emmet-builders 0.78.3__py3-none-any.whl → 0.86.0__py3-none-any.whl

emmet/builders/vasp/materials.py

@@ -1,22 +1,23 @@
+from __future__ import annotations
+
 from datetime import datetime
 from itertools import chain
 from math import ceil
-from typing import Dict, Iterable, Iterator, List, Optional, Union
 
 from maggma.builders import Builder
 from maggma.stores import Store
 from maggma.utils import grouper
-from pymatgen.analysis.elasticity.strain import Deformation
-from pymatgen.core.structure import Structure
-from pymatgen.transformations.standard_transformations import (
-    DeformStructureTransformation,
-)
 
 from emmet.builders.settings import EmmetBuildSettings
-from emmet.core.utils import group_structures, jsanitize
+from emmet.core.tasks import TaskDoc
+from emmet.core.utils import group_structures, jsanitize, undeform_structure
 from emmet.core.vasp.calc_types import TaskType
 from emmet.core.vasp.material import MaterialsDoc
-from emmet.core.vasp.task_valid import TaskDocument
+
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from collections.abc import Iterable, Iterator
 
 __author__ = "Shyam Dwaraknath <shyamd@lbl.gov>"
 
@@ -43,9 +44,9 @@ class MaterialsBuilder(Builder):
         self,
         tasks: Store,
         materials: Store,
-        task_validation: Optional[Store] = None,
-        query: Optional[Dict] = None,
-        settings: Optional[EmmetBuildSettings] = None,
+        task_validation: Store | None = None,
+        query: dict | None = None,
+        settings: EmmetBuildSettings | None = None,
         **kwargs,
     ):
         """
@@ -89,7 +90,7 @@ class MaterialsBuilder(Builder):
             self.task_validation.ensure_index("task_id")
             self.task_validation.ensure_index("valid")
 
-    def prechunk(self, number_splits: int) -> Iterable[Dict]:  # pragma: no cover
+    def prechunk(self, number_splits: int) -> Iterable[dict]:  # pragma: no cover
         """Prechunk the materials builder for distributed computation"""
         temp_query = dict(self.query)
         temp_query["state"] = "successful"
@@ -119,7 +120,7 @@ class MaterialsBuilder(Builder):
         for formula_chunk in grouper(to_process_forms, N):
             yield {"query": {"formula_pretty": {"$in": list(formula_chunk)}}}
 
-    def get_items(self) -> Iterator[List[Dict]]:
+    def get_items(self) -> Iterator[list[dict]]:
         """
         Gets all items to process into materials documents.
         This does no datetime checking; relying on whether
@@ -181,7 +182,7 @@ class MaterialsBuilder(Builder):
             invalid_ids = set()
 
         projected_fields = [
-            "last_updated",
+            # "last_updated",
             "completed_at",
             "task_id",
             "formula_pretty",
@@ -191,13 +192,16 @@ class MaterialsBuilder(Builder):
             # needed for run_type and task_type
             "calcs_reversed.input.parameters",
             "calcs_reversed.input.incar",
+            "calcs_reversed.run_type",
             "orig_inputs",
             "input.structure",
             # needed for entry from task_doc
             "output.energy",
+            "calcs_reversed.output.energy",
             "input.is_hubbard",
             "input.hubbards",
-            "input.potcar_spec",
+            "calcs_reversed.input.potcar_spec",
+            "calcs_reversed.output.structure",
             # needed for transform deformation structure back for grouping
             "transformations",
             # misc info for materials doc
@@ -215,7 +219,7 @@ class MaterialsBuilder(Builder):
 
             yield tasks
 
-    def process_item(self, items: List[Dict]) -> List[Dict]:
+    def process_item(self, items: list[dict]) -> list[dict]:
         """
         Process the tasks into a list of materials
 
@@ -227,7 +231,9 @@ class MaterialsBuilder(Builder):
                 were processed
         """
 
-        tasks = [TaskDocument(**task) for task in items]
+        tasks = [
+            TaskDoc(**task) for task in items
+        ]  # [TaskDoc(**task) for task in items]
         formula = tasks[0].formula_pretty
         task_ids = [task.task_id for task in tasks]
 
@@ -239,9 +245,11 @@ class MaterialsBuilder(Builder):
         grouped_tasks = self.filter_and_group_tasks(tasks, task_transformations)
         materials = []
         for group in grouped_tasks:
+            # commercial_license == True means that the default CC-BY license is applied
+            # commercial_license == False means that a CC-BY-NC license is applied
             commercial_license = True
             for task_doc in group:
-                if set(task_doc.tags).intersection(
+                if task_doc.tags and set(task_doc.tags).intersection(
                     set(self.settings.NON_COMMERCIAL_TAGS)
                 ):
                     commercial_license = False
@@ -271,7 +279,7 @@ class MaterialsBuilder(Builder):
 
         return jsanitize([mat.model_dump() for mat in materials], allow_bson=True)
 
-    def update_targets(self, items: List[List[Dict]]):
+    def update_targets(self, items: list[list[dict]]):
         """
         Inserts the new task_types into the task_types collection
 
@@ -295,8 +303,8 @@ class MaterialsBuilder(Builder):
             self.logger.info("No items to update")
 
     def filter_and_group_tasks(
-        self, tasks: List[TaskDocument], task_transformations: List[Union[Dict, None]]
-    ) -> Iterator[List[TaskDocument]]:
+        self, tasks: list[TaskDoc], task_transformations: list[dict | None]
+    ) -> Iterator[list[TaskDoc]]:
         """
         Groups tasks by structure matching
         """
@@ -318,18 +326,25 @@ class MaterialsBuilder(Builder):
             if task.task_type == TaskType.Deformation:
                 if (
                     transformations is None
+                    or not task.input
+                    or not task.input.structure
                 ):  # Do not include deformed tasks without transformation information
                     self.logger.debug(
-                        "Cannot find transformation for deformation task {}. Excluding task.".format(
-                            task.task_id
-                        )
+                        "Cannot find transformation or original structure "
+                        f"for deformation task {task.task_id}. Excluding task."
                     )
                     continue
                 else:
                     s = undeform_structure(task.input.structure, transformations)
 
+            elif task.output and task.output.structure:
+                s = task.output.structure  # type: ignore[assignment]
             else:
-                s = task.output.structure
+                self.logger.debug(
+                    f"Skipping task {task.task_id}, missing output structure."
+                )
+                continue
+
             s.index: int = idx  # type: ignore
             structures.append(s)
 
@@ -343,29 +358,3 @@ class MaterialsBuilder(Builder):
         for group in grouped_structures:
             grouped_tasks = [filtered_tasks[struct.index] for struct in group]  # type: ignore
             yield grouped_tasks
-
-
-def undeform_structure(structure: Structure, transformations: Dict) -> Structure:
-    """
-    Get the undeformed structure by applying the transformations in a reverse order.
-
-    Args:
-        structure: deformed structure
-        transformation: transformation that deforms the structure
-
-    Returns:
-        undeformed structure
-    """
-
-    for transformation in reversed(transformations.get("history", [])):
-        if transformation["@class"] == "DeformStructureTransformation":
-            deform = Deformation(transformation["deformation"])
-            dst = DeformStructureTransformation(deform.inv)
-            structure = dst.apply_transformation(structure)
-        else:
-            raise RuntimeError(
-                "Expect transformation to be `DeformStructureTransformation`; "
-                f"got {transformation['@class']}"
-            )
-
-    return structure

emmet/builders/vasp/task_validator.py

@@ -1,13 +1,12 @@
-from typing import Dict, Optional
-from collections import defaultdict
-
 from maggma.builders import MapBuilder
 from maggma.core import Store
 
 from emmet.builders.settings import EmmetBuildSettings
-from emmet.core.vasp.task_valid import TaskDocument
+from emmet.builders.utils import get_potcar_stats
+from emmet.core.tasks import TaskDoc
+from emmet.core.types.enums import DeprecationMessage
 from emmet.core.vasp.calc_types.enums import CalcType
-from emmet.core.vasp.validation import DeprecationMessage, ValidationDoc
+from emmet.core.vasp.validation_legacy import ValidationDoc
 
 
 class TaskValidator(MapBuilder):
@@ -15,9 +14,9 @@ class TaskValidator(MapBuilder):
         self,
         tasks: Store,
         task_validation: Store,
-        potcar_hashes: Optional[Dict[CalcType, Dict[str, str]]] = None,
-        settings: Optional[EmmetBuildSettings] = None,
-        query: Optional[Dict] = None,
+        potcar_stats: dict[CalcType, dict[str, str]] | None = None,
+        settings: EmmetBuildSettings | None = None,
+        query: dict | None = None,
         **kwargs,
     ):
         """
@@ -26,7 +25,7 @@ class TaskValidator(MapBuilder):
         Args:
             tasks: Store of task documents
             task_validation: Store of task_types for tasks
-            potcar_hashes: Optional dictionary of potcar hash data.
+            potcar_stats: Optional dictionary of potcar hash data.
                 Mapping is calculation type -> potcar symbol -> hash value.
         """
         self.tasks = tasks
@@ -34,29 +33,14 @@ class TaskValidator(MapBuilder):
         self.settings = EmmetBuildSettings.autoload(settings)
         self.query = query
         self.kwargs = kwargs
-        self.potcar_hashes = potcar_hashes
+        self.potcar_stats = potcar_stats
 
         # Set up potcar cache if appropriate
-        if self.settings.VASP_VALIDATE_POTCAR_HASHES:
-            if not self.potcar_hashes:
-                from pymatgen.io.vasp.inputs import PotcarSingle
-
-                hashes = defaultdict(dict)  # type: dict
-
-                for (
-                    calc_type,
-                    input_set,
-                ) in self.settings.VASP_DEFAULT_INPUT_SETS.items():
-                    functional = input_set.CONFIG["POTCAR_FUNCTIONAL"]
-                    for potcar_symbol in input_set.CONFIG["POTCAR"].values():
-                        potcar = PotcarSingle.from_symbol_and_functional(
-                            symbol=potcar_symbol, functional=functional
-                        )
-                        hashes[calc_type][potcar_symbol] = potcar._summary_stats
-
-                self.potcar_hashes = potcar_hashes
+        if self.settings.VASP_VALIDATE_POTCAR_STATS:
+            if not self.potcar_stats:
+                self.potcar_stats = get_potcar_stats(method="stored")
         else:
-            self.potcar_hashes = None
+            self.potcar_stats = None
 
         super().__init__(
             source=tasks,
@@ -80,7 +64,7 @@ class TaskValidator(MapBuilder):
         Args:
             item (dict): a (projection of a) task doc
         """
-        task_doc = TaskDocument(**item)
+        task_doc = TaskDoc(**item)
         validation_doc = ValidationDoc.from_task_doc(
             task_doc=task_doc,
             kpts_tolerance=self.settings.VASP_KPTS_TOLERANCE,
@@ -88,13 +72,18 @@ class TaskValidator(MapBuilder):
             input_sets=self.settings.VASP_DEFAULT_INPUT_SETS,
             LDAU_fields=self.settings.VASP_CHECKED_LDAU_FIELDS,
             max_allowed_scf_gradient=self.settings.VASP_MAX_SCF_GRADIENT,
-            potcar_hashes=self.potcar_hashes,
+            potcar_stats=self.potcar_stats,
         )
 
-        bad_tags = list(set(task_doc.tags).intersection(self.settings.DEPRECATED_TAGS))
-        if len(bad_tags) > 0:
-            validation_doc.warnings.append(f"Manual Deprecation by tags: {bad_tags}")
-            validation_doc.valid = False
-            validation_doc.reasons.append(DeprecationMessage.MANUAL)
+        if task_doc.tags:
+            bad_tags = list(
+                set(task_doc.tags).intersection(self.settings.DEPRECATED_TAGS)
+            )
+            if len(bad_tags) > 0:
+                validation_doc.warnings.append(
+                    f"Manual Deprecation by tags: {bad_tags}"
+                )
+                validation_doc.valid = False
+                validation_doc.reasons.append(DeprecationMessage.MANUAL)
 
         return validation_doc

emmet_builders-0.86.0.dist-info/METADATA

@@ -0,0 +1,37 @@
+Metadata-Version: 2.4
+Name: emmet-builders
+Version: 0.86.0
+Summary: Builders for the Emmet Library
+Author-email: The Materials Project <feedback@materialsproject.org>
+License: Modified BSD
+Project-URL: Homepage, https://github.com/materialsproject/emmet/tree/main/emmet-builders/
+Project-URL: Documentation, https://materialsproject.github.io/emmet/
+Requires-Python: >=3.11
+Requires-Dist: emmet-core[all]>=0.85
+Requires-Dist: maggma>=0.57.6
+Requires-Dist: matminer>=0.9.1
+Requires-Dist: pymatgen-io-validation>=0.1.1
+Provides-Extra: test
+Requires-Dist: pre-commit; extra == "test"
+Requires-Dist: pytest; extra == "test"
+Requires-Dist: pytest-cov; extra == "test"
+Requires-Dist: pytest-xdist; extra == "test"
+Requires-Dist: pycodestyle; extra == "test"
+Requires-Dist: pydocstyle; extra == "test"
+Requires-Dist: flake8; extra == "test"
+Requires-Dist: mypy; extra == "test"
+Requires-Dist: mypy-extensions; extra == "test"
+Requires-Dist: types-setuptools; extra == "test"
+Requires-Dist: types-requests; extra == "test"
+Requires-Dist: wincertstore; extra == "test"
+Provides-Extra: docs
+Requires-Dist: mkdocs; extra == "docs"
+Requires-Dist: mkdocs-material<8.3; extra == "docs"
+Requires-Dist: mkdocs-material-extensions; extra == "docs"
+Requires-Dist: mkdocs-minify-plugin; extra == "docs"
+Requires-Dist: mkdocstrings; extra == "docs"
+Requires-Dist: mkdocs-awesome-pages-plugin; extra == "docs"
+Requires-Dist: mkdocs-markdownextradata-plugin; extra == "docs"
+Requires-Dist: mkdocstrings[python]; extra == "docs"
+Requires-Dist: livereload; extra == "docs"
+Requires-Dist: jinja2; extra == "docs"

emmet_builders-0.86.0.dist-info/RECORD

@@ -0,0 +1,41 @@
+emmet/builders/__init__.py,sha256=y-ZREtieuFK3MaYvCBDMPf3YLxnsZG1VNho9lMjnRDU,221
+emmet/builders/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+emmet/builders/settings.py,sha256=ZNIUKYdwT9Am5Gb-r5tkCTr-R2nysKh4Q_6-PChKZo4,3036
+emmet/builders/utils.py,sha256=8x6wJgcV-DFGhDZzeYwpRXgz8PeZLLr_Q2wnIvBqlvA,10946
+emmet/builders/abinit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+emmet/builders/abinit/phonon.py,sha256=A8-bxMq3sTEiZ0dH4P9Gjb5pvOx040pSfhW4pGyTO1U,32034
+emmet/builders/abinit/sound_velocity.py,sha256=D-GFiFtm0DUwvsl31W4GHNFHeZYM4ditZY8hOwcnj9A,7091
+emmet/builders/feff/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+emmet/builders/feff/xas.py,sha256=wQnO0IcxAclYY4fVoyc4sDqs1Cx7vFzMq-_oIHnk3EU,2068
+emmet/builders/materials/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+emmet/builders/materials/absorption_spectrum.py,sha256=_uQSF8KX8BIHqiW_7oOMtur7uKkzf704H88bXHxJSCs,6892
+emmet/builders/materials/alloys.py,sha256=oAlS4TRt181Z_Cc3jfyrFXwqqRbEfthuv2GxcvKUzzI,14199
+emmet/builders/materials/basic_descriptors.py,sha256=IVCkN0vjkoNis2d_OUezVhPzGpaVcP6IkX123UwB6oQ,5845
+emmet/builders/materials/bonds.py,sha256=TFfkfKG1-7zcim9gPJqRz1UcyVN_px0889VWhSICc5g,1847
+emmet/builders/materials/chemenv.py,sha256=ZTR6_VyAif3yvcSy8xagBkmKczZsDD3LC77RMKi4E0U,1191
+emmet/builders/materials/corrected_entries.py,sha256=nlA7qSXdQM7_fe8WiPJ_dN971OFeMonkZqc7rlL6jIE,12480
+emmet/builders/materials/dielectric.py,sha256=-KVqY6l4qBcj_BaQf6hd9VsGlbC_Y9wEH_z2VfUNz2s,6692
+emmet/builders/materials/elasticity.py,sha256=2sNJAOTFEkIsyReQPGdzbIXt23PSsq_5dCv9RBeWpI4,16571
+emmet/builders/materials/electrodes.py,sha256=VESA_xY8BJiocPanRfta0hUyi0SBAOIlsZ0dEKty5tE,23855
+emmet/builders/materials/electronic_structure.py,sha256=YJiayaEUd5Hnfj4tKJpw1HpjAwCckf7S3O1et25Fbvs,29457
+emmet/builders/materials/magnetism.py,sha256=JxEWUzgrpI3fXoR9dIhT_iU8iW5O3bGIquDevlAvnjw,4738
+emmet/builders/materials/optimade.py,sha256=TYzw-xLaNeNa2h0Fa5Ft3Iqg0LMEHj1_-MbfMmfDdpk,5211
+emmet/builders/materials/oxidation_states.py,sha256=ptTfakXk1bjexniBzx87XCutiuRiolFpnMZETsJlj6I,1670
+emmet/builders/materials/piezoelectric.py,sha256=XPjl3iPwS9VFqmxu3mT34S1CHUEli3Samu4B2vH7Baw,7857
+emmet/builders/materials/provenance.py,sha256=HbjP7TW6GVIp86vylu4PiInem0oE9hWFKh0DRx_eIzs,9116
+emmet/builders/materials/robocrys.py,sha256=6nVAgqsk2T9VdibCR2eZeVosqwJ2lEt_Yr_4hzotEIA,1257
+emmet/builders/materials/similarity.py,sha256=SIqdmPgs3f7oUQCeu0IBh26y_evYWc0EOEvbIALl-0s,5414
+emmet/builders/materials/substrates.py,sha256=cdHNYabSvsdONWUP4alU73PpMzHc4DYLuEdUpIZETds,6132
+emmet/builders/materials/summary.py,sha256=ZIR2rV1WeGvU0B_wz9W_VX1KXhs104fDwSxsVMstlQk,8030
+emmet/builders/materials/thermo.py,sha256=oOH-8IEyUxNckXniFCe_-En2rTG2bNybudqdrf9ztL4,10988
+emmet/builders/matscholar/missing_compositions.py,sha256=6prFb3mmvr_y12XIzZ8w8SiHLEone1B6Hxyq6cTusSE,8704
+emmet/builders/mobility/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+emmet/builders/mobility/migration_graph.py,sha256=BxVh3homd9GEniB33_dJ1e2wmRvMnievHHPRs6fnbBw,3899
+emmet/builders/vasp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+emmet/builders/vasp/materials.py,sha256=pcSUF78RBaKL3FdyDB6QSjrL0apUi3PT0A8Sj6Bc5Ks,13302
+emmet/builders/vasp/mp_potcar_stats.json.gz,sha256=x3bn4gSMj1U_3bR2qKIaBtbJlYT-EJgoUIMFTA9bvaU,338957
+emmet/builders/vasp/task_validator.py,sha256=LCj-LBuNzt2vJQ8G6WJvBtiM7_Kxrh3Uhvq97viVoIA,3033
+emmet_builders-0.86.0.dist-info/METADATA,sha256=IANQcvHHJADuzqjBesW9So2XWUIQNQZE0FuaDPui554,1588
+emmet_builders-0.86.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+emmet_builders-0.86.0.dist-info/top_level.txt,sha256=6GcpbmWPeFhNCTfDFilb8GQ4T1UQu4z9c5jpobjwE-Q,6
+emmet_builders-0.86.0.dist-info/RECORD,,

{emmet_builders-0.78.3.dist-info → emmet_builders-0.86.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.42.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

emmet/builders/materials/ml.py

@@ -1,87 +0,0 @@
-from importlib.metadata import version
-from typing import TYPE_CHECKING, Optional, Union
-
-from maggma.builders.map_builder import MapBuilder
-from maggma.core import Store
-from matcalc.utils import get_universal_calculator
-from pymatgen.core import Structure
-
-from emmet.core.ml import MLDoc
-from emmet.core.utils import jsanitize
-
-if TYPE_CHECKING:
-    from ase.calculators.calculator import Calculator
-
-
-class MLBuilder(MapBuilder):
-    def __init__(
-        self,
-        materials: Store,
-        ml_potential: Store,
-        model: Union[str, "Calculator"],
-        model_kwargs: Optional[dict] = None,
-        prop_kwargs: Optional[dict] = None,
-        provenance: Optional[dict] = None,
-        **kwargs,
-    ):
-        """Machine learning interatomic potential builder.
-
-        Args:
-            materials (Store): Materials to use as input structures.
-            ml_potential (Store): Where to save MLDoc documents to.
-            model (str | Calculator): ASE calculator or name of model to use as ML
-                potential. See matcalc.utils.UNIVERSAL_CALCULATORS for recognized names.
-            model_kwargs (dict, optional): Additional kwargs to pass to the calculator.
-                Defaults to None.
-            prop_kwargs (dict[str, dict], optional): Separate kwargs passed to each matcalc
-                PropCalc class. Recognized keys are RelaxCalc, ElasticityCalc, PhononCalc, EOSCalc.
-                Defaults to None.
-            provenance (dict, optional): Additional provenance information to include in
-                MLDocs. Will be saved in each document so use sparingly. Defaults to None.
-                Set to {} to disable default provenance model, version, matcalc_version.
-        """
-        self.materials = materials
-        self.ml_potential = ml_potential
-        self.kwargs = kwargs
-        self.model = get_universal_calculator(model, **(model_kwargs or {}))
-        self.prop_kwargs = prop_kwargs or {}
-
-        if provenance == {}:
-            self.provenance = {}
-        else:
-            model_name = (
-                model if isinstance(model, str) else type(model).__name__
-            ).lower()
-            model_name = {"chgnetcalculator": "chgnet"}.get(model_name, model_name)
-            pkg_name = {"m3gnet": "matgl"}.get(model_name, model_name)
-            self.provenance = dict(
-                model=model_name,
-                version=version(pkg_name),
-                matcalc_version=version("matcalc"),
-                **(provenance or {}),
-            )
-
-        # Enforce that we key on material_id
-        self.materials.key = "material_id"
-        self.ml_potential.key = "material_id"
-        super().__init__(
-            source=materials,
-            target=ml_potential,
-            projection=["structure", "deprecated"],
-            **kwargs,
-        )
-
-    def unary_function(self, item):
-        struct = Structure.from_dict(item["structure"])
-        mp_id, deprecated = item["material_id"], item["deprecated"]
-
-        doc = MLDoc(
-            structure=struct,
-            material_id=mp_id,
-            calculator=self.model,
-            prop_kwargs=self.prop_kwargs,
-            deprecated=deprecated,
-            **self.provenance,
-        )
-
-        return jsanitize(doc, allow_bson=True)