fix return-before-assignment bug in notebook test script, add pre-commit, drop cuspatial notebooks

.github/ISSUE_TEMPLATE/bug_report.md

@@ -21,7 +21,7 @@ A clear and concise description of what you expected to happen.
  - Method of cuDF install: [conda, Docker, or from source]
    - If method of install is [Docker], provide `docker pull` & `docker run` commands used
  - Please run and attach the output of the `cudf/print_env.sh` script to gather relevant environment details
- 
+
 
 **Additional context**
 Add any other context about the problem here.

.github/workflows/pr.yml

@@ -10,7 +10,20 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  checks:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+      - name: Run pre-commit
+        run: |
+          pip install pre-commit
+          pre-commit run --all-files
   docker:
+    needs: [checks]
     uses: ./.github/workflows/build-test-publish-images.yml
     with:
       build_type: pull-request

.pre-commit-config.yaml

@@ -0,0 +1,12 @@
+---
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.5.2
+    hooks:
+      - id: ruff
+        args: ["--config", "pyproject.toml"]

context/test_notebooks.py

@@ -5,9 +5,7 @@
 import sys
 import timeit
 from typing import Iterable
-import nbconvert
 import nbformat
-from datetime import datetime
 from nbconvert.preprocessors import ExecutePreprocessor
 import yaml
 
@@ -29,12 +27,15 @@
     # following nbs are marked as skipped
     'cugraph/algorithms/layout/Force-Atlas2.ipynb',
     'cuspatial/binary_predicates.ipynb',
-    'cuspatial/cuproj_benchmark.ipynb'
+    'cuspatial/cuproj_benchmark.ipynb',
+    # context on these being skipped: https://github.com/rapidsai/cuspatial/pull/1407
+    'cuspatial/cuspatial_api_examples.ipynb',
+    'cuspatial/nyc_taxi_years_correlation.ipynb'
 ]
 
 
 def get_notebooks(directory: str) -> Iterable[str]:
-    for root, dirs, files in os.walk(directory):
+    for root, _, files in os.walk(directory):
         for file in files:
             if (
                 file.endswith(".ipynb")
@@ -71,12 +72,12 @@ def test_notebook(notebook_file, executed_nb_file):
 
         # use nbconvert to run the notebook natively
         ep = ExecutePreprocessor(timeout=600, kernel_name="python3", allow_errors=True)
+        task_init = timeit.default_timer()
         try:
-            task_init = timeit.default_timer()
-            nb, nb_resources = ep.preprocess(nb, {"metadata": {"path": ""}})
-            execution_time = timeit.default_timer() - task_init
+            nb, _ = ep.preprocess(nb, {"metadata": {"path": ""}})
         except Exception as e:
             errors.append(e)
+        execution_time = timeit.default_timer() - task_init
 
         with open(executed_nb_file, "w", encoding="utf-8") as f:
             nbformat.write(nb, f)
@@ -152,7 +153,7 @@ def test_notebook(notebook_file, executed_nb_file):
         print(f"Input must be a directory. Got: {ns.input}")
         sys.exit(1)
 
-    notebooks = sorted(list(get_notebooks(ns.input)))
+    notebooks = sorted(get_notebooks(ns.input))
     print(f"{len(notebooks)} Notebooks to be tested:")
     for notebook in notebooks:
         print(notebook)

pyproject.toml

@@ -0,0 +1,40 @@
+[tool.ruff]
+target-version = "py310"
+
+[tool.ruff.lint]
+ignore = [
+    # (flake8) line too long
+    "E501",
+    # (pylint) too many branches
+    "PLR0912",
+]
+select = [
+    # flake8-builtins
+    "A",
+    # flake8-bugbear
+    "B",
+    # flake8-comprehensions
+    "C4",
+    # pycodestyle
+    "E",
+    # eradicate
+    "ERA",
+    # pyflakes
+    "F",
+    # flynt
+    "FLY",
+    # perflint
+    "PERF",
+    # pygrep-hooks
+    "PGH",
+    # pylint
+    "PL",
+    # flake8-pyi
+    "PYI",
+    # flake8-return
+    "RET",
+    # ruff-exclusive checks
+    "RUF",
+    # flake8-bandit
+    "S",
+]

raft-ann-bench/README.md

@@ -2,7 +2,7 @@
 
 This folder contains the dockerfiles for generating GPU and CPU RAFT ANN benchmark images.
 
-This images are meant to enable end users of RAFT's ANN algorithms to easily run and reproduce benchmarks and comparisons between RAFT and third party libraries. 
+These images are meant to enable end users of RAFT's ANN algorithms to easily run and reproduce benchmarks and comparisons between RAFT and third party libraries.
 
 # Image types:
 

raft-ann-bench/cpu/Dockerfile

@@ -60,4 +60,3 @@ RUN /home/rapids/raftannbench/get_datasets.sh
 CMD ["--dataset fashion-mnist-784-euclidean", "", "--algorithms hnswlib"]
 
 ENTRYPOINT ["/bin/bash", "/data/scripts/run_benchmark_preloaded_datasets.sh"]
-