add .pre-commit-config.yaml, run lint

Author: ryan-williams

.pre-commit-config.yaml

@@ -0,0 +1,20 @@
+repos:
+  - repo: https://github.com/psf/black
+    rev: "24.8.0"
+    hooks:
+      - id: black
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.6.2
+    hooks:
+      - id: ruff
+        name: "ruff for tiledbsoma_ml"
+        args: ["--config=pyproject.toml"]
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.11.1
+    hooks:
+      - id: mypy
+        pass_filenames: false
+        args: ["--config-file=pyproject.toml", "src"]
+        additional_dependencies: ["attrs", "numpy"]

notebooks/tutorial_lightning.ipynb

@@ -31,12 +31,13 @@
    "outputs": [],
    "source": [
     "import pytorch_lightning as pl\n",
-    "import tiledbsoma_ml as soma_ml\n",
     "import torch\n",
     "from sklearn.preprocessing import LabelEncoder\n",
     "\n",
     "import tiledbsoma as soma\n",
     "\n",
+    "import tiledbsoma_ml as soma_ml\n",
+    "\n",
     "CZI_Census_Homo_Sapiens_URL = \"s3://cellxgene-census-public-us-west-2/cell-census/2024-07-01/soma/census_data/homo_sapiens/\"\n",
     "\n",
     "experiment = soma.open(\n",

notebooks/tutorial_pytorch.ipynb

@@ -42,11 +42,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import tiledbsoma_ml as soma_ml\n",
     "from sklearn.preprocessing import LabelEncoder\n",
     "\n",
     "import tiledbsoma as soma\n",
     "\n",
+    "import tiledbsoma_ml as soma_ml\n",
+    "\n",
     "CZI_Census_Homo_Sapiens_URL = \"s3://cellxgene-census-public-us-west-2/cell-census/2024-07-01/soma/census_data/homo_sapiens/\"\n",
     "\n",
     "experiment = soma.open(\n",

pyproject.toml

@@ -16,7 +16,7 @@ dependencies = [
     "pyarrow",
     "scipy"
 ]
-requires-python = ">= 3.8"
+requires-python = ">= 3.9"
 description = "Machine learning tools for use with tiledbsoma"
 readme = "README.md"
 authors = [
@@ -39,7 +39,6 @@ classifiers = [
     "Operating System :: MacOS :: MacOS X",
     "Operating System :: Microsoft :: Windows",
     "Programming Language :: Python",
-    "Programming Language :: Python :: 3.8",
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
@@ -65,15 +64,15 @@ show_error_codes = true
 ignore_missing_imports = true
 warn_unreachable = true
 strict = true
-python_version = 3.8
+python_version = 3.9
 plugins = "numpy.typing.mypy_plugin"
 
 [tool.ruff]
 lint.select = ["E", "F", "B", "I"]
 lint.ignore = ["E501"]  # line too long
 lint.extend-select = ["I001"]  # unsorted-imports
 fix = true
-target-version = "py38"
+target-version = "py39"
 line-length = 120
 
 

tests/test_pytorch.py

@@ -26,13 +26,14 @@
 # This supports the pytest `ml` mark, which can be used to disable all PyTorch-dependent
 # tests.
 try:
+    from torch.utils.data._utils.worker import WorkerInfo
+
     from tiledbsoma_ml.pytorch import (
         ExperimentAxisQueryIterable,
         ExperimentAxisQueryIterableDataset,
         ExperimentAxisQueryIterDataPipe,
         experiment_dataloader,
     )
-    from torch.utils.data._utils.worker import WorkerInfo
 except ImportError:
     # this should only occur when not running `ml`-marked tests
     pass
@@ -538,11 +539,11 @@ def test_distributed__returns_data_partition_for_rank(
     """Tests pytorch._partition_obs_joinids() behavior in a simulated PyTorch distributed processing mode,
     using mocks to avoid having to do real PyTorch distributed setup."""
 
-    with patch("torch.distributed.is_initialized") as mock_dist_is_initialized, patch(
-        "torch.distributed.get_rank"
-    ) as mock_dist_get_rank, patch(
-        "torch.distributed.get_world_size"
-    ) as mock_dist_get_world_size:
+    with (
+        patch("torch.distributed.is_initialized") as mock_dist_is_initialized,
+        patch("torch.distributed.get_rank") as mock_dist_get_rank,
+        patch("torch.distributed.get_world_size") as mock_dist_get_world_size,
+    ):
         mock_dist_is_initialized.return_value = True
         mock_dist_get_rank.return_value = rank
         mock_dist_get_world_size.return_value = world_size
@@ -593,13 +594,12 @@ def test_distributed_and_multiprocessing__returns_data_partition_for_rank(
     DataLoader multiprocessing mode, using mocks to avoid having to do distributed pytorch
     setup or real DataLoader multiprocessing."""
 
-    with patch("torch.utils.data.get_worker_info") as mock_get_worker_info, patch(
-        "torch.distributed.is_initialized"
-    ) as mock_dist_is_initialized, patch(
-        "torch.distributed.get_rank"
-    ) as mock_dist_get_rank, patch(
-        "torch.distributed.get_world_size"
-    ) as mock_dist_get_world_size:
+    with (
+        patch("torch.utils.data.get_worker_info") as mock_get_worker_info,
+        patch("torch.distributed.is_initialized") as mock_dist_is_initialized,
+        patch("torch.distributed.get_rank") as mock_dist_get_rank,
+        patch("torch.distributed.get_world_size") as mock_dist_get_world_size,
+    ):
         mock_get_worker_info.return_value = WorkerInfo(
             id=worker_id, num_workers=num_workers, seed=1234
         )