Fix default int on windows, numpy<2 (#395)

* Avoid rechunking when preferred_method="blockwise"

* Add new numpy1 environment

* try int_ instead of intp

* Use uintp instead

* Use np.uint instead

* more fixes

* Add test

* fix

* fix again

Author: dcherian

.github/workflows/ci.yaml

@@ -37,6 +37,9 @@ jobs:
           - os: "ubuntu-latest"
             env: "minimal-requirements"
             python-version: "3.10"
+          - os: "windows-latest"
+            env: "env-numpy1"
+            python-version: "3.10"
     steps:
       - uses: actions/checkout@v4
         with:

ci/env-numpy1.yml

@@ -0,0 +1,30 @@
+name: flox-tests
+channels:
+  - conda-forge
+dependencies:
+  - asv
+  - cachey
+  - cftime
+  - codecov
+  - cubed>=0.14.3
+  - dask-core
+  - pandas
+  - numpy<2
+  - scipy
+  - lxml # for mypy coverage report
+  - matplotlib
+  - pip
+  - pytest
+  - pytest-cov
+  - pytest-pretty
+  - pytest-xdist
+  - syrupy
+  - pre-commit
+  - numpy_groupies>=0.9.19
+  - pooch
+  - toolz
+  - numba
+  - numbagg>=0.3
+  - hypothesis
+  - pip:
+      - git+https://github.com/dcherian/xarray.git@flox-preserve-dtype

flox/core.py

@@ -2419,7 +2419,7 @@ def groupby_reduce(
     )
 
     is_bool_array = np.issubdtype(array.dtype, bool)
-    array = array.astype(np.intp) if is_bool_array else array
+    array = array.astype(np.int_) if is_bool_array else array
 
     isbins = _atleast_1d(isbin, nby)
 
@@ -2778,7 +2778,7 @@ def groupby_scan(
         return array
 
     is_bool_array = np.issubdtype(array.dtype, bool)
-    array = array.astype(np.intp) if is_bool_array else array
+    array = array.astype(np.int_) if is_bool_array else array
 
     if expected_groups is not None:
         raise NotImplementedError("Setting `expected_groups` and binning is not supported yet.")
@@ -2812,9 +2812,9 @@ def groupby_scan(
         # it defaults to the dtype of a, unless a
         # has an integer dtype with a precision less than that of the default platform integer.
         if array.dtype.kind == "i":
-            agg.dtype = np.result_type(array.dtype, np.intp)
+            agg.dtype = np.result_type(array.dtype, np.int_)
         elif array.dtype.kind == "u":
-            agg.dtype = np.result_type(array.dtype, np.uintp)
+            agg.dtype = np.result_type(array.dtype, np.uint)
     else:
         agg.dtype = array.dtype if dtype is None else dtype
 

flox/xrdtypes.py

@@ -179,9 +179,9 @@ def _maybe_promote_int(dtype) -> np.dtype:
     if not isinstance(dtype, np.dtype):
         dtype = np.dtype(dtype)
     if dtype.kind == "i":
-        dtype = np.result_type(dtype, np.intp)
+        dtype = np.result_type(dtype, np.int_)
     elif dtype.kind == "u":
-        dtype = np.result_type(dtype, np.uintp)
+        dtype = np.result_type(dtype, np.uint)
     return dtype
 
 

tests/conftest.py

@@ -12,6 +12,7 @@
 settings.register_profile(
     "default",
     max_examples=300,
+    deadline=500,
     suppress_health_check=[HealthCheck.filter_too_much, HealthCheck.too_slow],
     verbosity=Verbosity.verbose,
 )

tests/test_core.py

@@ -2005,4 +2005,4 @@ def test_blockwise_avoid_rechunk():
     by = np.array(["1", "1", "0", "", "0", ""], dtype="<U1")
     actual, groups = groupby_reduce(array, by, func="first")
     assert_equal(groups, ["", "0", "1"])
-    assert_equal(actual, [0, 0, 0])
+    assert_equal(actual, np.array([0, 0, 0], dtype=np.int64))