)
 
     def _estimate(self, dtrajs):
+
+        if self.core_set is not None and self.count_mode == 'effective':
+            raise RuntimeError('Cannot estimate core set MSM with effective counting.')
+
         # conduct MLE estimation (superclass) first
         _MLMSM._estimate(self, dtrajs)
 

pyemma/msm/estimators/oom_reweighted_msm.py

@@ -164,6 +164,8 @@ def __init__(self, lag=1, reversible=True, count_mode='sliding', sparse=False, c
 
     def _estimate(self, dtrajs):
         """ Estimate MSM """
+        if self.core_set is not None:
+            raise NotImplementedError('Core set MSMs currently not compatible with {}.'.format(self.__class__.__name__))
         # remove last lag steps from dtrajs:
         dtrajs_lag = [traj[:-self.lag] for traj in dtrajs]