Drop python 3.9, use ruff (#392)

* Drop python 3.9, use ruff

* switch to Ruff

* fix mypy

* remove toctrees

* fix

Author: dcherian

.github/workflows/ci.yaml

@@ -26,7 +26,7 @@ jobs:
       matrix:
         os: ["ubuntu-latest"]
         env: ["environment"]
-        python-version: ["3.9", "3.12"]
+        python-version: ["3.10", "3.12"]
         include:
           - os: "windows-latest"
             env: "environment"
@@ -36,7 +36,7 @@ jobs:
             python-version: "3.12"
           - os: "ubuntu-latest"
             env: "minimal-requirements"
-            python-version: "3.9"
+            python-version: "3.10"
     steps:
       - uses: actions/checkout@v4
         with:

.pre-commit-config.yaml

@@ -4,10 +4,11 @@ ci:
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: "v0.5.0"
+    rev: "v0.6.4"
     hooks:
       - id: ruff
         args: ["--fix", "--show-fixes"]
+      - id: ruff-format
 
   - repo: https://github.com/pre-commit/mirrors-prettier
     rev: "v4.0.0-alpha.8"
@@ -22,11 +23,6 @@ repos:
       - id: end-of-file-fixer
       - id: check-docstring-first
 
-  - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 24.4.2
-    hooks:
-      - id: black
-
   - repo: https://github.com/executablebooks/mdformat
     rev: 0.7.17
     hooks:
@@ -35,13 +31,6 @@ repos:
           - mdformat-black
           - mdformat-myst
 
-  - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.8.5
-    hooks:
-      - id: nbqa-black
-      - id: nbqa-ruff
-        args: [--fix]
-
   - repo: https://github.com/kynan/nbstripout
     rev: 0.7.1
     hooks:
@@ -56,7 +45,7 @@ repos:
           - tomli
 
   - repo: https://github.com/abravalheri/validate-pyproject
-    rev: v0.18
+    rev: v0.19
     hooks:
       - id: validate-pyproject
 

asv_bench/benchmarks/__init__.py

@@ -21,7 +21,6 @@ def _skip_slow():
     >>> from . import _skip_slow
     >>> def time_something_slow():
     ...     pass
-    ...
     >>> time_something.setup = _skip_slow
     """
     if os.environ.get("ASV_SKIP_SLOW", "0") == "1":

asv_bench/benchmarks/cohorts.py

@@ -67,7 +67,12 @@ def track_num_layers(self):
     track_num_tasks.unit = "tasks"  # type: ignore[attr-defined] # Lazy
     track_num_tasks_optimized.unit = "tasks"  # type: ignore[attr-defined] # Lazy
     track_num_layers.unit = "layers"  # type: ignore[attr-defined] # Lazy
-    for f in [track_num_tasks, track_num_tasks_optimized, track_num_layers, track_num_cohorts]:
+    for f in [
+        track_num_tasks,
+        track_num_tasks_optimized,
+        track_num_layers,
+        track_num_cohorts,
+    ]:
         f.repeat = 1  # type: ignore[attr-defined] # Lazy
         f.rounds = 1  # type: ignore[attr-defined] # Lazy
         f.number = 1  # type: ignore[attr-defined] # Lazy
@@ -82,9 +87,7 @@ def setup(self, *args, **kwargs):
         y = np.repeat(np.arange(30), 60)
         by = x[np.newaxis, :] * y[:, np.newaxis]
 
-        self.by = flox.core._factorize_multiple((by,), expected_groups=(None,), any_by_dask=False)[
-            0
-        ][0]
+        self.by = flox.core._factorize_multiple((by,), expected_groups=(None,), any_by_dask=False)[0][0]
 
         self.array = dask.array.ones(self.by.shape, chunks=(350, 350))
         self.axis = (-2, -1)
@@ -101,7 +104,12 @@ def __init__(self, *args, **kwargs):
 
     def rechunk(self):
         self.array = flox.core.rechunk_for_cohorts(
-            self.array, -1, self.by, force_new_chunk_at=[1], chunksize=48, ignore_old_chunks=True
+            self.array,
+            -1,
+            self.by,
+            force_new_chunk_at=[1],
+            chunksize=48,
+            ignore_old_chunks=True,
         )
 
 
@@ -151,7 +159,12 @@ def setup(self, *args, **kwargs):
 
     def rechunk(self):
         self.array = flox.core.rechunk_for_cohorts(
-            self.array, -1, self.by, force_new_chunk_at=[1], chunksize=4, ignore_old_chunks=True
+            self.array,
+            -1,
+            self.by,
+            force_new_chunk_at=[1],
+            chunksize=4,
+            ignore_old_chunks=True,
         )
 
 

asv_bench/benchmarks/combine.py

@@ -65,12 +65,8 @@ def construct_member(groups) -> dict[str, Any]:
             * 2
         ]
 
-        self.x_chunk_reindexed = [
-            construct_member(groups) for groups in [np.array((1, 2, 3, 4))] * 4
-        ]
+        self.x_chunk_reindexed = [construct_member(groups) for groups in [np.array((1, 2, 3, 4))] * 4]
         self.kwargs = {
-            "agg": flox.aggregations._initialize_aggregation(
-                "sum", "float64", np.float64, 0, 0, {}
-            ),
+            "agg": flox.aggregations._initialize_aggregation("sum", "float64", np.float64, 0, 0, {}),
             "axis": (3,),
         }

asv_bench/benchmarks/reduce.py

@@ -7,7 +7,11 @@
 
 N = 3000
 funcs = ["sum", "nansum", "mean", "nanmean", "max", "nanmax", "count"]
-engines = [None, "flox", "numpy"]  # numbagg is disabled for now since it takes ages in CI
+engines = [
+    None,
+    "flox",
+    "numpy",
+]  # numbagg is disabled for now since it takes ages in CI
 expected_groups = {
     "None": None,
     "bins": pd.IntervalIndex.from_breaks([1, 2, 4]),
@@ -17,9 +21,7 @@
 NUMBAGG_FUNCS = ["nansum", "nanmean", "nanmax", "count", "all"]
 numbagg_skip = []
 for name in expected_names:
-    numbagg_skip.extend(
-        list((func, name, "numbagg") for func in funcs if func not in NUMBAGG_FUNCS)
-    )
+    numbagg_skip.extend(list((func, name, "numbagg") for func in funcs if func not in NUMBAGG_FUNCS))
 
 
 def setup_jit():

ci/docs.yml

@@ -16,6 +16,7 @@ dependencies:
   - myst-parser
   - myst-nb
   - sphinx
+  - sphinx-remove-toctrees
   - furo>=2024.08
   - ipykernel
   - jupyter

docs/source/conf.py

@@ -40,6 +40,7 @@
     "sphinx.ext.napoleon",
     "myst_nb",
     "sphinx_codeautolink",
+    "sphinx_remove_toctrees",
 ]
 
 codeautolink_concat_default = True
@@ -54,6 +55,8 @@
 master_doc = "index"
 language = "en"
 
+remove_from_toctrees = ["generated/*"]
+
 # General information about the project.
 project = "flox"
 current_year = datetime.datetime.now().year

docs/source/user-stories/climatology-hourly.ipynb

@@ -92,7 +92,6 @@
     "%load_ext watermark\n",
     "\n",
     "\n",
-    "\n",
     "%watermark -iv"
    ]
   },

flox/__init__.py

@@ -1,9 +1,15 @@
 #!/usr/bin/env python
 # flake8: noqa
 """Top-level module for flox ."""
+
 from . import cache
 from .aggregations import Aggregation, Scan  # noqa
-from .core import groupby_reduce, groupby_scan, rechunk_for_blockwise, rechunk_for_cohorts  # noqa
+from .core import (
+    groupby_reduce,
+    groupby_scan,
+    rechunk_for_blockwise,
+    rechunk_for_cohorts,
+)  # noqa
 
 
 def _get_version():

flox/aggregate_flox.py

@@ -89,10 +89,14 @@ def quantile_(array, inv_idx, *, q, axis, skipna, group_idx, dtype=None, out=Non
         idxshape = (q.shape[0],) + array.shape[:-1] + (actual_sizes.shape[-1],)
 
     lo_ = np.floor(
-        virtual_index, casting="unsafe", out=np.empty(virtual_index.shape, dtype=np.int64)
+        virtual_index,
+        casting="unsafe",
+        out=np.empty(virtual_index.shape, dtype=np.int64),
     )
     hi_ = np.ceil(
-        virtual_index, casting="unsafe", out=np.empty(virtual_index.shape, dtype=np.int64)
+        virtual_index,
+        casting="unsafe",
+        out=np.empty(virtual_index.shape, dtype=np.int64),
     )
     kth = np.unique(np.concatenate([lo_.reshape(-1), hi_.reshape(-1)]))
 
@@ -119,7 +123,15 @@ def quantile_(array, inv_idx, *, q, axis, skipna, group_idx, dtype=None, out=Non
 
 
 def _np_grouped_op(
-    group_idx, array, op, axis=-1, size=None, fill_value=None, dtype=None, out=None, **kwargs
+    group_idx,
+    array,
+    op,
+    axis=-1,
+    size=None,
+    fill_value=None,
+    dtype=None,
+    out=None,
+    **kwargs,
 ):
     """
     most of this code is from shoyer's gist