Merge branch 'main' into fix-io-error-notes

scverse · Jan 2, 2024 · ff5c08f · ff5c08f
2 parents 36c8e21 + 63e6b29
commit ff5c08f
Show file tree

Hide file tree

Showing 6 changed files with 55 additions and 40 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -1,16 +1,14 @@
 repos:
-  - repo: https://github.com/psf/black
-    rev: 23.11.0
-    hooks:
-      - id: black
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    # Ruff version.
-    rev: "v0.1.7"
+    rev: v0.1.9
     hooks:
       - id: ruff
+        types_or: [python, pyi, jupyter]
         args: ["--fix"]
+      - id: ruff-format
+        types_or: [python, pyi, jupyter]
   - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: v4.0.0-alpha.4
+    rev: v4.0.0-alpha.8
     hooks:
       - id: prettier
         exclude_types:
@@ -28,7 +26,6 @@ repos:
       - id: detect-private-key
       - id: no-commit-to-branch
         args: ["--branch=main"]
-
   - repo: https://github.com/codespell-project/codespell
     rev: v2.2.6
     hooks:

diff --git a/anndata/_core/merge.py b/anndata/_core/merge.py
@@ -1108,12 +1108,18 @@ def concat(
     ...     X=sparse.csr_matrix(np.array([[0, 1], [2, 3]])),
     ...     obs=pd.DataFrame({"group": ["a", "b"]}, index=["s1", "s2"]),
     ...     var=pd.DataFrame(index=["var1", "var2"]),
-    ...     varm={"ones": np.ones((2, 5)), "rand": np.random.randn(2, 3), "zeros": np.zeros((2, 5))},
+    ...     varm={
+    ...         "ones": np.ones((2, 5)),
+    ...         "rand": np.random.randn(2, 3),
+    ...         "zeros": np.zeros((2, 5)),
+    ...     },
     ...     uns={"a": 1, "b": 2, "c": {"c.a": 3, "c.b": 4}},
     ... )
     >>> b = ad.AnnData(
     ...     X=sparse.csr_matrix(np.array([[4, 5, 6], [7, 8, 9]])),
-    ...     obs=pd.DataFrame({"group": ["b", "c"], "measure": [1.2, 4.3]}, index=["s3", "s4"]),
+    ...     obs=pd.DataFrame(
+    ...         {"group": ["b", "c"], "measure": [1.2, 4.3]}, index=["s3", "s4"]
+    ...     ),
     ...     var=pd.DataFrame(index=["var1", "var2", "var3"]),
     ...     varm={"ones": np.ones((3, 5)), "rand": np.random.randn(3, 5)},
     ...     uns={"a": 1, "b": 3, "c": {"c.b": 4}},
@@ -1147,7 +1153,7 @@ def concat(
     >>> (inner.obs_names, inner.var_names)  # doctest: +NORMALIZE_WHITESPACE
     (Index(['s1', 's2', 's3', 's4'], dtype='object'),
     Index(['var1', 'var2'], dtype='object'))
-    >>> outer = ad.concat([a, b], join="outer") # Joining on union of variables
+    >>> outer = ad.concat([a, b], join="outer")  # Joining on union of variables
     >>> outer
     AnnData object with n_obs × n_vars = 4 × 3
         obs: 'group', 'measure'

diff --git a/anndata/_core/sparse_dataset.py b/anndata/_core/sparse_dataset.py
@@ -499,12 +499,12 @@ def sparse_dataset(group: ZarrGroup | H5Group) -> CSRDataset | CSCDataset:
 
     >>> import zarr
     >>> from anndata.experimental import sparse_dataset
-    >>> group = zarr.open_group('./my_test_store.zarr')
-    >>> group['data'] = [10, 20, 30, 40, 50, 60, 70, 80]
-    >>> group['indices'] = [0, 1, 1, 3, 2, 3, 4, 5]
-    >>> group['indptr'] = [0, 2, 4, 7, 8]
-    >>> group.attrs['shape'] = (4, 6)
-    >>> group.attrs['encoding-type'] = 'csr_matrix'
+    >>> group = zarr.open_group("./my_test_store.zarr")
+    >>> group["data"] = [10, 20, 30, 40, 50, 60, 70, 80]
+    >>> group["indices"] = [0, 1, 1, 3, 2, 3, 4, 5]
+    >>> group["indptr"] = [0, 2, 4, 7, 8]
+    >>> group.attrs["shape"] = (4, 6)
+    >>> group.attrs["encoding-type"] = "csr_matrix"
     >>> sparse_dataset(group)
     CSRDataset: backend zarr, shape (4, 6), data_dtype int64
     """

diff --git a/anndata/experimental/multi_files/_anncollection.py b/anndata/experimental/multi_files/_anncollection.py
@@ -493,9 +493,12 @@ def convert(self):
         ::
 
             {
-                'X': lambda a: a.toarray() if issparse(a) else a, # densify .X
-                'obsm': lambda a: np.asarray(a, dtype='float32'), # change dtype for all keys of .obsm
-                'obs': dict(key1 = lambda c: c.astype(str)) # change type only for one key of .obs
+                # densify .X
+                "X": lambda a: a.toarray() if issparse(a) else a,
+                # change dtype for all keys of .obsm
+                "obsm": lambda a: np.asarray(a, dtype="float32"),
+                # change type only for one key of .obs
+                "obs": dict(key1=lambda c: c.astype(str)),
             }
         """
         return self._convert
@@ -817,9 +820,12 @@ def convert(self):
         ::
 
             {
-                'X': lambda a: a.toarray() if issparse(a) else a, # densify .X
-                'obsm': lambda a: np.asarray(a, dtype='float32'), # change dtype for all keys of .obsm
-                'obs': dict(key1 = lambda c: c.astype(str)) # change type only for one key of .obs
+                # densify .X
+                "X": lambda a: a.toarray() if issparse(a) else a,
+                # change dtype for all keys of .obsm
+                "obsm": lambda a: np.asarray(a, dtype="float32"),
+                # change type only for one key of .obs
+                "obs": dict(key1=lambda c: c.astype(str)),
             }
         """
         return self._convert

diff --git a/docs/benchmark-read-write.ipynb b/docs/benchmark-read-write.ipynb
@@ -20,8 +20,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import anndata as ad\n",
-    "import scanpy as sc"
+    "from __future__ import annotations\n",
+    "\n",
+    "import scanpy as sc\n",
+    "\n",
+    "import anndata as ad"
    ]
   },
   {
@@ -84,7 +87,7 @@
    ],
    "source": [
     "%%time\n",
-    "adata.write('test.h5ad')"
+    "adata.write(\"test.h5ad\")"
    ]
   },
   {
@@ -103,7 +106,7 @@
    ],
    "source": [
     "%%time\n",
-    "adata = ad.read_h5ad('test.h5ad')"
+    "adata = ad.read_h5ad(\"test.h5ad\")"
    ]
   },
   {
@@ -129,7 +132,7 @@
    ],
    "source": [
     "%%time\n",
-    "adata.write_loom('test.loom')"
+    "adata.write_loom(\"test.loom\")"
    ]
   },
   {
@@ -156,7 +159,7 @@
    ],
    "source": [
     "%%time\n",
-    "adata = ad.read_loom('test.loom')"
+    "adata = ad.read_loom(\"test.loom\")"
    ]
   }
  ],

diff --git a/pyproject.toml b/pyproject.toml
@@ -133,15 +133,10 @@ testpaths = ["anndata", "docs/concatenation.rst"]
 xfail_strict = true
 markers = ["gpu: mark test to run on GPU"]
 
-[tool.ruff]
-ignore = [
-    # line too long -> we accept long comment lines; black gets rid of long code lines
-    "E501",
-    # Do not assign a lambda expression, use a def -> AnnData allows lambda expression assignments,
-    "E731",
-    # allow I, O, l as variable names -> I is the identity matrix, i, j, k, l is reasonable indexing notation
-    "E741",
-]
+[tool.ruff.format]
+docstring-code-format = true
+
+[tool.ruff.lint]
 select = [
     "E",   # Error detected by Pycodestyle
     "F",   # Errors detected by Pyflakes
@@ -152,10 +147,18 @@ select = [
     "ICN", # Follow import conventions
     "PTH", # Pathlib instead of os.path
 ]
-[tool.ruff.per-file-ignores]
+ignore = [
+    # line too long -> we accept long comment lines; formatter gets rid of long code lines
+    "E501",
+    # Do not assign a lambda expression, use a def -> AnnData allows lambda expression assignments,
+    "E731",
+    # allow I, O, l as variable names -> I is the identity matrix, i, j, k, l is reasonable indexing notation
+    "E741",
+]
+[tool.ruff.lint.per-file-ignores]
 # E721 comparing types, but we specifically are checking that we aren't getting subtypes (views)
 "anndata/tests/test_readwrite.py" = ["E721"]
-[tool.ruff.isort]
+[tool.ruff.lint.isort]
 known-first-party = ["anndata"]
 required-imports = ["from __future__ import annotations"]