Merge pull request #311 from CCPBioSim/310-bug-mismatch-within-regression-test

Enforce deterministic group ordering across entropy pipeline and fix ethyl-acetate regression test topology mismatch

Author: harryswift01

CodeEntropy/entropy/nodes/configurational.py

@@ -53,7 +53,7 @@ def run(self, shared_data: MutableMapping[str, Any], **_: Any) -> dict[str, Any]
         fragments = universe.atoms.fragments
         results: dict[int, dict[str, float]] = {}
 
-        for group_id, mol_ids in groups.items():
+        for group_id, mol_ids in sorted(groups.items()):
             results[group_id] = {"ua": 0.0, "res": 0.0, "poly": 0.0}
             if not mol_ids:
                 continue

CodeEntropy/entropy/nodes/orientational.py

@@ -52,7 +52,7 @@ def run(self, shared_data: MutableMapping[str, Any], **_: Any) -> dict[str, Any]
 
         results: dict[int, float] = {}
 
-        for group_id, mol_ids in groups.items():
+        for group_id, mol_ids in sorted(groups.items()):
             results[group_id] = 0
             if not mol_ids:
                 continue

CodeEntropy/entropy/nodes/vibrational.py

@@ -90,7 +90,7 @@ def run(self, shared_data: MutableMapping[str, Any], **_: Any) -> dict[str, Any]
 
         results: dict[int, dict[str, dict[str, float]]] = {}
 
-        for group_id, mol_ids in groups.items():
+        for group_id, mol_ids in sorted(groups.items()):
             results[group_id] = {}
             if not mol_ids:
                 continue
@@ -198,7 +198,7 @@ def _get_group_id_to_index(self, shared_data: Mapping[str, Any]) -> dict[int, in
         if isinstance(gid2i, dict) and gid2i:
             return gid2i
         groups = shared_data["groups"]
-        return {gid: i for i, gid in enumerate(groups.keys())}
+        return {gid: i for i, gid in enumerate(sorted(groups.keys()))}
 
     def _get_ua_frame_counts(self, shared_data: Mapping[str, Any]) -> dict[CovKey, int]:
         """Extract per-(group,residue) frame counts for united-atom covariances.

CodeEntropy/entropy/workflow.py

@@ -293,15 +293,15 @@ def _split_water_groups(
 
         water_groups = {
             gid: mol_ids
-            for gid, mol_ids in groups.items()
+            for gid, mol_ids in sorted(groups.items())
             if any(
                 res.resid in water_resids
                 for mol in [universe.atoms.fragments[i] for i in mol_ids]
                 for res in mol.residues
             )
         }
         nonwater_groups = {
-            gid: g for gid, g in groups.items() if gid not in water_groups
+            gid: g for gid, g in sorted(groups.items()) if gid not in water_groups
         }
         return nonwater_groups, water_groups
 
@@ -354,7 +354,7 @@ def _finalize_molecule_results(self) -> None:
             except (TypeError, ValueError):
                 logger.warning("Skipping invalid entry: %s, %s", group_id, result)
 
-        for group_id, total in entropy_by_group.items():
+        for group_id, total in sorted(entropy_by_group.items()):
             self._reporter.molecule_data.append(
                 (group_id, "Group Total", "Group Total Entropy", total)
             )

CodeEntropy/levels/nodes/covariance.py

@@ -93,7 +93,7 @@ def run(self, ctx: FrameCtx) -> dict[str, Any]:
         res_molcount: dict[int, int] = {}
         poly_molcount: dict[int, int] = {}
 
-        for group_id, mol_ids in groups.items():
+        for group_id, mol_ids in sorted(groups.items()):
             for mol_id in mol_ids:
                 mol = fragments[mol_id]
                 level_list = levels[mol_id]

CodeEntropy/results/reporter.py

@@ -408,9 +408,9 @@ def _build_grouped_payload(
                 key = f"{level}:{typ}"
                 groups[gid]["components"][key] = val
 
-        for _gid, g in groups.items():
+        for g in groups.values():
             if g["total"] is None:
-                comps = g["components"].values()
+                comps = sorted(g["components"].values())
                 g["total"] = float(sum(comps)) if comps else 0.0
 
         payload: dict[str, Any] = {

tests/regression/baselines/ethyl-acetate/axes_off.json

@@ -1,10 +1,10 @@
 {
   "args": {
     "top_traj_file": [
-      "/home/harry-swift/BioSim/software/CodeEntropy/.testdata/benzaldehyde/molecules.top",
-      "/home/harry-swift/BioSim/software/CodeEntropy/.testdata/benzaldehyde/trajectory.crd"
+      "/home/harry-swift/BioSim/software/CodeEntropy/.testdata/ethyl-acetate/molecules.top",
+      "/home/harry-swift/BioSim/software/CodeEntropy/.testdata/ethyl-acetate/trajectory.crd"
     ],
-    "force_file": "/home/harry-swift/BioSim/software/CodeEntropy/.testdata/benzaldehyde/forces.frc",
+    "force_file": "/home/harry-swift/BioSim/software/CodeEntropy/.testdata/ethyl-acetate/forces.frc",
     "file_format": "MDCRD",
     "kcal_force_units": true,
     "selection_string": "resid 1:10",
@@ -14,7 +14,7 @@
     "bin_width": 30,
     "temperature": 298.0,
     "verbose": false,
-    "output_file": "/tmp/pytest-of-harry-swift/pytest-47/test_regression_matches_baseli0/job001/output_file.json",
+    "output_file": "/tmp/pytest-of-harry-swift/pytest-1/popen-gw0/test_regression_matches_baseli0/job001/output_file.json",
     "force_partitioning": 0.5,
     "water_entropy": true,
     "grouping": "molecules",
@@ -24,22 +24,22 @@
   },
   "provenance": {
     "python": "3.14.3",
-    "platform": "Linux-6.17.0-19-generic-x86_64-with-glibc2.39",
+    "platform": "Linux-6.17.0-20-generic-x86_64-with-glibc2.39",
     "codeentropy_version": "2.1.0",
-    "git_sha": "be46d826f4ae38e3c6e62a7d5bcddeca85e31590"
+    "git_sha": "35b54c7d4ea40dac345db7fe8f6a0285bf6852e8"
   },
   "groups": {
     "0": {
       "components": {
-        "united_atom:Transvibrational": 0.08982962903796131,
-        "united_atom:Rovibrational": 32.16018134884085,
-        "residue:FTmat-Transvibrational": 88.7671666695003,
-        "residue:FTmat-Rovibrational": 61.61036267672132,
-        "united_atom:Conformational": 0.0,
+        "united_atom:Transvibrational": 1.2655393305199973,
+        "united_atom:Rovibrational": 68.85184585731292,
+        "residue:FTmat-Transvibrational": 77.33844477785695,
+        "residue:FTmat-Rovibrational": 56.03921993686319,
+        "united_atom:Conformational": 8.140778318198597,
         "residue:Conformational": 0.0,
-        "residue:Orientational": 7.791711490122748
+        "residue:Orientational": 3.2718547817092687
       },
-      "total": 190.41925181422317
+      "total": 214.9076830024609
     }
   }
 }

tests/regression/configs/ethyl-acetate/axes_off.yaml

@@ -1,10 +1,10 @@
 ---
 
 run1:
-  force_file: ".testdata/benzaldehyde/forces.frc"
+  force_file: ".testdata/ethyl-acetate/forces.frc"
   top_traj_file:
-    - ".testdata/benzaldehyde/molecules.top"
-    - ".testdata/benzaldehyde/trajectory.crd"
+    - ".testdata/ethyl-acetate/molecules.top"
+    - ".testdata/ethyl-acetate/trajectory.crd"
   selection_string: "resid 1:10"
   start: 0
   end: 1