emmet-builders 0.48.2__tar.gz → 0.48.4__tar.gz

{emmet-builders-0.48.2 → emmet-builders-0.48.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: emmet-builders
-Version: 0.48.2
+Version: 0.48.4
 Summary: Builders for the Emmet Library
 Home-page: https://github.com/materialsproject/emmet
 Author: The Materials Project

{emmet-builders-0.48.2 → emmet-builders-0.48.4}/emmet/builders/abinit/phonon.py

@@ -56,7 +56,8 @@ class PhononBuilder(Builder):
         standard MongoDB document.
 
         Args:
-            materials (Store): source Store of materials documents.
+            phonon_materials (Store): source Store of phonon materials documents
+                containing abinit_input and abinit_output.
             ddb_source (Store): source Store of ddb files. Matching the data in the materials Store.
             phonon (Store): target Store of the phonon properties
             phonon_bs (Store): target Store for the phonon band structure. The document may

{emmet-builders-0.48.2 → emmet-builders-0.48.4}/emmet/builders/abinit/sound_velocity.py

@@ -1,5 +1,4 @@
 import tempfile
-import gridfs
 import traceback
 from typing import Optional, Dict, List, Iterator
 
@@ -16,7 +15,8 @@ from emmet.core.utils import jsanitize
 class SoundVelocityBuilder(Builder):
     def __init__(
         self,
-        materials: Store,
+        phonon_materials: Store,
+        ddb_source: Store,
         sound_vel: Store,
         query: Optional[dict] = None,
         manager: Optional[TaskManager] = None,
@@ -27,14 +27,17 @@ class SoundVelocityBuilder(Builder):
         the phonon calculations.
 
         Args:
-            materials (Store): source Store of materials documents
+            phonon_materials (Store): source Store of phonon materials documents
+                containing abinit_input and abinit_output.
+            ddb_source (Store): source Store of ddb files. Matching the data in the materials Store.
             sound_vel (Store): target Store of the sound velocity
             query (dict): dictionary to limit materials to be analyzed
             manager (TaskManager): an instance of the abipy TaskManager. If None it will be
                 generated from user configuration.
         """
 
-        self.materials = materials
+        self.phonon_materials = phonon_materials
+        self.ddb_source = ddb_source
         self.sound_vel = sound_vel
         self.query = query or {}
 
@@ -43,7 +46,7 @@ class SoundVelocityBuilder(Builder):
         else:
             self.manager = manager
 
-        super().__init__(sources=[materials], targets=[sound_vel], **kwargs)
+        super().__init__(sources=[phonon_materials], targets=[sound_vel], **kwargs)
 
     def get_items(self) -> Iterator[Dict]:
         """
@@ -71,15 +74,12 @@ class SoundVelocityBuilder(Builder):
         # file ids to be fetched
         projection["abinit_output.ddb_id"] = 1
 
-        # initialize the gridfs
-        ddbfs = gridfs.GridFS(self.materials.collection.database, "ddb_fs")
-
         for m in mats:
-            item = self.materials.query_one(properties=projection, criteria={self.materials.key: m})
+            item = self.phonon_materials.query_one(properties=projection, criteria={self.phonon_materials.key: m})
 
             # Read the DDB file and pass as an object. Do not write here since in case of parallel
             # execution each worker will write its own file.
-            item["ddb_str"] = ddbfs.get(item["abinit_output"]["ddb_id"]).read().decode("utf-8")
+            item["ddb_str"] = self.ddb_source.get(item["abinit_output"]["ddb_id"]).read().decode("utf-8")
 
             yield item
 

{emmet-builders-0.48.2 → emmet-builders-0.48.4}/emmet/builders/molecules/atomic.py

@@ -229,11 +229,22 @@ class PartialChargesBuilder(Builder):
                     best_entry = relevant_entries[0]
                     task = best_entry["task_id"]
 
-                    task_doc = TaskDocument(
-                        **self.tasks.query_one({"task_id": int(task),
-                                                "formula_alphabetical": formula,
-                                                "orig": {"$exists": True}})
-                    )
+                    tdoc = self.tasks.query_one({"task_id": task,
+                                                 "formula_alphabetical": formula,
+                                                 "orig": {"$exists": True}})
+
+                    if tdoc is None:
+                        try:
+                            tdoc = self.tasks.query_one({"task_id": int(task),
+                                                         "formula_alphabetical": formula,
+                                                         "orig": {"$exists": True}})
+                        except ValueError:
+                            tdoc = None
+
+                    if tdoc is None:
+                        continue
+
+                    task_doc = TaskDocument(**tdoc)
 
                     if task_doc is None:
                         continue
@@ -277,7 +288,7 @@ class PartialChargesBuilder(Builder):
             # Neither molecule_id nor method need to be unique, but the combination must be
             self.charges.update(
                 docs=docs,
-                key=["molecule_id", "method"],
+                key=["molecule_id", "method", "solvent"],
             )
         else:
             self.logger.info("No items to update")
@@ -488,15 +499,23 @@ class PartialSpinsBuilder(Builder):
                     best_entry = relevant_entries[0]
                     task = best_entry["task_id"]
 
-                    task_doc = TaskDocument(
-                        **self.tasks.query_one({"task_id": int(task),
-                                                "formula_alphabetical": formula,
-                                                "orig": {"$exists": True}})
-                    )
+                    tdoc = self.tasks.query_one({"task_id": task,
+                                                 "formula_alphabetical": formula,
+                                                 "orig": {"$exists": True}})
 
-                    if task_doc is None:
+                    if tdoc is None:
+                        try:
+                            tdoc = self.tasks.query_one({"task_id": int(task),
+                                                         "formula_alphabetical": formula,
+                                                         "orig": {"$exists": True}})
+                        except ValueError:
+                            tdoc = None
+
+                    if tdoc is None:
                         continue
 
+                    task_doc = TaskDocument(**tdoc)
+
                     doc = PartialSpinsDoc.from_task(
                         task_doc,
                         molecule_id=mol.molecule_id,
@@ -538,7 +557,7 @@ class PartialSpinsBuilder(Builder):
             # Neither molecule_id nor method need to be unique, but the combination must be
             self.spins.update(
                 docs=docs,
-                key=["molecule_id", "method"],
+                key=["molecule_id", "method", "solvent"],
             )
         else:
             self.logger.info("No items to update")

{emmet-builders-0.48.2 → emmet-builders-0.48.4}/emmet/builders/molecules/bonds.py

@@ -247,11 +247,22 @@ class BondingBuilder(Builder):
                     best_entry = relevant_entries[0]
                     task = best_entry["task_id"]
 
-                    task_doc = TaskDocument(
-                        **self.tasks.query_one({"task_id": int(task),
-                                                "formula_alphabetical": formula,
-                                                "orig": {"$exists": True}})
-                    )
+                    tdoc = self.tasks.query_one({"task_id": task,
+                                                 "formula_alphabetical": formula,
+                                                 "orig": {"$exists": True}})
+
+                    if tdoc is None:
+                        try:
+                            tdoc = self.tasks.query_one({"task_id": int(task),
+                                                         "formula_alphabetical": formula,
+                                                         "orig": {"$exists": True}})
+                        except ValueError:
+                            tdoc = None
+
+                    if tdoc is None:
+                        continue
+
+                    task_doc = TaskDocument(**tdoc)
 
                     if task_doc is None:
                         continue
@@ -294,7 +305,7 @@ class BondingBuilder(Builder):
             # Neither molecule_id nor method need to be unique, but the combination must be
             self.bonds.update(
                 docs=docs,
-                key=["molecule_id", "method"],
+                key=["molecule_id", "method", "solvent"],
             )
         else:
             self.logger.info("No items to update")

{emmet-builders-0.48.2 → emmet-builders-0.48.4}/emmet/builders/molecules/orbitals.py

@@ -213,11 +213,22 @@ class OrbitalBuilder(Builder):
                     for best in sorted_entries:
                         task = best["task_id"]
 
-                        task_doc = TaskDocument(
-                            **self.tasks.query_one({"task_id": int(task),
-                                                    "formula_alphabetical": formula,
-                                                    "orig": {"$exists": True}})
-                        )
+                        tdoc = self.tasks.query_one({"task_id": task,
+                                                     "formula_alphabetical": formula,
+                                                     "orig": {"$exists": True}})
+
+                        if tdoc is None:
+                            try:
+                                tdoc = self.tasks.query_one({"task_id": int(task),
+                                                             "formula_alphabetical": formula,
+                                                             "orig": {"$exists": True}})
+                            except ValueError:
+                                tdoc = None
+
+                        if tdoc is None:
+                            continue
+
+                        task_doc = TaskDocument(**tdoc)
 
                         if task_doc is None:
                             continue
@@ -258,7 +269,7 @@ class OrbitalBuilder(Builder):
             self.orbitals.remove_docs({self.orbitals.key: {"$in": molecule_ids}})
             self.orbitals.update(
                 docs=docs,
-                key=["molecule_id"],
+                key=["molecule_id", "solvent"],
             )
         else:
             self.logger.info("No items to update")

{emmet-builders-0.48.2 → emmet-builders-0.48.4}/emmet/builders/molecules/redox.py

@@ -5,9 +5,6 @@ from itertools import chain, groupby
 from math import ceil
 from typing import Any, Dict, Iterable, Iterator, List, Optional, Union
 
-from pymatgen.analysis.graphs import MoleculeGraph
-from pymatgen.analysis.local_env import OpenBabelNN
-
 from maggma.builders import Builder
 from maggma.core import Store
 from maggma.utils import grouper
@@ -17,7 +14,7 @@ from emmet.core.qchem.molecule import MoleculeDoc
 from emmet.core.molecules.bonds import metals
 from emmet.core.molecules.thermo import ThermoDoc
 from emmet.core.molecules.redox import RedoxDoc
-from emmet.core.utils import confirm_molecule, jsanitize
+from emmet.core.utils import confirm_molecule, get_graph_hash, jsanitize
 from emmet.builders.settings import EmmetBuildSettings
 
 
@@ -213,26 +210,54 @@ class RedoxBuilder(Builder):
                     continue
 
                 ie_sp_task_ids = [
-                    int(e["task_id"]) for e in gg.entries
+                    e["task_id"] for e in gg.entries
                     if e["charge"] == gg.charge + 1
                     and e["task_type"] == "Single Point"
                     and e["output"].get("final_energy")
                 ]
-                ie_tasks = [TaskDocument(**e) for e in self.tasks.query({"task_id": {"$in": ie_sp_task_ids},
-                                                                         "formula_alphabetical": formula,
-                                                                         "orig": {"$exists": True}
-                                                                         })]
+                ie_tasks = list()
+                for i in ie_sp_task_ids:
+                    tdoc = self.tasks.query_one({"task_id": i,
+                                                 "formula_alphabetical": formula,
+                                                 "orig": {"$exists": True}})
+
+                    if tdoc is None:
+                        try:
+                            tdoc = self.tasks.query_one({"task_id": int(i),
+                                                         "formula_alphabetical": formula,
+                                                         "orig": {"$exists": True}})
+                        except ValueError:
+                            tdoc = None
+
+                    if tdoc is None:
+                        continue
+
+                    ie_tasks.append(TaskDocument(**tdoc))
 
                 ea_sp_task_ids = [
-                    int(e["task_id"]) for e in gg.entries
+                    e["task_id"] for e in gg.entries
                     if e["charge"] == gg.charge - 1
                     and e["task_type"] == "Single Point"
                     and e["output"].get("final_energy")
                 ]
-                ea_tasks = [TaskDocument(**e) for e in self.tasks.query({"task_id": {"$in": ea_sp_task_ids},
-                                                                         "formula_alphabetical": formula,
-                                                                         "orig": {"$exists": True}
-                                                                         })]
+                ea_tasks = list()
+                for i in ea_sp_task_ids:
+                    tdoc = self.tasks.query_one({"task_id": i,
+                                                 "formula_alphabetical": formula,
+                                                 "orig": {"$exists": True}})
+
+                    if tdoc is None:
+                        try:
+                            tdoc = self.tasks.query_one({"task_id": int(i),
+                                                         "formula_alphabetical": formula,
+                                                         "orig": {"$exists": True}})
+                        except ValueError:
+                            tdoc = None
+
+                    if tdoc is None:
+                        continue
+
+                    ea_tasks.append(TaskDocument(**tdoc))
 
                 grouped_docs = self._collect_by_lot_solvent(thermo_docs, ie_tasks, ea_tasks)
                 if gg.charge in charges:
@@ -325,7 +350,7 @@ class RedoxBuilder(Builder):
             self.redox.remove_docs({self.redox.key: {"$in": molecule_ids}})
             self.redox.update(
                 docs=docs,
-                key=["molecule_id"],
+                key=["molecule_id", "solvent"],
             )
         else:
             self.logger.info("No items to update")
@@ -339,7 +364,7 @@ class RedoxBuilder(Builder):
         :return: Grouped molecule entries
         """
 
-        mol_graphs_nometal: List[MoleculeGraph] = list()
+        graph_hashes_nometal: List[str] = list()
         results = defaultdict(list)
 
         # Within each group, group by the covalent molecular graph
@@ -352,19 +377,17 @@ class RedoxBuilder(Builder):
                 mol_nometal.remove_species(metals)
 
             mol_nometal.set_charge_and_spin(0)
-            mg_nometal = MoleculeGraph.with_local_env_strategy(
-                mol_nometal, OpenBabelNN()
-            )
+            gh_nometal = get_graph_hash(mol_nometal, node_attr="specie")
 
             match = None
-            for i, mg in enumerate(mol_graphs_nometal):
-                if mg_nometal.isomorphic_to(mg):
+            for i, gh in enumerate(graph_hashes_nometal):
+                if gh_nometal == gh:
                     match = i
                     break
 
             if match is None:
-                results[len(mol_graphs_nometal)].append(t)
-                mol_graphs_nometal.append(mg_nometal)
+                results[len(graph_hashes_nometal)].append(t)
+                graph_hashes_nometal.append(gh_nometal)
             else:
                 results[match].append(t)
 

{emmet-builders-0.48.2 → emmet-builders-0.48.4}/emmet/builders/molecules/summary.py

@@ -3,6 +3,8 @@ from itertools import chain
 from math import ceil
 from typing import Any, Optional, Iterable, Iterator, List, Dict
 
+# from monty.serialization import loadfn, dumpfn
+
 from maggma.builders import Builder
 from maggma.core import Store
 from maggma.utils import grouper
@@ -284,6 +286,10 @@ class SummaryBuilder(Builder):
             for td in to_delete:
                 del d[td]
 
+            # For debugging; keep because it might be needed again
+            # dumpfn(d, f"{mol_id}.json.gz")
+            # break
+
             summary_doc = SummaryDoc.from_docs(molecule_id=mol_id, docs=d)
             summary_docs.append(summary_doc)
 

{emmet-builders-0.48.2 → emmet-builders-0.48.4}/emmet/builders/molecules/thermo.py

@@ -255,7 +255,7 @@ class ThermoBuilder(Builder):
 
         thermo_docs = list()
 
-        mm = MoleculeMatcher()
+        mm = MoleculeMatcher(tolerance=0.000001)
 
         for mol in mols:
             this_thermo_docs = list()
@@ -277,7 +277,7 @@ class ThermoBuilder(Builder):
                     task_type = entry["task_type"]
 
                 if (
-                    task_type == "Single Point"
+                    task_type in ["Single Point", "Force"]
                     and entry["charge"] == mol.charge
                     and entry["spin_multiplicity"] == mol.spin_multiplicity
                 ):
@@ -307,11 +307,22 @@ class ThermoBuilder(Builder):
                 )[0]
                 task = best["task_id"]
 
-                task_doc = TaskDocument(
-                        **self.tasks.query_one({"task_id": int(task),
-                                                "formula_alphabetical": formula,
-                                                "orig": {"$exists": True}})
-                )
+                tdoc = self.tasks.query_one({"task_id": task,
+                                             "formula_alphabetical": formula,
+                                             "orig": {"$exists": True}})
+
+                if tdoc is None:
+                    try:
+                        tdoc = self.tasks.query_one({"task_id": int(task),
+                                                     "formula_alphabetical": formula,
+                                                     "orig": {"$exists": True}})
+                    except ValueError:
+                        tdoc = None
+
+                if tdoc is None:
+                    continue
+
+                task_doc = TaskDocument(**tdoc)
 
                 if task_doc is None:
                     continue
@@ -337,9 +348,11 @@ class ThermoBuilder(Builder):
 
                     matching_structures = list()
                     for entry in thermo_entries:
-                        if (mm.fit(Molecule.from_dict(entry["molecule"]), Molecule.from_dict(best_spec["molecule"]))
-                            and (sum(evaluate_lot(entry["level_of_theory"])) <
-                                 sum(evaluate_lot(best_spec["level_of_theory"])))):
+                        mol1 = Molecule.from_dict(entry["molecule"])
+                        mol2 = Molecule.from_dict(best_spec["molecule"])
+                        if ((mm.fit(mol1, mol2) or mol1 == mol2)
+                            and (sum(evaluate_lot(best_spec["level_of_theory"])) <
+                                 sum(evaluate_lot(entry["level_of_theory"])))):
                             matching_structures.append(entry)
 
                     if len(matching_structures) == 0:
@@ -416,7 +429,7 @@ class ThermoBuilder(Builder):
             self.thermo.remove_docs({self.thermo.key: {"$in": molecule_ids}})
             self.thermo.update(
                 docs=docs,
-                key=["molecule_id"],
+                key=["molecule_id", "solvent"],
             )
         else:
             self.logger.info("No items to update")

{emmet-builders-0.48.2 → emmet-builders-0.48.4}/emmet/builders/molecules/vibration.py

@@ -206,11 +206,22 @@ class VibrationBuilder(Builder):
                     )[0]
                     task = best["task_id"]
 
-                task_doc = TaskDocument(
-                        **self.tasks.query_one({"task_id": int(task),
-                                                "formula_alphabetical": formula,
-                                                "orig": {"$exists": True}})
-                )
+                tdoc = self.tasks.query_one({"task_id": task,
+                                             "formula_alphabetical": formula,
+                                             "orig": {"$exists": True}})
+
+                if tdoc is None:
+                    try:
+                        tdoc = self.tasks.query_one({"task_id": int(task),
+                                                     "formula_alphabetical": formula,
+                                                     "orig": {"$exists": True}})
+                    except ValueError:
+                        tdoc = None
+
+                if tdoc is None:
+                    continue
+
+                task_doc = TaskDocument(**tdoc)
 
                 if task_doc is None:
                     continue
@@ -249,7 +260,7 @@ class VibrationBuilder(Builder):
             self.vibes.remove_docs({self.vibes.key: {"$in": molecule_ids}})
             self.vibes.update(
                 docs=docs,
-                key=["molecule_id"],
+                key=["molecule_id", "solvent"],
             )
         else:
             self.logger.info("No items to update")