General maintenance (#73)

crusaderky · web-flow · commit fc8fe5b92aa3 · 2026-03-08T18:48:50.000Z
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -19,7 +19,7 @@ jobs:
 
       - uses: prefix-dev/setup-pixi@v0
         with:
-          pixi-version: v0.63.2
+          pixi-version: v0.65.0
           cache: true
           environments: docs
 
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -13,7 +13,7 @@ jobs:
       - uses: actions/checkout@v6
       - uses: prefix-dev/setup-pixi@v0
         with:
-          pixi-version: v0.63.2
+          pixi-version: v0.65.0
           cache: true
           environments: lint
       - name: Run linters
diff --git a/.github/workflows/pytest.yml b/.github/workflows/pytest.yml
@@ -55,7 +55,7 @@ jobs:
 
       - uses: prefix-dev/setup-pixi@v0
         with:
-          pixi-version: v0.63.2
+          pixi-version: v0.65.0
           environments: ${{ matrix.environment }}
           cache: ${{ matrix.environment != 'upstream' }}
           locked: ${{ matrix.environment != 'upstream' }}
diff --git a/.github/workflows/wheels.yml b/.github/workflows/wheels.yml
@@ -22,7 +22,7 @@ jobs:
 
       - uses: prefix-dev/setup-pixi@v0
         with:
-          pixi-version: v0.63.2
+          pixi-version: v0.65.0
           cache: true
           environments: dist
 
diff --git a/doc/requirements.yml b/doc/requirements.yml
@@ -11,6 +11,7 @@ dependencies:
 - msgpack-python *
 - pyyaml *
 - netcdf4 *
+- libnetcdf !=4.10.0
 - scipy *
 - h5netcdf *
 - zarr *
diff --git a/doc/whats-new.rst b/doc/whats-new.rst
@@ -9,8 +9,8 @@ v2.1.0 (unreleased)
   of text messages for all differences in numpy, pandas, and xarray objects
 - New function :func:`display_diffs` that displays differences
   in Jupyter notebooks
-- Fixed issue that would cause excessive RAM usage when comparing Dask arrays with
-  2+ dimensions using a distributed scheduler
+- Fixed issues that would cause slowdowns and excessive RAM usage when comparing Dask
+  arrays with 2+ dimensions using a distributed scheduler
 - Added support for P2P rechunk in Dask distributed
 
 
diff --git a/pixi.lock b/pixi.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -170,6 +170,7 @@ distributed = "*"
 msgpack-python = "*"
 PyYAML = "*"
 netcdf4 = "*" # netCDF engine
+libnetcdf = "!=4.10.0" # Breaks coverage
 scipy = "*" # netCDF engine
 h5netcdf = "*" # netCDF engine
 zarr = "*"
@@ -227,6 +228,7 @@ ipython = { cmd = "ipython", description = "Launch IPython" }
 
 [tool.pixi.feature.jupyter.dependencies]
 jupyterlab = "*"
+python-graphviz = "*"
 
 [tool.pixi.feature.jupyter.tasks]
 jupyter = { cmd = "jupyter lab", description = "Launch JupyterLab" }
diff --git a/recursive_diff/core.py b/recursive_diff/core.py
@@ -430,15 +430,9 @@ def _diff_dataarrays(
     # Generate a bit-mask of the differences
     # For Dask-backed arrays, this operation is delayed.
     if lhs.dtype.kind in "iufc" and rhs.dtype.kind in "iufc":
-        # Both arrays are numeric
-        if is_dask:
-            import dask.array as da
-
-            isclose = da.isclose
-        else:
-            isclose = np.isclose
-
-        mask = ~isclose(lhs.data, rhs.data, rtol=rel_tol, atol=abs_tol, equal_nan=True)
+        mask = ~np.isclose(
+            lhs.data, rhs.data, rtol=rel_tol, atol=abs_tol, equal_nan=True
+        )
     elif lhs.dtype.kind == "M" and rhs.dtype.kind == "M":
         # Both arrays are datetime64
         # Unlike with np.isclose(equal_nan=True), there is no
diff --git a/recursive_diff/tests/test_diff_arrays.py b/recursive_diff/tests/test_diff_arrays.py
@@ -52,7 +52,7 @@ def test_diff_arrays(chunk):
                 "abs_delta": [1.0],
                 "rel_delta": [0.25],
                 "x": ["b"],
-                "y": np.asarray([1]),
+                "y": np.asarray([1], dtype=np.int_),
             }
         ).set_index(["x", "y"]),
     )
@@ -61,7 +61,7 @@ def test_diff_arrays(chunk):
         arrays["[3][data]"],
         pd.DataFrame(
             {"lhs": ["bar"], "rhs": ["baz"]},
-            index=pd.Index(np.asarray([1]), name="dim_0"),
+            index=pd.Index(np.asarray([1], dtype=np.int_), name="dim_0"),
         ),
     )
 
diff --git a/recursive_diff/tests/test_recursive_diff.py b/recursive_diff/tests/test_recursive_diff.py
@@ -83,9 +83,10 @@ def __repr__(self):
         return f"Square({self.side})"
 
 
-def check(lhs, rhs, *expect, **kwargs):
-    expect = sorted(expect)
-    actual = sorted(recursive_diff(lhs, rhs, **kwargs))
+def check(lhs, rhs, *expect, order=False, **kwargs):
+    f = list if order else sorted
+    expect = f(expect)
+    actual = f(recursive_diff(lhs, rhs, **kwargs))
     assert actual == expect
 
 
@@ -1165,6 +1166,67 @@ def test_dask_dataarray(chunk_lhs, chunk_rhs):
     check(lhs, rhs, "[data][x=2]: c != d")
 
 
+@requires_dask
+@pytest.mark.parametrize(
+    "chunk_lhs,chunk_rhs",
+    [
+        (None, None),
+        (None, -1),
+        (None, 2),
+        ({"x": 3, "y": 1}, {"x": 2, "y": 2}),
+    ],
+)
+def test_dask_dataarray_2d(chunk_lhs, chunk_rhs):
+    lhs = xarray.DataArray([[0, 1, 2], [3, 4, 5]], dims=["x", "y"])
+    rhs = xarray.DataArray([[0, 1, 2], [3, 4, 6]], dims=["x", "y"])
+    if chunk_lhs:
+        lhs = lhs.chunk(chunk_lhs)
+    if chunk_rhs:
+        rhs = rhs.chunk(chunk_rhs)
+
+    check(lhs, rhs, "[data][x=1, y=2]: 5 != 6 (abs: 1.0e+00, rel: 2.0e-01)")
+
+
+def test_dask_dataarray_ordered(chunk):
+    """Test that difference order goes in C order and is not influenced
+    by Dask chunks.
+    """
+    lhs = xarray.DataArray(np.arange(2 * 3 * 4).reshape(2, 3, 4), dims=["x", "y", "z"])
+    rhs = lhs + 1
+    if chunk:
+        lhs = lhs.chunk({"x": 2, "y": 2, "z": 3})
+        rhs = rhs.chunk({"x": 2, "y": 2, "z": 3})
+    check(
+        lhs,
+        rhs,
+        "[data][x=0, y=0, z=0]: 0 != 1 (abs: 1.0e+00, rel: nan)",
+        "[data][x=0, y=0, z=1]: 1 != 2 (abs: 1.0e+00, rel: 1.0e+00)",
+        "[data][x=0, y=0, z=2]: 2 != 3 (abs: 1.0e+00, rel: 5.0e-01)",
+        "[data][x=0, y=0, z=3]: 3 != 4 (abs: 1.0e+00, rel: 3.3e-01)",
+        "[data][x=0, y=1, z=0]: 4 != 5 (abs: 1.0e+00, rel: 2.5e-01)",
+        "[data][x=0, y=1, z=1]: 5 != 6 (abs: 1.0e+00, rel: 2.0e-01)",
+        "[data][x=0, y=1, z=2]: 6 != 7 (abs: 1.0e+00, rel: 1.7e-01)",
+        "[data][x=0, y=1, z=3]: 7 != 8 (abs: 1.0e+00, rel: 1.4e-01)",
+        "[data][x=0, y=2, z=0]: 8 != 9 (abs: 1.0e+00, rel: 1.2e-01)",
+        "[data][x=0, y=2, z=1]: 9 != 10 (abs: 1.0e+00, rel: 1.1e-01)",
+        "[data][x=0, y=2, z=2]: 10 != 11 (abs: 1.0e+00, rel: 1.0e-01)",
+        "[data][x=0, y=2, z=3]: 11 != 12 (abs: 1.0e+00, rel: 9.1e-02)",
+        "[data][x=1, y=0, z=0]: 12 != 13 (abs: 1.0e+00, rel: 8.3e-02)",
+        "[data][x=1, y=0, z=1]: 13 != 14 (abs: 1.0e+00, rel: 7.7e-02)",
+        "[data][x=1, y=0, z=2]: 14 != 15 (abs: 1.0e+00, rel: 7.1e-02)",
+        "[data][x=1, y=0, z=3]: 15 != 16 (abs: 1.0e+00, rel: 6.7e-02)",
+        "[data][x=1, y=1, z=0]: 16 != 17 (abs: 1.0e+00, rel: 6.2e-02)",
+        "[data][x=1, y=1, z=1]: 17 != 18 (abs: 1.0e+00, rel: 5.9e-02)",
+        "[data][x=1, y=1, z=2]: 18 != 19 (abs: 1.0e+00, rel: 5.6e-02)",
+        "[data][x=1, y=1, z=3]: 19 != 20 (abs: 1.0e+00, rel: 5.3e-02)",
+        "[data][x=1, y=2, z=0]: 20 != 21 (abs: 1.0e+00, rel: 5.0e-02)",
+        "[data][x=1, y=2, z=1]: 21 != 22 (abs: 1.0e+00, rel: 4.8e-02)",
+        "[data][x=1, y=2, z=2]: 22 != 23 (abs: 1.0e+00, rel: 4.5e-02)",
+        "[data][x=1, y=2, z=3]: 23 != 24 (abs: 1.0e+00, rel: 4.3e-02)",
+        order=False,
+    )
+
+
 @requires_dask
 def test_dask_dataarray_discards_data():
     """Test that chunked Dask datasets are loaded into memory and then
@@ -1305,9 +1367,9 @@ def test_lazy_datasets_without_dask(tmp_path):
     [
         # Different OSes and dependency versions have different peak RAM usages.
         # These are the worst case scenarios across all combinations.
-        ("netcdf", None, 100),  # Takes more on MacOS
+        ("netcdf", None, 100),  # Uses more RAM on MacOS
         ("netcdf", {}, 50),
-        ("zarr", None, 90),
+        ("zarr", None, 100),
         ("zarr", {}, 25),  # ~5 MiB on Linux, up to 25 MiB on Windows
     ],
 )

Original file line number	Diff line number	Diff line change
`@@ -52,7 +52,7 @@ def test_diff_arrays(chunk):`
`52`	`52`	`"abs_delta": [1.0],`
`53`	`53`	`"rel_delta": [0.25],`
`54`	`54`	`"x": ["b"],`
`55`		`- "y": np.asarray([1]),`
	`55`	`+ "y": np.asarray([1], dtype=np.int_),`
`56`	`56`	`}`
`57`	`57`	`).set_index(["x", "y"]),`
`58`	`58`	`)`
`@@ -61,7 +61,7 @@ def test_diff_arrays(chunk):`
`61`	`61`	`arrays["[3][data]"],`
`62`	`62`	`pd.DataFrame(`
`63`	`63`	`{"lhs": ["bar"], "rhs": ["baz"]},`
`64`		`- index=pd.Index(np.asarray([1]), name="dim_0"),`
	`64`	`+ index=pd.Index(np.asarray([1], dtype=np.int_), name="dim_0"),`
`65`	`65`	`),`
`66`	`66`	`)`
`67`	`67`