emmet-builders 0.84.2rc6__py3-none-any.whl → 0.84.2rc7__py3-none-any.whl

emmet/builders/molecules/vibration.py

@@ -27,7 +27,7 @@ class VibrationBuilder(Builder):
     each solvent available).
 
     The process is as follows:
-        1. Gather MoleculeDocs by formula
+        1. Gather MoleculeDocs by species hash
         2. For each doc, sort tasks by solvent
         3. For each solvent, grab the best TaskDoc (doc with vibrational
             information that has the highest level of theory with lowest
@@ -73,12 +73,14 @@ class VibrationBuilder(Builder):
         self.tasks.ensure_index("last_updated")
         self.tasks.ensure_index("state")
         self.tasks.ensure_index("formula_alphabetical")
+        self.tasks.ensure_index("species_hash")
 
         # Search index for molecules
         self.molecules.ensure_index("molecule_id")
         self.molecules.ensure_index("last_updated")
         self.molecules.ensure_index("task_ids")
         self.molecules.ensure_index("formula_alphabetical")
+        self.molecules.ensure_index("species_hash")
 
         # Search index for vibrational properties
         self.vibes.ensure_index("molecule_id")
@@ -97,23 +99,23 @@ class VibrationBuilder(Builder):
 
         self.logger.info("Finding documents to process")
         all_mols = list(
-            self.molecules.query(
-                temp_query, [self.molecules.key, "formula_alphabetical"]
-            )
+            self.molecules.query(temp_query, [self.molecules.key, "species_hash"])
         )
 
         processed_docs = set([e for e in self.vibes.distinct("molecule_id")])
         to_process_docs = {d[self.molecules.key] for d in all_mols} - processed_docs
-        to_process_forms = {
-            d["formula_alphabetical"]
+        to_process_hashes = {
+            d["species_hash"]
             for d in all_mols
             if d[self.molecules.key] in to_process_docs
         }
 
-        N = ceil(len(to_process_forms) / number_splits)
+        N = ceil(len(to_process_hashes) / number_splits)
 
-        for formula_chunk in grouper(to_process_forms, N):
-            yield {"query": {"formula_alphabetical": {"$in": list(formula_chunk)}}}
+        for hash_chunk in grouper(to_process_hashes, N):
+            query = dict(temp_query)
+            query["species_hash"] = {"$in": list(hash_chunk)}
+            yield {"query": query}
 
     def get_items(self) -> Iterator[List[Dict]]:
         """
@@ -138,28 +140,26 @@ class VibrationBuilder(Builder):
 
         self.logger.info("Finding documents to process")
         all_mols = list(
-            self.molecules.query(
-                temp_query, [self.molecules.key, "formula_alphabetical"]
-            )
+            self.molecules.query(temp_query, [self.molecules.key, "species_hash"])
         )
 
         processed_docs = set([e for e in self.vibes.distinct("molecule_id")])
         to_process_docs = {d[self.molecules.key] for d in all_mols} - processed_docs
-        to_process_forms = {
-            d["formula_alphabetical"]
+        to_process_hashes = {
+            d["species_hash"]
             for d in all_mols
             if d[self.molecules.key] in to_process_docs
         }
 
         self.logger.info(f"Found {len(to_process_docs)} unprocessed documents")
-        self.logger.info(f"Found {len(to_process_forms)} unprocessed formulas")
+        self.logger.info(f"Found {len(to_process_hashes)} unprocessed hashes")
 
         # Set total for builder bars to have a total
-        self.total = len(to_process_forms)
+        self.total = len(to_process_hashes)
 
-        for formula in to_process_forms:
+        for shash in to_process_hashes:
             mol_query = dict(temp_query)
-            mol_query["formula_alphabetical"] = formula
+            mol_query["species_hash"] = shash
             molecules = list(self.molecules.query(criteria=mol_query))
 
             yield molecules
@@ -176,9 +176,9 @@ class VibrationBuilder(Builder):
         """
 
         mols = [MoleculeDoc(**item) for item in items]
-        formula = mols[0].formula_alphabetical
+        shash = mols[0].species_hash
         mol_ids = [m.molecule_id for m in mols]
-        self.logger.debug(f"Processing {formula} : {mol_ids}")
+        self.logger.debug(f"Processing {shash} : {mol_ids}")
 
         vibe_docs = list()
 
@@ -213,7 +213,7 @@ class VibrationBuilder(Builder):
                 tdoc = self.tasks.query_one(
                     {
                         "task_id": task,
-                        "formula_alphabetical": formula,
+                        "species_hash": shash,
                         "orig": {"$exists": True},
                     }
                 )
@@ -223,7 +223,7 @@ class VibrationBuilder(Builder):
                         tdoc = self.tasks.query_one(
                             {
                                 "task_id": int(task),
-                                "formula_alphabetical": formula,
+                                "species_hash": shash,
                                 "orig": {"$exists": True},
                             }
                         )
@@ -243,7 +243,7 @@ class VibrationBuilder(Builder):
                 )
                 vibe_docs.append(vibe_doc)
 
-        self.logger.debug(f"Produced {len(vibe_docs)} vibration docs for {formula}")
+        self.logger.debug(f"Produced {len(vibe_docs)} vibration docs for {shash}")
 
         return jsanitize([doc.model_dump() for doc in vibe_docs], allow_bson=True)
 

emmet/builders/qchem/molecules.py

@@ -138,6 +138,7 @@ class MoleculesAssociationBuilder(Builder):
         self.tasks.ensure_index("formula_alphabetical")
         self.tasks.ensure_index("smiles")
         self.tasks.ensure_index("species_hash")
+        self.tasks.ensure_index("coord_hash")
 
         # Search index for molecules
         self.assoc.ensure_index("molecule_id")
@@ -165,7 +166,9 @@ class MoleculesAssociationBuilder(Builder):
         N = ceil(len(to_process_hashes) / number_splits)
 
         for hash_chunk in grouper(to_process_hashes, N):
-            yield {"query": {"species_hash": {"$in": list(hash_chunk)}}}
+            query = dict(temp_query)
+            query["species_hash"] = {"$in": list(hash_chunk)}
+            yield {"query": query}
 
     def get_items(self) -> Iterator[List[TaskDocument]]:
         """
@@ -390,6 +393,7 @@ class MoleculesBuilder(Builder):
         self.assoc.ensure_index("last_updated")
         self.assoc.ensure_index("task_ids")
         self.assoc.ensure_index("formula_alphabetical")
+        self.assoc.ensure_index("species_hash")
 
         # Search index for molecules
         self.molecules.ensure_index("molecule_id")
@@ -433,16 +437,18 @@ class MoleculesBuilder(Builder):
             xyz_species_id_map[d[self.assoc.key]] = this_id
         to_process_docs = assoc_ids - processed_docs
 
-        to_process_forms = {
-            d["formula_alphabetical"]
+        to_process_hashes = {
+            d["species_hash"]
             for d in all_assoc
             if xyz_species_id_map[d[self.assoc.key]] in to_process_docs
         }
 
-        N = ceil(len(to_process_forms) / number_splits)
+        N = ceil(len(to_process_hashes) / number_splits)
 
-        for formula_chunk in grouper(to_process_forms, N):
-            yield {"query": {"formula_alphabetical": {"$in": list(formula_chunk)}}}
+        for hash_chunk in grouper(to_process_hashes, N):
+            query = dict(temp_query)
+            query["species_hash"] = {"$in": list(hash_chunk)}
+            yield {"query": query}
 
     def get_items(self) -> Iterator[List[Dict]]:
         """
@@ -495,21 +501,21 @@ class MoleculesBuilder(Builder):
             xyz_species_id_map[d[self.assoc.key]] = this_id
         to_process_docs = assoc_ids - processed_docs
 
-        to_process_forms = {
-            d["formula_alphabetical"]
+        to_process_hashes = {
+            d["species_hash"]
             for d in all_assoc
             if xyz_species_id_map[d[self.assoc.key]] in to_process_docs
         }
 
         self.logger.info(f"Found {len(to_process_docs)} unprocessed documents")
-        self.logger.info(f"Found {len(to_process_forms)} unprocessed formulas")
+        self.logger.info(f"Found {len(to_process_hashes)} unprocessed hashes")
 
         # Set total for builder bars to have a total
-        self.total = len(to_process_forms)
+        self.total = len(to_process_hashes)
 
-        for formula in to_process_forms:
+        for shash in to_process_hashes:
             assoc_query = dict(temp_query)
-            assoc_query["formula_alphabetical"] = formula
+            assoc_query["species_hash"] = shash
             assoc = list(self.assoc.query(criteria=assoc_query))
 
             yield assoc
@@ -526,9 +532,9 @@ class MoleculesBuilder(Builder):
         """
 
         assoc = [MoleculeDoc(**item) for item in items]
-        formula = assoc[0].formula_alphabetical
+        shash = assoc[0].species_hash
         mol_ids = [a.molecule_id for a in assoc]
-        self.logger.debug(f"Processing {formula} : {mol_ids}")
+        self.logger.debug(f"Processing {shash} : {mol_ids}")
 
         complete_mol_docs = list()
 
@@ -646,7 +652,7 @@ class MoleculesBuilder(Builder):
 
                 complete_mol_docs.append(base_doc)
 
-        self.logger.debug(f"Produced {len(complete_mol_docs)} molecules for {formula}")
+        self.logger.debug(f"Produced {len(complete_mol_docs)} molecules for {shash}")
 
         return jsanitize(
             [mol.model_dump() for mol in complete_mol_docs], allow_bson=True

{emmet_builders-0.84.2rc6.dist-info → emmet_builders-0.84.2rc7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: emmet-builders
-Version: 0.84.2rc6
+Version: 0.84.2rc7
 Summary: Builders for the Emmet Library
 Home-page: https://github.com/materialsproject/emmet
 Author: The Materials Project

{emmet_builders-0.84.2rc6.dist-info → emmet_builders-0.84.2rc7.dist-info}/RECORD

@@ -32,21 +32,23 @@ emmet/builders/matscholar/missing_compositions.py,sha256=RGQOEhfmJ6YMbjD4osLWqs7
 emmet/builders/mobility/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 emmet/builders/mobility/migration_graph.py,sha256=WEXtPSn0UE5Q8mnvJ-T19FB3_LrZ3ojvNyRBs1PXWRg,3923
 emmet/builders/molecules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-emmet/builders/molecules/atomic.py,sha256=X590oMDIPaHJMk0Xuy_r4hATm1TEj0hKfJD6ofi1asg,20823
-emmet/builders/molecules/bonds.py,sha256=5orXkCBgBBOqz1iGoacDUb5iGMsOPVmdmghtQLud9ZU,12086
-emmet/builders/molecules/metal_binding.py,sha256=gyL5Nu1pmu0ZJq4HgTxwLh8_1696pJiMnrFggFESnjo,23317
-emmet/builders/molecules/orbitals.py,sha256=W_7_3zz9bFfHQZgAMdp3PSSt4PDH4DVZVervHPrv1Pk,10041
-emmet/builders/molecules/redox.py,sha256=HHmj-nFMTEV7qq3g3GM2lB5RdLUMBE-xOIZogIgmORc,18427
-emmet/builders/molecules/summary.py,sha256=I9-4-oKoUSg5sxvr-CHYVIuCyD48mpV9rsMno4pbbOk,13198
-emmet/builders/molecules/thermo.py,sha256=DizVM9rLXo7AhHW3cq0Bo6vO1OI6YtK4PeIVixmt47g,19855
-emmet/builders/molecules/vibration.py,sha256=9LNeKh8BHck-ooW4XzAZAFeio2u6bDwdsUV1aA5XVb4,9501
+emmet/builders/molecules/atomic.py,sha256=DBG_FScwT7YU1GgI69yRrR3_wUoWBwiP1uBvbL7xP3Y,20839
+emmet/builders/molecules/bonds.py,sha256=aHp9U_LX3sZvdTIaZj2T8PG_wTFYqw6nOcYC-4MiI0E,12103
+emmet/builders/molecules/electric.py,sha256=ldoLSfIAjue6YQlyXkgJRXLcfh178goiarjI_f_EtH4,10065
+emmet/builders/molecules/metal_binding.py,sha256=kimYsmQWdmukRRX2_GgVywCNRhNHz_-fp2oMYJTVMrg,23308
+emmet/builders/molecules/orbitals.py,sha256=nIsmx0m6Zi402opHE6OoEljGgQ2714p1Gig8Py1IXrU,10060
+emmet/builders/molecules/redox.py,sha256=52er0zK_IVQ0UYUh7svml-zwlvOtbptz1D8ZYCglfI0,18448
+emmet/builders/molecules/summary.py,sha256=7KHsnc9PBstps6s-hK4mYrWOBHt26_PTPKsCSFw3018,13848
+emmet/builders/molecules/thermo.py,sha256=MutvuYJsU0Hj5Qaa_Z7qnikM6mkPSBPNE4RG8JK4qes,19874
+emmet/builders/molecules/trajectory.py,sha256=oKrmWtKJ6mC0d1uJRE7g72X97kkS7JQ7nMhupVOUEUU,18163
+emmet/builders/molecules/vibration.py,sha256=_FA-tRixghsJdlls6oO9U2abxCHWqWv5SucbxpP5mVQ,9520
 emmet/builders/qchem/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-emmet/builders/qchem/molecules.py,sha256=CZyVQzjfb-_gAS997BFbd9xkKwvwPWrquNH0Aoy6oY8,26217
+emmet/builders/qchem/molecules.py,sha256=qI8WFOJ69FMPu9hxGzoFR4V3y4qO7UhtzVZwG9AWPpw,26382
 emmet/builders/vasp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 emmet/builders/vasp/materials.py,sha256=5bjP-W5-gmSjDzmcHdF7bviwgk4ywUceCL4FcF9Ya9c,12700
 emmet/builders/vasp/mp_potcar_stats.json.gz,sha256=RD6gbZEmmmKQYRKpFtEKHzncGO1WsLYMPjn3wvONrIc,291869
 emmet/builders/vasp/task_validator.py,sha256=bmRTDiOWof4rpHVg3ksoxocN9xxieYu7IE-ylMjYOVs,2922
-emmet_builders-0.84.2rc6.dist-info/METADATA,sha256=BcolWawuU8KK3szLsPqC28hrhnz2W2PKXXw1zvGkEc0,2162
-emmet_builders-0.84.2rc6.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-emmet_builders-0.84.2rc6.dist-info/top_level.txt,sha256=6GcpbmWPeFhNCTfDFilb8GQ4T1UQu4z9c5jpobjwE-Q,6
-emmet_builders-0.84.2rc6.dist-info/RECORD,,
+emmet_builders-0.84.2rc7.dist-info/METADATA,sha256=QqGWpUDogkBmmZbyiHsduf3OWrUR3lfjmlBZigf8Kzk,2162
+emmet_builders-0.84.2rc7.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+emmet_builders-0.84.2rc7.dist-info/top_level.txt,sha256=6GcpbmWPeFhNCTfDFilb8GQ4T1UQu4z9c5jpobjwE-Q,6
+emmet_builders-0.84.2rc7.dist-info/RECORD,,