[BE] Single ruff config (#751)

* ruff toml

* ruff fix

* fix and format

* update ruff

* remove ruff config in pyproject

* lint workflow use ruff.toml

* unpin ruff

* fix circular imports

* clean up imports

* revert to 3.9 annotations, dataclasses_json does not work with __future__ annotations

* pin ruff

.github/workflows/lint.yml

@@ -25,7 +25,4 @@ jobs:
       - name: ruff
         run: |
           ruff --version
-          ruff check --statistics --config packages/fairchem-core/pyproject.toml src/fairchem/core/
-          ruff check --statistics --config packages/fairchem-data-oc/pyproject.toml src/fairchem/data/oc/
-          #ruff check --statistics --config packages/fairchem-data-om/pyproject.toml src/fairchem/data/om/
-          #ruff check --statistics --config packages/fairchem-demo-ocpapi/pyproject.toml src/fairchem/demo/ocpapi/
+          ruff check src

.pre-commit-config.yaml

@@ -5,13 +5,13 @@ ci:
 
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.4.4
+  rev: v0.5.1
   hooks:
     - id: ruff
       args: [ --fix ]
     - id: ruff-format
 - repo: https://github.com/adamchainz/blacken-docs
-  rev: 1.16.0
+  rev: 1.18.0
   hooks:
     - id: blacken-docs
 - repo: https://github.com/pre-commit/pre-commit-hooks

packages/fairchem-core/pyproject.toml

@@ -26,7 +26,7 @@ dependencies = [
 ]
 
 [project.optional-dependencies]  # add optional dependencies to be installed as pip install fairchem.core[dev]
-dev = ["pre-commit", "pytest", "pytest-cov", "coverage", "syrupy", "ruff==0.4.10"]
+dev = ["pre-commit", "pytest", "pytest-cov", "coverage", "syrupy", "ruff==0.5.1"]
 docs = ["jupyter-book", "jupytext", "sphinx","sphinx-autoapi", "umap-learn", "vdict"]
 adsorbml = ["dscribe","x3dase","scikit-image"]
 
@@ -74,73 +74,3 @@ testpaths = ["tests"]
 
 [tool.coverage.run]
 source = ["fairchem.core"]
-
-[tool.ruff]
-line-length = 88
-lint.select = [
-  "B",      # flake8-bugbear
-  "C4",     # flake8-comprehensions
-  "E",      # pycodestyle error
-  "EXE",    # flake8-executable
-  "F",      # pyflakes
-  "FA",     # flake8-future-annotations
-  "FBT003", # boolean-positional-value-in-call
-  "FLY",    # flynt
-  "I",      # isort
-  "ICN",    # flake8-import-conventions
-  "PD",     # pandas-vet
-  "PERF",   # perflint
-  "PIE",    # flake8-pie
-  "PL",     # pylint
-  "PT",     # flake8-pytest-style
-  "PYI",    # flakes8-pyi
-  "Q",      # flake8-quotes
-  "RET",    # flake8-return
-  "RSE",    # flake8-raise
-  "RUF",    # Ruff-specific rules
-  "SIM",    # flake8-simplify
-  "SLOT",   # flake8-slots
-  "TCH",    # flake8-type-checking
-  "TID",    # tidy imports
-  "TID",    # flake8-tidy-imports
-  "UP",     # pyupgrade
-  "W",      # pycodestyle warning
-  "YTT",    # flake8-2020
-]
-lint.ignore = [
-  "PLR",    # Design related pylint codes
-  "E501",   # Line too long
-  "B028",   # No explicit stacklevel
-  "EM101",  # Exception must not use a string literal
-  "EM102",  # Exception must not use an f-string literal
-  "G004",   # f-string in Logging statement
-  "RUF015", # Prefer next(iter())
-  "RET505", # Unnecessary `elif` after `return`
-  "PT004",  # Fixture does not return anthing
-  "B017",   # pytest.raises
-  "PT011",  # pytest.raises
-  "PT012",  # pytest.raises"
-  "E741",  # ambigous variable naming, i.e. one letter
-  "FBT003",  # boolean positional variable in function call
-  "PERF203",  # `try`-`except` within a loop incurs performance overhead (no overhead in Py 3.11+)
-  "EXE002",  # The file is executable but no shebang is present (not sure why some files come up as this)
-]
-
-lint.typing-modules = ["mypackage._compat.typing"]
-src = ["src"]
-lint.unfixable = [
-  "T20",  # Removes print statements
-  "F841", # Removes unused variables
-]
-lint.pydocstyle.convention = "google"
-lint.isort.known-first-party = ["fairchem.core"]
-lint.isort.required-imports = ["from __future__ import annotations"]
-
-[tool.ruff.lint.per-file-ignores]
-# Ignore `E402` (import violations) in all `__init__.py` files, and in `path/to/file.py`.
-"src/fairchem/core/__init__.py" = ["I002"]
-"src/fairchem/core/conf.py" = ["I002"]
-"src/fairchem/core/common/*" = ["PLW0603"]  # Using the global statement to update [] is discouraged
-"src/fairchem/core/scripts/*" = ["PLW0603"]  # Using the global statement to update [] is discouraged
-"src/fairchem/core/models/*" = ["PERF401"]  # Use a list comprehension to create a transformed list
-"src/fairchem/core/models/gemnet*" = ["B023"]  # Function definition does not bind loop variable `first_sph`

packages/fairchem-data-oc/pyproject.toml

@@ -42,8 +42,3 @@ content-type = "text/markdown"
 fragments = [
   { path = "src/fairchem/data/oc/README.md" }
 ]
-
-[tool.ruff.lint.per-file-ignores]
-# Ignore `E402` (import violations) in all `__init__.py` files, and in `path/to/file.py`.
-"src/fairchem/data/oc/core/__init__.py" = ["F401"]
-"src/fairchem/data/oc/utils/__init__.py" = ["F401"]

ruff.toml

@@ -0,0 +1,76 @@
+include = ["src/fairchem/core/**/*.py", "src/fairchem/data/oc/**/*.py"]
+line-length = 88
+
+[lint]
+select = [
+  "B",      # flake8-bugbear
+  "C4",     # flake8-comprehensions
+  "E",      # pycodestyle error
+  "EXE",    # flake8-executable
+  "F",      # pyflakes
+  "FA",     # flake8-future-annotations
+  "FBT003", # boolean-positional-value-in-call
+  "FLY",    # flynt
+  "I",      # isort
+  "ICN",    # flake8-import-conventions
+  "PD",     # pandas-vet
+  "PERF",   # perflint
+  "PIE",    # flake8-pie
+  "PL",     # pylint
+  "PT",     # flake8-pytest-style
+  "PYI",    # flakes8-pyi
+  "Q",      # flake8-quotes
+  "RET",    # flake8-return
+  "RSE",    # flake8-raise
+  "RUF",    # Ruff-specific rules
+  "SIM",    # flake8-simplify
+  "SLOT",   # flake8-slots
+  "TCH",    # flake8-type-checking
+  "TID",    # tidy imports
+  "TID",    # flake8-tidy-imports
+  "UP",     # pyupgrade
+  "W",      # pycodestyle warning
+  "YTT",    # flake8-2020
+]
+ignore = [
+  "PLR",    # Design related pylint codes
+  "E501",   # Line too long
+  "B028",   # No explicit stacklevel
+  "EM101",  # Exception must not use a string literal
+  "EM102",  # Exception must not use an f-string literal
+  "G004",   # f-string in Logging statement
+  "RUF015", # Prefer next(iter())
+  "RET505", # Unnecessary `elif` after `return`
+  "PT004",  # Fixture does not return anthing
+  "B017",   # pytest.raises
+  "PT011",  # pytest.raises
+  "PT012",  # pytest.raises"
+  "E741",  # ambigous variable naming, i.e. one letter
+  "FBT003",  # boolean positional variable in function call
+  "PERF203",  # `try`-`except` within a loop incurs performance overhead (no overhead in Py 3.11+)
+  "EXE002",  # The file is executable but no shebang is present (not sure why some files come up as this)
+  "PLC2401", # non ASCII characters
+]
+unfixable = [
+  "T20",  # Removes print statements
+  "F841", # Removes unused variables
+]
+
+[lint.isort]
+known-first-party = ["fairchem.core"]
+required-imports = ["from __future__ import annotations"]
+
+[lint.pydocstyle]
+convention = "google"
+
+[lint.per-file-ignores]
+# Ignore `E402` (import violations) in all `__init__.py` files, and in `path/to/file.py`.
+"src/fairchem/core/__init__.py" = ["I002"]
+"src/fairchem/core/conf.py" = ["I002"]
+"src/fairchem/core/common/*" = ["PLW0603"]  # Using the global statement to update [] is discouraged
+"src/fairchem/core/scripts/*" = ["PLW0603"]  # Using the global statement to update [] is discouraged
+"src/fairchem/core/models/*" = ["PERF401"]  # Use a list comprehension to create a transformed list
+"src/fairchem/core/models/gemnet*" = ["B023"]  # Function definition does not bind loop variable `first_sph`
+# Ignore `E402` (import violations) in all `__init__.py` files, and in `path/to/file.py`.
+"src/fairchem/data/oc/core/__init__.py" = ["F401"]
+"src/fairchem/data/oc/utils/__init__.py" = ["F401"]

src/fairchem/applications/AdsorbML/adsorbml/2023_neurips_challenge/challenge_eval.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import argparse
 import pickle
 from collections import defaultdict
@@ -19,9 +21,7 @@ def is_successful(best_pred_energy, best_dft_energy, SUCCESS_THRESHOLD=0.1):
     # Given best ML and DFT energy, compute various success metrics:
     # success_parity: base success metric (ML - DFT <= SUCCESS_THRESHOLD)
     diff = best_pred_energy - best_dft_energy
-    success_parity = diff <= SUCCESS_THRESHOLD
-
-    return success_parity
+    return diff <= SUCCESS_THRESHOLD
 
 
 def compute_valid_ml_success(ml_data, dft_data):

src/fairchem/applications/AdsorbML/adsorbml/scripts/dense_eval.py

@@ -67,6 +67,8 @@
     }
 """
 
+from __future__ import annotations
+
 import argparse
 import pickle
 from collections import defaultdict

src/fairchem/applications/AdsorbML/adsorbml/scripts/process_mlrs.py

@@ -15,6 +15,8 @@
 - errors_by_sid.pkl: any errors that occurred
 """
 
+from __future__ import annotations
+
 import argparse
 import multiprocessing as mp
 import os
@@ -52,8 +54,7 @@ def parse_args():
     )
     parser.add_argument("--surface-dir", type=str, help="Path to surface DFT outputs")
 
-    args = parser.parse_args()
-    return args
+    return parser.parse_args()
 
 
 def min_diff(atoms_init, atoms_final):
@@ -159,7 +160,7 @@ def process_mlrs(arg):
             continue
         anomalies[sid] = anomaly
         if not anomaly:
-            grouped_configs[system].append(tuple([adslab_idx, predE, mlrs]))
+            grouped_configs[system].append((adslab_idx, predE, mlrs))
 
     # group configs by system and sort
     sorted_grouped_configs = {}

src/fairchem/applications/AdsorbML/adsorbml/scripts/utils.py

@@ -1,7 +1,9 @@
+from __future__ import annotations
+
 import glob
 import os
 
-from pymatgen.io.vasp.outputs import *
+from pymatgen.io.vasp.outputs import Oszicar
 
 """
 This script provides utility functions that can be useful for trying to

src/fairchem/applications/AdsorbML/adsorbml/scripts/write_top_k_vasp.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import argparse
 import os
 import pickle

src/fairchem/applications/cattsunami/core/__init__.py

@@ -1,4 +1,6 @@
-from .reaction import Reaction
+from __future__ import annotations
+
 from .ocpneb import OCPNEB
+from .reaction import Reaction
 
 __all__ = ["Reaction", "OCPNEB"]

src/fairchem/applications/cattsunami/core/autoframe.py

@@ -3,18 +3,24 @@
 and final frames for NEB calculations.
 """
 
-import numpy as np
+from __future__ import annotations
+
+import copy
+from copy import deepcopy
+from itertools import combinations, product
+from typing import TYPE_CHECKING
+
 import ase
+import networkx as nx
+import numpy as np
+import torch
 from ase.data import atomic_numbers, covalent_radii
-from scipy.spatial.distance import euclidean
-from itertools import combinations, product
 from ase.optimize import BFGS
-import copy
-import torch
 from fairchem.data.oc.utils import DetectTrajAnomaly
-import networkx as nx
-from copy import deepcopy
-from fairchem.applications.cattsunami.core import Reaction
+from scipy.spatial.distance import euclidean
+
+if TYPE_CHECKING:
+    from fairchem.applications.cattsunami.core import Reaction
 
 
 class AutoFrame:
@@ -76,13 +82,11 @@ def only_keep_unique_systems(self, systems, energies):
         # Iterate over the systems and see where there are matches (systems where every adsorbate atom is overlapping)
         for idx in range(len(systems)):
             if not any(
-                [
-                    self.are_all_adsorbate_atoms_overlapping(
-                        adsorbates_stripped_out[unique_system],
-                        adsorbates_stripped_out[idx],
-                    )
-                    for unique_system in unique_systems
-                ]
+                self.are_all_adsorbate_atoms_overlapping(
+                    adsorbates_stripped_out[unique_system],
+                    adsorbates_stripped_out[idx],
+                )
+                for unique_system in unique_systems
             ):
                 unique_systems.append(idx)
                 unique_energies.append(energies[idx])
@@ -162,9 +166,9 @@ def __init__(
         product1_energies: list,
         product2_systems: list,
         product2_energies: list,
-        r_product1_max: float = None,
-        r_product2_max: float = None,
-        r_product2_min: float = None,
+        r_product1_max: float | None = None,
+        r_product2_max: float | None = None,
+        r_product2_min: float | None = None,
     ):
         """
         Initialize class to handle the automatic generation of NEB frames for dissociation.
@@ -1071,8 +1075,7 @@ def interpolate_and_correct_frames(
         reaction,
         map_idx,
     )
-    images = interpolate(initial, final, n_frames)
-    return images
+    return interpolate(initial, final, n_frames)
 
 
 def get_shortest_path(
@@ -1122,7 +1125,7 @@ def get_shortest_path(
     # atoms (2) the bound atom of product 1 (3) the atom of product 2 which formed a new bond
     shortest_path_final_positions = []
     equivalent_idx_factors = len(initial) * np.array(list(range(9)))
-    for idx, atom in enumerate(initial):
+    for idx, _atom in enumerate(initial):
         equivalent_indices = equivalent_idx_factors + idx
         final_distances = [
             euclidean(initial.positions[idx], new_atoms_final.positions[i])
@@ -1421,8 +1424,7 @@ def get_product2_idx(
         edge for edge in reaction.edge_list_initial if edge not in edge_list_final
     ][0]
     flat_nodes = [item for sublist in traversal_rxt1_final for item in sublist]
-    product2_binding_idx = [idx for idx in broken_edge if idx not in flat_nodes][0]
-    return product2_binding_idx
+    return [idx for idx in broken_edge if idx not in flat_nodes][0]
 
 
 def traverse_adsorbate_general(
@@ -1556,7 +1558,7 @@ def interpolate(initial_frame: ase.Atoms, final_frame: ase.Atoms, num_frames: in
         atoms_frames.append(atoms_now)
 
     # Iteratively update positions to avoid overlap
-    for i in range(100):
+    for _i in range(100):
         rate = 0.1
 
         frame_dist = []