Housekeeping: Update package versions / lint workflow (#533)

* Add a linting workflow

* Partial mypy fixes

* Bumping versions of packages dependencies to keep in sync with emmet-core

Author: esoteric-ephemera

.github/workflows/lint.yaml

@@ -0,0 +1,26 @@
+name: Linting
+
+on: [push]
+
+permissions:
+  contents: read
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+          cache: pip
+
+      - name: Install dependencies
+        run: |
+          pip install pre-commit
+
+      - name: Run pre-commit
+        run: |
+          pre-commit run --all-files --show-diff-on-failure

.github/workflows/tests.yml

@@ -13,14 +13,18 @@ jobs:
         uses: conda-incubator/setup-miniconda@v3
         with:
           python-version: "3.10"
+          auto-update-conda: true
+          channels: anaconda, conda-forge
 
       - name: Install dependencies
+        shell: bash -l {0}
         run: |
           conda install --quiet --yes -c conda-forge openbabel pip ruamel.yaml
           pip install -r requirements.txt
           pip install -e .[tests,cli]
 
       - name: Test
+        shell: bash -l {0}
         run: pytest --cov=robocrys --cov-report=xml --cov-config=.coveragerc tests/
 
   docs:

.pre-commit-config.yaml

@@ -1,8 +1,5 @@
 exclude: ^(docs|tests|dev_scripts|.github)
 
-default_language_version:
-  python: python3.11
-
 ci:
   autoupdate_schedule: yearly
   skip: [flake8, autoflake, mypy]

requirements.txt

@@ -1,10 +1,10 @@
-spglib==2.5.0
+spglib==2.6.0
 numpy==1.26.4
-scipy==1.14.1
-pymatgen==2024.4.13
-inflect==7.4.0
-networkx==3.3
-matminer==0.9.2
-monty==2024.7.30
+scipy==1.15.2
+pymatgen==2025.3.10
+inflect==7.5.0
+networkx==3.4.2
+matminer==0.9.3
+monty==2025.3.3
 pubchempy==1.0.4
 pybtex==0.24.0

robocrys/cli.py

@@ -9,7 +9,7 @@
 from pymatgen.core.structure import Structure
 
 try:
-    from mp_api.client import MPRestError
+    from mp_api.client import MPRestError  # type:ignore[import-untyped]
 except ImportError:
     MPRestError = None
 

robocrys/condense/fingerprint.py

@@ -3,8 +3,12 @@
 from collections.abc import Iterable
 
 import numpy as np
-from matminer.featurizers.site import CrystalNNFingerprint
-from matminer.featurizers.structure import SiteStatsFingerprint
+from matminer.featurizers.site import (
+    CrystalNNFingerprint,
+)  # type:ignore[import-untyped]
+from matminer.featurizers.structure import (
+    SiteStatsFingerprint,
+)  # type:ignore[import-untyped]
 from pymatgen.core.structure import IStructure
 
 
@@ -42,7 +46,7 @@ def get_site_fingerprints(
 
     if as_dict:
         labels = ssf.feature_labels()
-        site_fingerprints = [dict(zip(labels, x)) for x in site_fingerprints]
+        return [dict(zip(labels, x)) for x in site_fingerprints]
 
     return site_fingerprints
 
@@ -107,13 +111,13 @@ def get_fingerprint_distance(
         The euclidean distance between fingerprints as a :class:`numpy.ndarray`.
     """
     if issubclass(type(structure_a), IStructure):
-        fingerprint_a = get_structure_fingerprint(structure_a)
+        fingerprint_a = get_structure_fingerprint(structure_a)  # type: ignore[arg-type]
     else:
         fingerprint_a = np.array(structure_a)
 
     if issubclass(type(structure_b), IStructure):
-        fingerprint_b = get_structure_fingerprint(structure_b)
+        fingerprint_b = get_structure_fingerprint(structure_b)  # type: ignore[arg-type]
     else:
         fingerprint_b = np.array(structure_b)
 
-    return np.linalg.norm(fingerprint_a - fingerprint_b)
+    return np.linalg.norm(fingerprint_a - fingerprint_b)  # type: ignore[return-value]

robocrys/condense/mineral.py

@@ -5,22 +5,25 @@
 from importlib.resources import files as import_resource_file
 from itertools import islice
 from pathlib import Path
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING
 
 import numpy as np
-from matminer.utils.io import load_dataframe_from_json
+from matminer.utils.io import load_dataframe_from_json  # type:ignore[import-untyped]
 from pymatgen.analysis.prototypes import AflowPrototypeMatcher
-from pymatgen.core.structure import IStructure
 from robocrys.condense.fingerprint import (
     get_fingerprint_distance,
     get_structure_fingerprint,
 )
 
 
 if TYPE_CHECKING:
+    from typing import Any
     import pandas as pd
 
-_mineral_db_file = import_resource_file("robocrys.condense") / "mineral_db.json.gz"
+    from pymatgen.core.structure import Structure
+
+
+_mineral_db_file = str(import_resource_file("robocrys.condense") / "mineral_db.json.gz")
 
 
 class MineralMatcher:
@@ -60,9 +63,11 @@ def __init__(
         fingerprint_distance_cutoff: float = 0.4,
         mineral_db: str | Path | pd.DataFrame | None = None,
     ):
-        self.mineral_db = mineral_db if mineral_db is not None else _mineral_db_file
-        if isinstance(self.mineral_db, (str, Path)):
-            self.mineral_db = load_dataframe_from_json(self.mineral_db, pbar=False)
+        mineral_db = mineral_db or _mineral_db_file
+        if isinstance(mineral_db, (str, Path)):
+            self.mineral_db = load_dataframe_from_json(mineral_db, pbar=False)
+        else:
+            self.mineral_db = mineral_db
 
         self.initial_ltol = initial_ltol
         self.initial_stol = initial_stol
@@ -72,7 +77,7 @@ def __init__(
         self._structure = None
         self._mineral_db = None
 
-    def get_best_mineral_name(self, structure: IStructure) -> dict[str, Any]:
+    def get_best_mineral_name(self, structure: Structure) -> dict[str, Any]:
         """Gets the "best" mineral name for a structure.
 
         Uses a combination of AFLOW prototype matching and fingerprinting to
@@ -138,7 +143,7 @@ def get_best_mineral_name(self, structure: IStructure) -> dict[str, Any]:
 
     def get_aflow_matches(
         self,
-        structure: IStructure,
+        structure: Structure,
     ) -> list[dict[str, Any]] | None:
         """Gets minerals for a structure by matching to AFLOW prototypes.
 
@@ -190,7 +195,7 @@ def _match_prototype(structure_matcher, s):
 
     def get_fingerprint_matches(
         self,
-        structure: IStructure,
+        structure: Structure,
         max_n_matches: int | None = None,
         match_n_sp: bool = True,
         mineral_name_constraint: str | None = None,
@@ -240,7 +245,7 @@ def get_fingerprint_matches(
 
         return minerals if minerals else None
 
-    def _set_distance_matrix(self, structure: IStructure):
+    def _set_distance_matrix(self, structure: Structure):
         """Utility func to calculate distance between structure and minerals.
 
         First checks to see if the distances have already been calculated for

robocrys/condense/molecule.py

@@ -9,7 +9,7 @@
 
 from monty.serialization import loadfn
 from importlib.resources import files as import_resource_file
-from pubchempy import BadRequestError, get_compounds
+from pubchempy import BadRequestError, get_compounds  # type:ignore[import-untyped]
 from pymatgen.analysis.graphs import MoleculeGraph
 from pymatgen.io.babel import BabelMolAdaptor
 
@@ -20,7 +20,7 @@ class MoleculeNamer:
     def __init__(
         self,
         use_online_pubchem: bool = True,
-        name_preference: tuple[str] = name_sources,
+        name_preference: tuple[str, ...] = name_sources,
     ):
         """Class to match molecule graphs to known molecule names.
 
@@ -36,8 +36,8 @@ def __init__(
                 to last.
         """
         db_file = import_resource_file("robocrys.condense") / "molecule_db.json.gz"
-        self.molecule_db = loadfn(db_file)
-        self.matched_molecules = {}
+        self.molecule_db: dict[str, dict[str, str]] = loadfn(str(db_file))
+        self.matched_molecules: dict[str, str] = {}
         self.use_online_pubchem = use_online_pubchem
 
         # append the sources list to the end in case the user only supplies
@@ -122,7 +122,7 @@ def molecule_graph_to_smiles(molecule_graph: MoleculeGraph) -> str | None:
         try:
             bma = BabelMolAdaptor.from_molecule_graph(molecule_graph)
             pbmol = bma.pybel_mol
-            return pbmol.write("smi").split()[0]
+            return pbmol.write("smi").split()[0]  # type: ignore[attr-defined]
         except RuntimeError:
             warnings.warn(
                 "Molecule naming requires openbabel to be installed "

robocrys/describe/adapter.py

@@ -5,13 +5,16 @@
 from __future__ import annotations
 
 from collections import defaultdict, namedtuple
-from typing import Any
+from typing import TYPE_CHECKING
 
 import numpy as np
 from pymatgen.core.periodic_table import get_el_sp
 
 from robocrys.adapter import BaseAdapter
 
+if TYPE_CHECKING:
+    from typing import Any
+
 ComponentDetails = namedtuple(
     "ComponentDetails",
     [
@@ -178,7 +181,7 @@ def get_next_nearest_neighbor_details(
             geometry = self.sites[nnn_site]["geometry"]["type"]
 
             if group:
-                identity = (element, connectivity, geometry)
+                identity: tuple[Any, ...] = (element, connectivity, geometry)
             else:
                 identity = (element, connectivity, geometry, labels)
 

robocrys/describe/describer.py

@@ -198,9 +198,7 @@ def get_component_makeup_summary(self) -> str:
             if self._da.dimensionality == 3:
                 desc = "The structure consists of "
             else:
-                desc = "The structure is {}-dimensional and consists of ".format(
-                    en.number_to_words(self._da.dimensionality)
-                )
+                desc = f"The structure is {en.number_to_words(self._da.dimensionality)}-dimensional and consists of "
 
             component_makeup_summaries = []
             nframeworks = len(