Fix seed for random test data. (#9844)

* Fix seed for random test data.

Also switch to using default_rng instead of RandomState.

* Fixes

* one more fix.

* more fixes

* last one?

* one more

Author: dcherian

asv_bench/benchmarks/__init__.py

@@ -30,13 +30,13 @@ def requires_sparse():
 
 
 def randn(shape, frac_nan=None, chunks=None, seed=0):
-    rng = np.random.RandomState(seed)
+    rng = np.random.default_rng(seed)
     if chunks is None:
         x = rng.standard_normal(shape)
     else:
         import dask.array as da
 
-        rng = da.random.RandomState(seed)
+        rng = da.random.default_rng(seed)
         x = rng.standard_normal(shape, chunks=chunks)
 
     if frac_nan is not None:
@@ -47,7 +47,7 @@ def randn(shape, frac_nan=None, chunks=None, seed=0):
 
 
 def randint(low, high=None, size=None, frac_minus=None, seed=0):
-    rng = np.random.RandomState(seed)
+    rng = np.random.default_rng(seed)
     x = rng.randint(low, high, size)
     if frac_minus is not None:
         inds = rng.choice(range(x.size), int(x.size * frac_minus))

asv_bench/benchmarks/reindexing.py

@@ -11,7 +11,7 @@
 
 class Reindex:
     def setup(self):
-        data = np.random.RandomState(0).randn(ntime, nx, ny)
+        data = np.random.default_rng(0).random((ntime, nx, ny))
         self.ds = xr.Dataset(
             {"temperature": (("time", "x", "y"), data)},
             coords={"time": np.arange(ntime), "x": np.arange(nx), "y": np.arange(ny)},

asv_bench/benchmarks/unstacking.py

@@ -8,7 +8,7 @@
 
 class Unstacking:
     def setup(self):
-        data = np.random.RandomState(0).randn(250, 500)
+        data = np.random.default_rng(0).random((250, 500))
         self.da_full = xr.DataArray(data, dims=list("ab")).stack(flat_dim=[...])
         self.da_missing = self.da_full[:-1]
         self.df_missing = self.da_missing.to_pandas()

doc/user-guide/computation.rst

@@ -30,7 +30,8 @@ numpy) over all array values:
 .. ipython:: python
 
     arr = xr.DataArray(
-        np.random.RandomState(0).randn(2, 3), [("x", ["a", "b"]), ("y", [10, 20, 30])]
+        np.random.default_rng(0).random((2, 3)),
+        [("x", ["a", "b"]), ("y", [10, 20, 30])],
     )
     arr - 3
     abs(arr)

doc/user-guide/dask.rst

@@ -292,7 +292,7 @@ work as a streaming operation, when run on arrays loaded from disk:
 .. ipython::
     :verbatim:
 
-    In [56]: rs = np.random.RandomState(0)
+    In [56]: rs = np.random.default_rng(0)
 
     In [57]: array1 = xr.DataArray(rs.randn(1000, 100000), dims=["place", "time"])  # 800MB
 

doc/user-guide/pandas.rst

@@ -202,7 +202,7 @@ Let's take a look:
 
 .. ipython:: python
 
-    data = np.random.RandomState(0).rand(2, 3, 4)
+    data = np.random.default_rng(0).rand(2, 3, 4)
     items = list("ab")
     major_axis = list("mno")
     minor_axis = pd.date_range(start="2000", periods=4, name="date")

xarray/tests/__init__.py

@@ -298,12 +298,12 @@ def assert_allclose(a, b, check_default_indexes=True, **kwargs):
 
 
 def create_test_data(
-    seed: int | None = None,
+    seed: int = 12345,
     add_attrs: bool = True,
     dim_sizes: tuple[int, int, int] = _DEFAULT_TEST_DIM_SIZES,
     use_extension_array: bool = False,
 ) -> Dataset:
-    rs = np.random.RandomState(seed)
+    rs = np.random.default_rng(seed)
     _vars = {
         "var1": ["dim1", "dim2"],
         "var2": ["dim1", "dim2"],
@@ -329,15 +329,15 @@ def create_test_data(
             "dim1",
             pd.Categorical(
                 rs.choice(
-                    list(string.ascii_lowercase[: rs.randint(1, 5)]),
+                    list(string.ascii_lowercase[: rs.integers(1, 5)]),
                     size=dim_sizes[0],
                 )
             ),
         )
     if dim_sizes == _DEFAULT_TEST_DIM_SIZES:
         numbers_values = np.array([0, 1, 2, 0, 0, 1, 1, 2, 2, 3], dtype="int64")
     else:
-        numbers_values = rs.randint(0, 3, _dims["dim3"], dtype="int64")
+        numbers_values = rs.integers(0, 3, _dims["dim3"], dtype="int64")
     obj.coords["numbers"] = ("dim3", numbers_values)
     obj.encoding = {"foo": "bar"}
     assert_writeable(obj)

xarray/tests/test_backends.py

@@ -2868,8 +2868,11 @@ def test_append_with_new_variable(self) -> None:
 
         # check append mode for new variable
         with self.create_zarr_target() as store_target:
-            xr.concat([ds, ds_to_append], dim="time").to_zarr(
-                store_target, mode="w", **self.version_kwargs
+            combined = xr.concat([ds, ds_to_append], dim="time")
+            combined.to_zarr(store_target, mode="w", **self.version_kwargs)
+            assert_identical(
+                combined,
+                xr.open_dataset(store_target, engine="zarr", **self.version_kwargs),
             )
             ds_with_new_var.to_zarr(store_target, mode="a", **self.version_kwargs)
             combined = xr.concat([ds, ds_to_append], dim="time")
@@ -6494,7 +6497,7 @@ def test_zarr_safe_chunk_region(tmp_path):
         arr.isel(a=slice(5, -1)).chunk(a=5).to_zarr(store, region="auto", mode="r+")
 
     # Test if the code is detecting the last chunk correctly
-    data = np.random.RandomState(0).randn(2920, 25, 53)
+    data = np.random.default_rng(0).random((2920, 25, 53))
     ds = xr.Dataset({"temperature": (("time", "lat", "lon"), data)})
     chunks = {"time": 1000, "lat": 25, "lon": 53}
     ds.chunk(chunks).to_zarr(store, compute=False, mode="w")

xarray/tests/test_computation.py

@@ -1293,9 +1293,9 @@ def covariance(x, y):
             (x - x.mean(axis=-1, keepdims=True)) * (y - y.mean(axis=-1, keepdims=True))
         ).mean(axis=-1)
 
-    rs = np.random.RandomState(42)
-    array1 = da.from_array(rs.randn(4, 4), chunks=(2, 4))
-    array2 = da.from_array(rs.randn(4, 4), chunks=(2, 4))
+    rs = np.random.default_rng(42)
+    array1 = da.from_array(rs.random((4, 4)), chunks=(2, 4))
+    array2 = da.from_array(rs.random((4, 4)), chunks=(2, 4))
     data_array_1 = xr.DataArray(array1, dims=("x", "z"))
     data_array_2 = xr.DataArray(array2, dims=("y", "z"))
 

xarray/tests/test_dask.py

@@ -38,7 +38,7 @@
 
 
 def test_raise_if_dask_computes():
-    data = da.from_array(np.random.RandomState(0).randn(4, 6), chunks=(2, 2))
+    data = da.from_array(np.random.default_rng(0).random((4, 6)), chunks=(2, 2))
     with pytest.raises(RuntimeError, match=r"Too many computes"):
         with raise_if_dask_computes():
             data.compute()
@@ -77,7 +77,7 @@ def assertLazyAndAllClose(self, expected, actual):
 
     @pytest.fixture(autouse=True)
     def setUp(self):
-        self.values = np.random.RandomState(0).randn(4, 6)
+        self.values = np.random.default_rng(0).random((4, 6))
         self.data = da.from_array(self.values, chunks=(2, 2))
 
         self.eager_var = Variable(("x", "y"), self.values)