[Fix] Removed the possibility to create an Obs from data on several replica (#258)

* [Fix] Removed the possibility to create an Obs from data on several replica

* [Fix] extended tests and corrected a small bug in the previous commit

---------

Co-authored-by: Simon Kuberski <simon.kuberski@cern.ch>

pyerrors/input/dobs.py

@@ -529,7 +529,8 @@ def import_dobs_string(content, full_output=False, separator_insertion=True):
                 deltas.append(repdeltas)
                 idl.append(repidl)
 
-        res.append(Obs(deltas, obs_names, idl=idl))
+        obsmeans = [np.average(deltas[j]) for j in range(len(deltas))]
+        res.append(Obs([np.array(deltas[j]) - obsmeans[j] for j in range(len(obsmeans))], obs_names, idl=idl, means=obsmeans))
         res[-1]._value = mean[i]
     _check(len(e_names) == ne)
 

pyerrors/input/json.py

@@ -133,10 +133,11 @@ def create_json_string(ol, description='', indent=1):
         names = []
         idl = []
         for key, value in obs.idl.items():
-            samples.append([np.nan] * len(value))
+            samples.append(np.array([np.nan] * len(value)))
             names.append(key)
             idl.append(value)
-        my_obs = Obs(samples, names, idl)
+        my_obs = Obs(samples, names, idl, means=[np.nan for n in names])
+        my_obs._value = np.nan
         my_obs._covobs = obs._covobs
         for name in obs._covobs:
             my_obs.names.append(name)
@@ -331,7 +332,8 @@ def _parse_json_dict(json_dict, verbose=True, full_output=False):
         cd = _gen_covobsd_from_cdatad(o.get('cdata', {}))
 
         if od:
-            ret = Obs([[ddi[0] + values[0] for ddi in di] for di in od['deltas']], od['names'], idl=od['idl'])
+            r_offsets = [np.average([ddi[0] for ddi in di]) for di in od['deltas']]
+            ret = Obs([np.array([ddi[0] for ddi in od['deltas'][i]]) - r_offsets[i] for i in range(len(od['deltas']))], od['names'], idl=od['idl'], means=[ro + values[0] for ro in r_offsets])
             ret._value = values[0]
         else:
             ret = Obs([], [], means=[])
@@ -356,7 +358,8 @@ def _parse_json_dict(json_dict, verbose=True, full_output=False):
         taglist = o.get('tag', layout * [None])
         for i in range(layout):
             if od:
-                ret.append(Obs([list(di[:, i] + values[i]) for di in od['deltas']], od['names'], idl=od['idl']))
+                r_offsets = np.array([np.average(di[:, i]) for di in od['deltas']])
+                ret.append(Obs([od['deltas'][j][:, i] - r_offsets[j] for j in range(len(od['deltas']))], od['names'], idl=od['idl'], means=[ro + values[i] for ro in r_offsets]))
                 ret[-1]._value = values[i]
             else:
                 ret.append(Obs([], [], means=[]))
@@ -383,7 +386,8 @@ def _parse_json_dict(json_dict, verbose=True, full_output=False):
         taglist = o.get('tag', N * [None])
         for i in range(N):
             if od:
-                ret.append(Obs([di[:, i] + values[i] for di in od['deltas']], od['names'], idl=od['idl']))
+                r_offsets = np.array([np.average(di[:, i]) for di in od['deltas']])
+                ret.append(Obs([od['deltas'][j][:, i] - r_offsets[j] for j in range(len(od['deltas']))], od['names'], idl=od['idl'], means=[ro + values[i] for ro in r_offsets]))
                 ret[-1]._value = values[i]
             else:
                 ret.append(Obs([], [], means=[]))

pyerrors/obs.py

@@ -82,6 +82,8 @@ class Obs:
                     raise ValueError('Names are not unique.')
                 if not all(isinstance(x, str) for x in names):
                     raise TypeError('All names have to be strings.')
+                if len(set([o.split('|')[0] for o in names])) > 1:
+                    raise ValueError('Cannot initialize Obs based on multiple ensembles. Please average separate Obs from each ensemble.')
             else:
                 if not isinstance(names[0], str):
                     raise TypeError('All names have to be strings.')
@@ -1407,6 +1409,8 @@ def reweight(weight, obs, **kwargs):
             raise ValueError('Error: Not possible to reweight an Obs that contains covobs!')
         if not set(obs[i].names).issubset(weight.names):
             raise ValueError('Error: Ensembles do not fit')
+        if len(obs[i].mc_names) > 1 or len(weight.mc_names) > 1:
+            raise ValueError('Error: Cannot reweight an Obs that contains multiple ensembles.')
         for name in obs[i].names:
             if not set(obs[i].idl[name]).issubset(weight.idl[name]):
                 raise ValueError('obs[%d] has to be defined on a subset of the configs in weight.idl[%s]!' % (i, name))
@@ -1442,9 +1446,12 @@ def correlate(obs_a, obs_b):
     -----
     Keep in mind to only correlate primary observables which have not been reweighted
     yet. The reweighting has to be applied after correlating the observables.
-    Currently only works if ensembles are identical (this is not strictly necessary).
+    Only works if a single ensemble is present in the Obs.
+    Currently only works if ensemble content is identical (this is not strictly necessary).
     """
 
+    if len(obs_a.mc_names) > 1 or len(obs_b.mc_names) > 1:
+        raise ValueError('Error: Cannot correlate Obs that contain multiple ensembles.')
     if sorted(obs_a.names) != sorted(obs_b.names):
         raise ValueError(f"Ensembles do not fit {set(sorted(obs_a.names)) ^ set(sorted(obs_b.names))}")
     if len(obs_a.cov_names) or len(obs_b.cov_names):
@@ -1755,7 +1762,11 @@ def import_bootstrap(boots, name, random_numbers):
 
 
 def merge_obs(list_of_obs):
-    """Combine all observables in list_of_obs into one new observable
+    """Combine all observables in list_of_obs into one new observable.
+    This allows to merge Obs that have been computed on multiple replica
+    of the same ensemble.
+    If you like to merge Obs that are based on several ensembles, please
+    average them yourself.
 
     Parameters
     ----------