clean up

emmet-builders/emmet/builders/vasp/materials.py

@@ -1,21 +1,13 @@
 from datetime import datetime
 from itertools import chain
-from operator import itemgetter
-from typing import Dict, Iterator, List, Optional
+from typing import Dict, Iterable, Iterator, List, Optional
 
 from maggma.builders import Builder
 from maggma.stores import Store
-from pymatgen.core import Structure
-from pymatgen.analysis.structure_analyzer import oxide_type
-from pymatgen.analysis.structure_matcher import ElementComparator, StructureMatcher
+from maggma.utils import grouper
 
-from emmet.builders.utils import maximal_spanning_non_intersecting_subsets
-
-# from emmet.core import SETTINGS
-from emmet.builders import SETTINGS
 from emmet.builders.settings import EmmetBuildSettings
 from emmet.core.utils import group_structures, jsanitize
-from emmet.core.vasp.calc_types import TaskType
 from emmet.core.vasp.material import MaterialsDoc
 from emmet.core.vasp.task import TaskDocument
 
@@ -33,11 +25,8 @@ class MaterialsBuilder(Builder):
         1.) Find all documents with the same formula
         2.) Select only task documents for the task_types we can select properties from
         3.) Aggregate task documents based on strucutre similarity
-        4.) Convert task docs to property docs with metadata for selection and aggregation
-        5.) Select the best property doc for each property
-        6.) Build material document from best property docs
-        7.) Post-process material document
-        8.) Validate material document
+        4.) Create a MaterialDoc from the group of task documents
+        5.) Validate material document
 
     """
 
@@ -56,6 +45,7 @@ def __init__(
             materials: Store of materials documents to generate
             task_validation: Store for storing task validation results
             query: dictionary to limit tasks to be analyzed
+            settings: EmmetSettings to use in the build process
         """
 
         self.tasks = tasks

emmet-builders/emmet/builders/vasp/task_validator.py

@@ -1,15 +1,15 @@
-from typing import Dict, List, Union, Optional
+from typing import Dict, List, Optional, Union
 
 import numpy as np
 from maggma.builders import MapBuilder
 from maggma.core import Store
 from pymatgen.core import Structure
 
 from emmet.builders import SETTINGS
+from emmet.builders.settings import EmmetBuildSettings
 from emmet.core.vasp.calc_types import run_type, task_type
 from emmet.core.vasp.task import TaskDocument
 from emmet.core.vasp.validation import DeprecationMessage, ValidationDoc
-from emmet.builders.settings import EmmetBuildSettings
 
 
 class TaskValidator(MapBuilder):

emmet-builders/emmet/builders/vasp/thermo.py

@@ -1,23 +1,17 @@
 from collections import defaultdict
-from datetime import datetime
 from itertools import chain
-from typing import Dict, Iterator, List, Optional, Set, Tuple
+from typing import Dict, Iterable, Iterator, List, Optional, Set, Tuple
 
 from maggma.core import Builder, Store
+from maggma.utils import grouper
 from monty.json import MontyDecoder
-from pymatgen.core import Structure
 from pymatgen.analysis.phase_diagram import PhaseDiagramError
-from pymatgen.analysis.structure_analyzer import oxide_type
-from pymatgen.entries.compatibility import MaterialsProjectCompatibility
+from pymatgen.entries.compatibility import MaterialsProject2020Compatibility
 from pymatgen.entries.computed_entries import ComputedEntry, ComputedStructureEntry
 
-from emmet.core.utils import jsanitize
-from emmet.builders.utils import (
-    chemsys_permutations,
-    maximal_spanning_non_intersecting_subsets,
-)
+from emmet.builders.utils import chemsys_permutations
 from emmet.core.thermo import ThermoDoc
-from emmet.core.vasp.calc_types import run_type
+from emmet.core.utils import jsanitize
 
 
 class Thermo(Builder):
@@ -121,13 +115,12 @@ def get_items(self) -> Iterator[List[Dict]]:
             entries = self.get_entries(chemsys)
             yield entries
 
-    def process_item(self, item: Tuple[List[str], List[ComputedEntry]]):
+    def process_item(self, item: List[Dict]):
 
-        entries = item
-        if len(entries) == 0:
+        if len(item) == 0:
             return []
 
-        entries = [ComputedStructureEntry.from_dict(entry) for entry in entries]
+        entries = [ComputedStructureEntry.from_dict(entry) for entry in item]
         # determine chemsys
         elements = sorted(
             set([el.symbol for e in entries for el in e.composition.elements])
@@ -229,9 +222,7 @@ def get_entries(self, chemsys: str) -> List[Dict]:
         new_q["chemsys"] = {"$in": list(query_chemsys)}
         new_q["deprecated"] = False
         materials_docs = list(
-            self.materials.query(
-                criteria=new_q, properties=[self.materials.key, "entries"]
-            )
+            self.materials.query(criteria=new_q, properties=["material_id", "entries"])
         )
 
         # Get Oxidation state data for each material
@@ -268,7 +259,7 @@ def get_entries(self, chemsys: str) -> List[Dict]:
     def get_updated_chemsys(
         self,
     ) -> Set:
-        """ Gets updated chemical system as defined by the updating of an existing material """
+        """Gets updated chemical system as defined by the updating of an existing material"""
 
         updated_mats = self.thermo.newer_in(self.materials, criteria=self.query)
         updated_chemsys = set(
@@ -281,7 +272,7 @@ def get_updated_chemsys(
         return updated_chemsys
 
     def get_new_chemsys(self) -> Set:
-        """ Gets newer chemical system as defined by introduction of a new material """
+        """Gets newer chemical system as defined by introduction of a new material"""
 
         # All materials that are not present in the thermo collection
         thermo_mat_ids = self.thermo.distinct(self.thermo.key)
@@ -294,7 +285,7 @@ def get_new_chemsys(self) -> Set:
         return new_mat_chemsys
 
     def get_affected_chemsys(self, chemical_systems: Set) -> Set:
-        """ Gets chemical systems affected by changes in the supplied chemical systems """
+        """Gets chemical systems affected by changes in the supplied chemical systems"""
         # First get all chemsys with any of the elements we've marked
         affected_chemsys = set()
         affected_els = list({el for c in chemical_systems for el in c.split("-")})