feat: add more pre-commit hooks and Ruff checks

.github/dependabot.yml

@@ -0,0 +1,10 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/" # .github/workflows
+    schedule:
+      interval: "monthly"
+    groups:
+      gha-workflow-deps:
+        patterns:
+          - "*"

.github/workflows/ci.yml

@@ -14,12 +14,12 @@ jobs:
     env:
       FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v7
       with:
         persist-credentials: false
 
     - name: Setup Micromamba
-      uses: mamba-org/setup-micromamba@v2
+      uses: mamba-org/setup-micromamba@v3
       with:
         environment-file: environment.yml
         init-shell: bash

.github/workflows/docs.yml

@@ -25,10 +25,10 @@ jobs:
     env:
       FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v7
 
       - name: Setup Micromamba
-        uses: mamba-org/setup-micromamba@v2
+        uses: mamba-org/setup-micromamba@v3
         with:
           environment-file: environment.yml
           init-shell: bash
@@ -70,7 +70,7 @@ jobs:
           import subprocess; subprocess.run(['zensical', 'build', '--clean'], check=True)"
 
       - name: Upload artifact
-        uses: actions/upload-pages-artifact@v3
+        uses: actions/upload-pages-artifact@v5
         with:
           path: ./site
 
@@ -84,4 +84,4 @@ jobs:
     steps:
       - name: Deploy to GitHub Pages
         id: deployment
-        uses: actions/deploy-pages@v4
+        uses: actions/deploy-pages@v5

.pre-commit-config.yaml

@@ -1,14 +1,30 @@
 repos:
--   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.3.0
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
     hooks:
-    -   id: ruff
-        args: [ --fix ]
-    -   id: ruff-format
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+        args: ['--unsafe']
+      - id: check-json
+      - id: check-toml
+      - id: check-shebang-scripts-are-executable
+        exclude: '\.sl$'  # Slurm job scripts
+      - id: check-executables-have-shebangs
+      - id: check-symlinks
+      - id: check-added-large-files
+        args: ['--maxkb=1000']
 
--   repo: local
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.15.22
     hooks:
-    -   id: generate-requirements
+      - id: ruff-check
+        args: [--fix]
+      - id: ruff-format
+
+  - repo: local
+    hooks:
+      - id: generate-requirements
         name: generate-requirements
         entry: python3 scripts/generate_requirements.py
         language: system

benchmarks/real_benchmark.py

@@ -1,7 +1,9 @@
 import time
+
 import numpy as np
 import xarray as xr
 import xesmf as xe
+
 from xregrid import Regridder
 
 
@@ -21,21 +23,15 @@ def create_sample_dataset(nlat, nlon, ntime=1):
     return ds
 
 
-def benchmark_resolution(
-    name, nlat_in, nlon_in, nlat_out, nlon_out, ntime=10, trials=3
-):
+def benchmark_resolution(name, nlat_in, nlon_in, nlat_out, nlon_out, ntime=10, trials=3):
     print(f"\n--- Benchmarking {name} ({ntime} time steps) ---")
     source_ds = create_sample_dataset(nlat_in, nlon_in, ntime=ntime)
     target_ds = create_sample_dataset(nlat_out, nlon_out, ntime=1)
 
     # --- Weight Generation ---
     print("Generating weights...")
-    regridder_xesmf = xe.Regridder(
-        source_ds.isel(time=0), target_ds.isel(time=0), method="bilinear", periodic=True
-    )
-    regridder_xregrid = Regridder(
-        source_ds.isel(time=0), target_ds.isel(time=0), method="bilinear", periodic=True
-    )
+    regridder_xesmf = xe.Regridder(source_ds.isel(time=0), target_ds.isel(time=0), method="bilinear", periodic=True)
+    regridder_xregrid = Regridder(source_ds.isel(time=0), target_ds.isel(time=0), method="bilinear", periodic=True)
 
     # --- Weight Application ---
     print(f"Applying weights ({trials} trials)...")
@@ -64,9 +60,7 @@ def benchmark_resolution(
         times_xregrid.append(time.perf_counter() - start)
     avg_xregrid = np.mean(times_xregrid) / ntime
 
-    print(
-        f"App avg per time step - xESMF: {avg_xesmf:.6f}s, XRegrid: {avg_xregrid:.6f}s"
-    )
+    print(f"App avg per time step - xESMF: {avg_xesmf:.6f}s, XRegrid: {avg_xregrid:.6f}s")
     print(f"Application Speedup: {avg_xesmf / avg_xregrid:.1f}x")
 
     return {
@@ -85,18 +79,12 @@ def benchmark_resolution(
 results.append(benchmark_resolution("0.25° Global", 720, 1440, 720, 1440, ntime=3))
 
 # 0.1° Global
-results.append(
-    benchmark_resolution("0.1° Global", 1800, 3600, 1800, 3600, ntime=1, trials=1)
-)
+results.append(benchmark_resolution("0.1° Global", 1800, 3600, 1800, 3600, ntime=1, trials=1))
 
 print("\n\n" + "=" * 50)
 print("FINAL RESULTS SUMMARY (SINGLE TIME STEP REGRIDDING)")
 print("=" * 50)
-print(
-    f"{'Resolution':<15} | {'xESMF App (s)':<15} | {'XRegrid App (s)':<15} | {'Speedup':<10}"
-)
+print(f"{'Resolution':<15} | {'xESMF App (s)':<15} | {'XRegrid App (s)':<15} | {'Speedup':<10}")
 print("-" * 65)
 for r in results:
-    print(
-        f"{r['name']:<15} | {r['app_xesmf']:<15.6f} | {r['app_xregrid']:<15.6f} | {r['speedup']:<10.1f}x"
-    )
+    print(f"{r['name']:<15} | {r['app_xesmf']:<15.6f} | {r['app_xregrid']:<15.6f} | {r['speedup']:<10.1f}x")

benchmarks/run_benchmarks.py

@@ -36,9 +36,7 @@ def generate_mock_weights(n_src, n_dst, weights_per_row=4):
     return csr_matrix((data, (row, col)), shape=(n_dst, n_src))
 
 
-def benchmark_apply(
-    res_name, n_lat, n_lon, target_n_lat, target_n_lon, n_time=1, skipna=False
-):
+def benchmark_apply(res_name, n_lat, n_lon, target_n_lat, target_n_lon, n_time=1, skipna=False):
     n_src = n_lat * n_lon
     n_dst = target_n_lat * target_n_lon
 
@@ -99,9 +97,7 @@ def benchmark_stationary_mask(n_lat, n_lon, n_time=10):
 
     # Time with skipna=True
     start = time.perf_counter()
-    _ = _apply_weights_core(
-        data, weights_key, ("lat", "lon"), (n_lat, n_lon), skipna=True
-    )
+    _ = _apply_weights_core(data, weights_key, ("lat", "lon"), (n_lat, n_lon), skipna=True)
     end = time.perf_counter()
 
     total_time = end - start
@@ -126,7 +122,7 @@ def benchmark_stationary_mask(n_lat, n_lon, n_time=10):
 print("| Time Steps | Resolution | Avg Time per Step |")
 print("|------------|------------|-------------------|")
 for n_t in [1, 10, 100]:
-    for name, ny, nx, tny, tnx in [
+    for name, ny, nx, _tny, _tnx in [
         ("1.0°", 180, 360, 180, 360),
         ("0.25°", 720, 1440, 720, 1440),
     ]:

benchmarks/run_dask_benchmark.py

@@ -29,9 +29,7 @@ def generate_mock_weights(n_src, n_dst, weights_per_row=4):
 
 
 def benchmark_dask(n_workers, n_chunks, n_lat=360, n_lon=720):
-    cluster = dask.distributed.LocalCluster(
-        n_workers=n_workers, threads_per_worker=1, processes=True
-    )
+    cluster = dask.distributed.LocalCluster(n_workers=n_workers, threads_per_worker=1, processes=True)
     client = dask.distributed.Client(cluster)
 
     try:
@@ -41,9 +39,7 @@ def benchmark_dask(n_workers, n_chunks, n_lat=360, n_lon=720):
 
         # 20 time steps
         data = np.random.rand(20, n_lat, n_lon).astype(np.float32)
-        da = xr.DataArray(data, dims=("time", "lat", "lon")).chunk(
-            {"time": 20 // n_chunks}
-        )
+        da = xr.DataArray(data, dims=("time", "lat", "lon")).chunk({"time": 20 // n_chunks})
 
         # We need to distribute weights to workers
         weights_key = "bench_weights"

docs/examples/scripts/create_sample_data.py

@@ -8,6 +8,7 @@
 """
 
 import numpy as np
+
 from xregrid.utils import create_global_grid
 
 
@@ -18,9 +19,7 @@ def create_sample_data():
     # Add some dummy data
     lat = ds.lat.values
     lon = ds.lon.values
-    data = (
-        np.sin(np.deg2rad(lat))[:, np.newaxis] * np.cos(np.deg2rad(lon))[np.newaxis, :]
-    )
+    data = np.sin(np.deg2rad(lat))[:, np.newaxis] * np.cos(np.deg2rad(lon))[np.newaxis, :]
 
     ds["sample_var"] = (["lat", "lon"], data)
     ds["sample_var"].attrs["units"] = "dimensionless"

docs/examples/scripts/plot_accessor_showcase.py

@@ -11,9 +11,9 @@
 - Passing Regridder parameters through the accessor
 """
 
-import xarray as xr
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
+import xarray as xr
 
 # Load air_temperature tutorial dataset
 ds = xr.tutorial.open_dataset("air_temperature").isel(time=0)

docs/examples/scripts/plot_air_temperature.py

@@ -12,9 +12,10 @@
 - Regridding 3D datasets (time, lat, lon)
 """
 
-import xarray as xr
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
+import xarray as xr
+
 from xregrid import Regridder
 
 # Load air_temperature tutorial dataset (North America, 2.5° resolution)

docs/examples/scripts/plot_basic_regridding.py

@@ -13,9 +13,10 @@
 - Handling global periodicity
 """
 
-import xarray as xr
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
+import xarray as xr
+
 from xregrid import Regridder
 
 # Load tutorial dataset (global, 0.75° resolution)

docs/examples/scripts/plot_conservative_regridding.py

@@ -10,8 +10,9 @@
 (bounds), which are automatically provided by XRegrid's grid creation utilities.
 """
 
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
+
 from xregrid import Regridder, create_global_grid
 
 # 1. Create a source grid with boundaries (2.0° resolution)

docs/examples/scripts/plot_curvilinear_grids.py

@@ -7,9 +7,10 @@
 We use the 'rasm' tutorial dataset which features a curvilinear Arctic grid.
 """
 
-import xarray as xr
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
+import xarray as xr
+
 from xregrid import Regridder
 
 # Load rasm tutorial dataset (curvilinear Arctic grid)

docs/examples/scripts/plot_dateline_fix.py

@@ -9,6 +9,7 @@
 
 import numpy as np
 import xarray as xr
+
 from xregrid import Regridder
 from xregrid.utils import create_global_grid
 
@@ -55,9 +56,7 @@ def run_example():
 
     print("Regridding complete.")
     print(f"Output Variables: {list(ds_regrid.data_vars)}")
-    print(
-        f"Source Longitude Range: {ds_src.lon.min().values:.1f} to {ds_src.lon.max().values:.1f}"
-    )
+    print(f"Source Longitude Range: {ds_src.lon.min().values:.1f} to {ds_src.lon.max().values:.1f}")
     print("Coordinates crossing the dateline are handled correctly by using SPH_DEG.")
 
     # In a real environment with matplotlib:

docs/examples/scripts/plot_esmpy_comparison.py

@@ -11,9 +11,10 @@
 API while delivering better performance than other wrappers.
 """
 
-import xarray as xr
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
+import xarray as xr
+
 from xregrid import Regridder
 
 # --- Part 1: Load Sample Data ---

docs/examples/scripts/plot_larger_than_memory.py

@@ -17,11 +17,13 @@
 - Memory-efficient processing on a local machine.
 """
 
-import xarray as xr
-import numpy as np
+import time
+
 import dask.array as da
+import numpy as np
+import xarray as xr
 from dask.distributed import Client, LocalCluster
-import time
+
 from xregrid import Regridder
 
 
@@ -75,9 +77,7 @@ def run_example():
     # for high-resolution grids.
     print("\nGenerating weights in parallel...")
     start = time.time()
-    regridder = Regridder(
-        ds_src, ds_tgt, method="bilinear", periodic=True, parallel=True
-    )
+    regridder = Regridder(ds_src, ds_tgt, method="bilinear", periodic=True, parallel=True)
     print(f"Weight generation took: {time.time() - start:.2f}s")
 
     # 5. Apply regridding (Lazy)

docs/examples/scripts/plot_multidimensional_regridding.py

@@ -12,9 +12,10 @@
 - Global periodicity for 4D atmospheric data
 """
 
-import xarray as xr
-import numpy as np
 import matplotlib.pyplot as plt
+import numpy as np
+import xarray as xr
+
 from xregrid import Regridder
 
 # Load multidimensional tutorial dataset (ERA-Interim)