Merge pull request #420 from sandialabs/bugfix-cirq-datasets

Bugfix Cirq Datasets and LGST Bug

pygsti/algorithms/core.py

@@ -247,7 +247,10 @@ def run_lgst(dataset, prep_fiducials, effect_fiducials, target_model, op_labels=
                     circuit = rhostr
                 dsRow_fractions = dataset[circuit].fractions
                 # outcome labels should just be effect labels (no instruments!)
-                EVec[0, i] = dsRow_fractions[(effectLabel,)]
+                # when using a sparse data set format it might not be the case
+                # that all effect labels are present (only ones with non-zero counts are)
+                # so return 0 for the fraction in that case.
+                EVec[0, i] = dsRow_fractions.get((effectLabel,), 0)
             EVec_p = _np.dot(_np.dot(EVec, Vd), Pj)  # truncate Evec => Evec', shape (1,trunc)
             povm_effects.append((effectLabel, _np.transpose(EVec_p)))
         lgstModel.povms[povmLabel] = _povm.UnconstrainedPOVM(povm_effects, evotype='default')
@@ -262,7 +265,10 @@ def run_lgst(dataset, prep_fiducials, effect_fiducials, target_model, op_labels=
                 # try without prepLabel since it will be the default
                 circuit = estr
             dsRow_fractions = dataset[circuit].fractions
-            rhoVec[eoff:eoff + povmLen, 0] = [dsRow_fractions[(ol,)] for ol in target_model.povms[povmLbl]]
+            # when using a sparse data set format it might not be the case
+            # that all effect labels are present (only ones with non-zero counts are)
+            # so return 0 for the fraction in that case.
+            rhoVec[eoff:eoff + povmLen, 0] = [dsRow_fractions.get((ol,),0) for ol in target_model.povms[povmLbl]]
             eoff += povmLen
         rhoVec_p = _np.dot(Pjt, _np.dot(Ud, rhoVec))  # truncate rhoVec => rhoVec', shape (trunc, 1)
         rhoVec_p = _np.dot(invABMat_p, rhoVec_p)

pygsti/data/dataset.py

@@ -1603,7 +1603,7 @@ def add_count_arrays(self, circuit, outcome_index_array, count_array,
         self._add_raw_arrays(circuit, outcome_index_array, time_array, count_array,
                              overwriteExisting, record_zero_counts, aux)
 
-    def add_cirq_trial_result(self, circuit, trial_result, key):
+    def add_cirq_trial_result(self, circuit, trial_result, key, convert_int_to_binary = True, num_qubits = None):
         """
         Add a single circuit's counts --- stored in a Cirq TrialResult --- to this DataSet
 
@@ -1619,6 +1619,16 @@ def add_cirq_trial_result(self, circuit, trial_result, key):
         key : str
             The string key of the measurement. Set by cirq.measure.
 
+        convert_int_to_binary : bool, optional (defaut True)
+            By default the keys in the cirq Results object are the integers representing
+            the bitstrings of the measurements on a set of qubits, in big-endian convention.
+            If True this uses the cirq function `cirq.big_endian_int_to_bits` to convert back
+            to a binary string before adding the counts as a entry into the pygsti dataset.
+
+        num_qubits : int, optional (default None)
+            Number of qubits used in the conversion from integers to binary when convert_int_to_binary
+            is True. If None, then the number of line_labels on the input circuit is used.
+
         Returns
         -------
         None
@@ -1631,8 +1641,17 @@ def add_cirq_trial_result(self, circuit, trial_result, key):
 
         # TrialResult.histogram returns a collections.Counter object, which is a subclass of dict.
         histogram_counter = trial_result.histogram(key=key)
+
+        if num_qubits is None:
+            num_qubits = len(circuit.line_labels)
+
         # The keys in histogram_counter are integers, but pyGSTi likes dictionary keys to be strings.
-        count_dict = {str(key): value for key, value in histogram_counter.items()}
+        count_dict = {}
+        for key, value in histogram_counter.items():
+            if convert_int_to_binary:
+                count_dict[_np.binary_repr(key, width= num_qubits)] = value
+            else:
+                count_dict[str(key)] = value
         self.add_count_dict(circuit, count_dict)
 
     def add_raw_series_data(self, circuit, outcome_label_list, time_stamp_list,