From 4ad583261751afb89d947ce79fd6d3c3252f92a7 Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Mon, 8 May 2023 10:13:28 -0400
Subject: [PATCH 01/14] json

---
 python/cudf/cudf/tests/test_json.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/python/cudf/cudf/tests/test_json.py b/python/cudf/cudf/tests/test_json.py
index 8dcab37d20a..ccf051b581f 100644
--- a/python/cudf/cudf/tests/test_json.py
+++ b/python/cudf/cudf/tests/test_json.py
@@ -32,13 +32,11 @@ def make_numeric_dataframe(nrows, dtype):
 def pdf(request):
     types = NUMERIC_TYPES + DATETIME_TYPES + ["bool"]
     typer = {"col_" + val: val for val in types}
-    ncols = len(types)
     nrows = request.param
 
     # Create a pandas dataframe with random data of mixed types
     test_pdf = pd.DataFrame(
-        [list(range(ncols * i, ncols * (i + 1))) for i in range(nrows)],
-        columns=pd.Index([f"col_{typ}" for typ in types], name="foo"),
+        {f"col_{typ}": np.random.randint(0, nrows, nrows) for typ in types}
     )
     # Delete the name of the column index, and rename the row index
     test_pdf.columns.name = None

From 809cc6e158c8b0c0d0aff7305a19152f12c631f9 Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Tue, 9 May 2023 10:26:43 -0400
Subject: [PATCH 02/14] Start making changes to support np 1.24

---
 python/cudf/cudf/__init__.py              |  2 ++
 python/cudf/cudf/core/column/numerical.py |  4 ++--
 python/cudf/cudf/tests/test_column.py     |  4 ++--
 python/cudf/cudf/tests/test_csv.py        |  6 +++---
 python/cudf/cudf/tests/test_numerical.py  |  6 +++++-
 python/cudf/cudf/tests/test_replace.py    | 13 ++++++++++---
 python/cudf/cudf/utils/queryutils.py      |  2 +-
 7 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/python/cudf/cudf/__init__.py b/python/cudf/cudf/__init__.py
index 06310e278a2..48e622acc07 100644
--- a/python/cudf/cudf/__init__.py
+++ b/python/cudf/cudf/__init__.py
@@ -85,6 +85,7 @@
 
 try:
     from cubinlinker.patch import patch_numba_linker_if_needed
+    from ptxcompiler.patch import patch_numba_codegen_if_needed
 except ImportError:
     pass
 else:
@@ -96,6 +97,7 @@
 
     _setup_numba_linker(_PTX_FILE)
 
+    patch_numba_codegen_if_needed()
     del patch_numba_linker_if_needed
 
 cuda.set_memory_manager(RMMNumbaManager)
diff --git a/python/cudf/cudf/core/column/numerical.py b/python/cudf/cudf/core/column/numerical.py
index 87e73d212ef..a35efbb6ac2 100644
--- a/python/cudf/cudf/core/column/numerical.py
+++ b/python/cudf/cudf/core/column/numerical.py
@@ -767,8 +767,8 @@ def _normalize_find_and_replace_input(
             if cudf._lib.scalar._is_null_host_scalar(col_to_normalize[0]):
                 return normalized_column.astype(input_column_dtype)
             else:
-                col_to_normalize_casted = input_column_dtype.type(
-                    col_to_normalize[0]
+                col_to_normalize_casted = np.array(col_to_normalize[0]).astype(
+                    input_column_dtype
                 )
             if not np.isnan(col_to_normalize_casted) and (
                 col_to_normalize_casted != col_to_normalize[0]
diff --git a/python/cudf/cudf/tests/test_column.py b/python/cudf/cudf/tests/test_column.py
index a15afa727c0..db0446d506c 100644
--- a/python/cudf/cudf/tests/test_column.py
+++ b/python/cudf/cudf/tests/test_column.py
@@ -398,8 +398,8 @@ def test_column_view_string_slice(slc):
             cudf.core.column.as_column([], dtype="uint8"),
         ),
         (
-            cp.array([453], dtype="uint8"),
-            cudf.core.column.as_column([453], dtype="uint8"),
+            cp.array([255], dtype="uint8"),
+            cudf.core.column.as_column([255], dtype="uint8"),
         ),
     ],
 )
diff --git a/python/cudf/cudf/tests/test_csv.py b/python/cudf/cudf/tests/test_csv.py
index 4a7804da62c..25f173aeac7 100644
--- a/python/cudf/cudf/tests/test_csv.py
+++ b/python/cudf/cudf/tests/test_csv.py
@@ -150,8 +150,8 @@ def make_all_numeric_extremes_dataframe():
         np_type = pdf_dtypes[gdf_dtype]
         if np.issubdtype(np_type, np.integer):
             itype = np.iinfo(np_type)
-            extremes = [0, +1, -1, itype.min, itype.max]
-            df[gdf_dtype] = np.array(extremes * 4, dtype=np_type)[:20]
+            extremes = [itype.min, itype.max]
+            df[gdf_dtype] = np.array(extremes * 10, dtype=np_type)[:20]
         else:
             ftype = np.finfo(np_type)
             extremes = [
@@ -1433,7 +1433,7 @@ def test_csv_reader_hexadecimal_overflow(np_dtype, gdf_dtype):
 
     gdf = read_csv(StringIO(buffer), dtype=[gdf_dtype], names=["hex_int"])
 
-    expected = np.array(values, dtype=np_dtype)
+    expected = np.array(values).astype(np_dtype)
     actual = gdf["hex_int"].to_numpy()
     np.testing.assert_array_equal(expected, actual)
 
diff --git a/python/cudf/cudf/tests/test_numerical.py b/python/cudf/cudf/tests/test_numerical.py
index e2fbd55c051..5bb55c164fe 100644
--- a/python/cudf/cudf/tests/test_numerical.py
+++ b/python/cudf/cudf/tests/test_numerical.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2021-2022, NVIDIA CORPORATION.
+# Copyright (c) 2021-2023, NVIDIA CORPORATION.
 
 import numpy as np
 import pandas as pd
@@ -194,6 +194,7 @@ def test_to_numeric_downcast_int(data, downcast):
     assert_eq(expected, got)
 
 
+@pytest.mark.filterwarnings("ignore:invalid value encountered in cast")
 @pytest.mark.parametrize(
     "data",
     [
@@ -223,6 +224,7 @@ def test_to_numeric_downcast_float(data, downcast):
     assert_eq(expected, got)
 
 
+@pytest.mark.filterwarnings("ignore:invalid value encountered in cast")
 @pytest.mark.parametrize(
     "data",
     [
@@ -245,6 +247,7 @@ def test_to_numeric_downcast_large_float(data, downcast):
     assert_eq(expected, got)
 
 
+@pytest.mark.filterwarnings("ignore:overflow encountered in cast")
 @pytest.mark.parametrize(
     "data",
     [
@@ -325,6 +328,7 @@ def test_to_numeric_downcast_string_float(data, downcast):
     assert_eq(expected, got)
 
 
+@pytest.mark.filterwarnings("ignore:overflow encountered in cast")
 @pytest.mark.parametrize(
     "data",
     [
diff --git a/python/cudf/cudf/tests/test_replace.py b/python/cudf/cudf/tests/test_replace.py
index 9e93dd6d227..13e44e7cf59 100644
--- a/python/cudf/cudf/tests/test_replace.py
+++ b/python/cudf/cudf/tests/test_replace.py
@@ -944,8 +944,15 @@ def test_numeric_series_replace_dtype(series_dtype, replacement):
     psr = pd.Series([0, 1, 2, 3, 4, 5], dtype=series_dtype)
     sr = cudf.from_pandas(psr)
 
+    if sr.dtype.kind in "ui":
+        can_replace = np.array([replacement])[0].is_integer() and np.can_cast(
+            int(replacement), sr.dtype
+        )
+    else:
+        can_replace = np.can_cast(replacement, sr.dtype)
+
     # Both Scalar
-    if sr.dtype.type(replacement) != replacement:
+    if not can_replace:
         with pytest.raises(TypeError):
             sr.replace(1, replacement)
     else:
@@ -954,7 +961,7 @@ def test_numeric_series_replace_dtype(series_dtype, replacement):
         assert_eq(expect, got)
 
     # to_replace is a list, replacement is a scalar
-    if sr.dtype.type(replacement) != replacement:
+    if not can_replace:
         with pytest.raises(TypeError):
 
             sr.replace([2, 3], replacement)
@@ -974,7 +981,7 @@ def test_numeric_series_replace_dtype(series_dtype, replacement):
     # Both lists of equal length
     if (
         np.dtype(type(replacement)).kind == "f" and sr.dtype.kind in {"i", "u"}
-    ) or (sr.dtype.type(replacement) != replacement):
+    ) or (not can_replace):
         with pytest.raises(TypeError):
             sr.replace([2, 3], [replacement, replacement])
     else:
diff --git a/python/cudf/cudf/utils/queryutils.py b/python/cudf/cudf/utils/queryutils.py
index 4ce89b526d6..aecbe4fd659 100644
--- a/python/cudf/cudf/utils/queryutils.py
+++ b/python/cudf/cudf/utils/queryutils.py
@@ -137,7 +137,7 @@ def query_compile(expr):
         key "args" is a sequence of name of the arguments.
     """
 
-    funcid = f"queryexpr_{np.uintp(hash(expr)):x}"
+    funcid = f"queryexpr_{np.uintp(abs(hash(expr))):x}"
     # Load cache
     compiled = _cache.get(funcid)
     # Cache not found

From 4e4ad8285e501e4a459dadf8dd56a96149e9e0e7 Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Wed, 10 May 2023 08:35:40 -0400
Subject: [PATCH 03/14] More

---
 python/cudf/cudf/tests/test_feather.py   |  9 +--------
 python/cudf/cudf/tests/test_parquet.py   | 17 ++---------------
 python/cudf/cudf/tests/test_rank.py      | 13 ++++++-------
 python/cudf/cudf/tests/test_sparse_df.py |  4 ++--
 python/cudf/cudf/tests/test_unaops.py    |  8 ++++++--
 5 files changed, 17 insertions(+), 34 deletions(-)

diff --git a/python/cudf/cudf/tests/test_feather.py b/python/cudf/cudf/tests/test_feather.py
index 6cdf47ed948..83aaf0a4407 100644
--- a/python/cudf/cudf/tests/test_feather.py
+++ b/python/cudf/cudf/tests/test_feather.py
@@ -15,23 +15,16 @@
 @pytest.fixture(params=[0, 1, 10, 100])
 def pdf(request):
     types = NUMERIC_TYPES + ["bool"]
-    typer = {"col_" + val: val for val in types}
-    ncols = len(types)
     nrows = request.param
 
     # Create a pandas dataframe with random data of mixed types
     test_pdf = pd.DataFrame(
-        [list(range(ncols * i, ncols * (i + 1))) for i in range(nrows)],
-        columns=pd.Index([f"col_{typ}" for typ in types], name="foo"),
+        {f"col_{typ}": np.random.randint(0, nrows, nrows) for typ in types}
     )
     # Delete the name of the column index, and rename the row index
     test_pdf.columns.name = None
     test_pdf.index.name = "index"
 
-    # Cast all the column dtypes to objects, rename them, and then cast to
-    # appropriate types
-    test_pdf = test_pdf.astype("object").astype(typer)
-
     # Create non-numeric categorical data otherwise may get typecasted
     data = [ascii_letters[np.random.randint(0, 52)] for i in range(nrows)]
     test_pdf["col_category"] = pd.Series(data, dtype="category")
diff --git a/python/cudf/cudf/tests/test_parquet.py b/python/cudf/cudf/tests/test_parquet.py
index c24ff080033..3d3e731e7e6 100644
--- a/python/cudf/cudf/tests/test_parquet.py
+++ b/python/cudf/cudf/tests/test_parquet.py
@@ -69,14 +69,11 @@ def simple_pdf(request):
         "float32",
         "float64",
     ]
-    typer = {"col_" + val: val for val in types}
-    ncols = len(types)
     nrows = request.param
 
     # Create a pandas dataframe with random data of mixed types
     test_pdf = pd.DataFrame(
-        [list(range(ncols * i, ncols * (i + 1))) for i in range(nrows)],
-        columns=pd.Index([f"col_{typ}" for typ in types], name="foo"),
+        {f"col_{typ}": np.random.randint(0, nrows, nrows) for typ in types},
         # Need to ensure that this index is not a RangeIndex to get the
         # expected round-tripping behavior from Parquet reader/writer.
         index=pd.Index(list(range(nrows))),
@@ -85,10 +82,6 @@ def simple_pdf(request):
     test_pdf.columns.name = None
     test_pdf.index.name = "test_index"
 
-    # Cast all the column dtypes to objects, rename them, and then cast to
-    # appropriate types
-    test_pdf = test_pdf.astype("object").astype(typer)
-
     return test_pdf
 
 
@@ -115,13 +108,11 @@ def build_pdf(num_columns, day_resolution_timestamps):
         "datetime64[us]",
         "str",
     ]
-    typer = {"col_" + val: val for val in types}
-    ncols = len(types)
     nrows = num_columns.param
 
     # Create a pandas dataframe with random data of mixed types
     test_pdf = pd.DataFrame(
-        [list(range(ncols * i, ncols * (i + 1))) for i in range(nrows)],
+        {f"col_{typ}": np.random.randint(0, nrows, nrows) for typ in types},
         columns=pd.Index([f"col_{typ}" for typ in types], name="foo"),
         # Need to ensure that this index is not a RangeIndex to get the
         # expected round-tripping behavior from Parquet reader/writer.
@@ -131,10 +122,6 @@ def build_pdf(num_columns, day_resolution_timestamps):
     test_pdf.columns.name = None
     test_pdf.index.name = "test_index"
 
-    # Cast all the column dtypes to objects, rename them, and then cast to
-    # appropriate types
-    test_pdf = test_pdf.astype(typer)
-
     # make datetime64's a little more interesting by increasing the range of
     # dates note that pandas will convert these to ns timestamps, so care is
     # taken to avoid overflowing a ns timestamp. There is also the ability to
diff --git a/python/cudf/cudf/tests/test_rank.py b/python/cudf/cudf/tests/test_rank.py
index 9bd67309ece..0bccf02ce3c 100644
--- a/python/cudf/cudf/tests/test_rank.py
+++ b/python/cudf/cudf/tests/test_rank.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2020-2022, NVIDIA CORPORATION.
+# Copyright (c) 2020-2023, NVIDIA CORPORATION.
 
 from itertools import chain, combinations_with_replacement, product
 
@@ -125,7 +125,7 @@ def test_rank_error_arguments(pdf):
     np.full((3,), np.inf),
     np.full((3,), -np.inf),
 ]
-sort_dtype_args = [np.int32, np.int64, np.float32, np.float64]
+sort_dtype_args = [np.float32, np.float64]
 
 
 @pytest.mark.parametrize(
@@ -139,13 +139,12 @@ def test_rank_error_arguments(pdf):
 )
 def test_series_rank_combinations(elem, dtype):
     np.random.seed(0)
+    aa = np.fromiter(chain.from_iterable(elem), dtype=dtype)
     gdf = DataFrame()
-    gdf["a"] = aa = np.fromiter(chain.from_iterable(elem), np.float64).astype(
-        dtype
-    )
-    ranked_gs = gdf["a"].rank(method="first")
     df = pd.DataFrame()
+    gdf["a"] = aa
     df["a"] = aa
+    ranked_gs = gdf["a"].rank(method="first")
     ranked_ps = df["a"].rank(method="first")
     # Check
-    assert_eq(ranked_ps, ranked_gs.to_pandas())
+    assert_eq(ranked_ps, ranked_gs)
diff --git a/python/cudf/cudf/tests/test_sparse_df.py b/python/cudf/cudf/tests/test_sparse_df.py
index 0dd47c219c0..3248e7f72c0 100644
--- a/python/cudf/cudf/tests/test_sparse_df.py
+++ b/python/cudf/cudf/tests/test_sparse_df.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2018-2022, NVIDIA CORPORATION.
+# Copyright (c) 2018-2023, NVIDIA CORPORATION.
 
 import numpy as np
 
@@ -7,7 +7,7 @@
 
 def test_to_dense_array():
     data = np.random.random(8)
-    mask = np.asarray([0b11010110], dtype=np.byte)
+    mask = np.asarray([0b11010110]).astype(np.byte)
 
     sr = Series.from_masked_array(data=data, mask=mask, null_count=3)
     assert sr.has_nulls
diff --git a/python/cudf/cudf/tests/test_unaops.py b/python/cudf/cudf/tests/test_unaops.py
index 3f2f2072758..f821b06e07b 100644
--- a/python/cudf/cudf/tests/test_unaops.py
+++ b/python/cudf/cudf/tests/test_unaops.py
@@ -1,4 +1,4 @@
-# Copyright (c) 2019-2022, NVIDIA CORPORATION.
+# Copyright (c) 2019-2023, NVIDIA CORPORATION.
 
 import itertools
 import operator
@@ -79,9 +79,13 @@ def generate_valid_scalar_unaop_combos():
 
 @pytest.mark.parametrize("slr,dtype,op", generate_valid_scalar_unaop_combos())
 def test_scalar_unary_operations(slr, dtype, op):
-    slr_host = cudf.dtype(dtype).type(slr)
+    slr_host = np.array([slr])[0].astype(cudf.dtype(dtype))
     slr_device = cudf.Scalar(slr, dtype=dtype)
 
+    if op.__name__ == "neg" and np.dtype(dtype).kind == "u":
+        # TODO: what do we want to do here?
+        return
+
     expect = op(slr_host)
     got = op(slr_device)
 

From b94427fa081f5d31ad9379bfa684c64c1ea5148d Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Thu, 11 May 2023 14:51:28 -0400
Subject: [PATCH 04/14] Special-case inf

---
 python/cudf/cudf/core/column/numerical.py | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/python/cudf/cudf/core/column/numerical.py b/python/cudf/cudf/core/column/numerical.py
index a35efbb6ac2..406c4836c5b 100644
--- a/python/cudf/cudf/core/column/numerical.py
+++ b/python/cudf/cudf/core/column/numerical.py
@@ -766,10 +766,12 @@ def _normalize_find_and_replace_input(
         if len(col_to_normalize) == 1:
             if cudf._lib.scalar._is_null_host_scalar(col_to_normalize[0]):
                 return normalized_column.astype(input_column_dtype)
-            else:
-                col_to_normalize_casted = np.array(col_to_normalize[0]).astype(
-                    input_column_dtype
-                )
+            if np.isinf(col_to_normalize[0]):
+                return normalized_column
+            col_to_normalize_casted = np.array(col_to_normalize[0]).astype(
+                input_column_dtype
+            )
+
             if not np.isnan(col_to_normalize_casted) and (
                 col_to_normalize_casted != col_to_normalize[0]
             ):

From ba3ede72352f20b2042ea3354d9560ce1469513a Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Thu, 11 May 2023 17:54:25 -0400
Subject: [PATCH 05/14] Remove numpy upper bounds

---
 conda/environments/all_cuda-118_arch-x86_64.yaml | 1 +
 conda/recipes/cudf/meta.yaml                     | 2 +-
 dependencies.yaml                                | 2 +-
 python/cudf/pyproject.toml                       | 2 +-
 python/cudf_kafka/pyproject.toml                 | 2 +-
 5 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/conda/environments/all_cuda-118_arch-x86_64.yaml b/conda/environments/all_cuda-118_arch-x86_64.yaml
index 4031f1aa1c3..56463ad87cc 100644
--- a/conda/environments/all_cuda-118_arch-x86_64.yaml
+++ b/conda/environments/all_cuda-118_arch-x86_64.yaml
@@ -49,6 +49,7 @@ dependencies:
 - ninja
 - notebook
 - numba>=0.56.4,<0.57
+- numpy>=1.21
 - numpy>=1.21,<1.24
 - numpydoc
 - nvcc_linux-64=11.8
diff --git a/conda/recipes/cudf/meta.yaml b/conda/recipes/cudf/meta.yaml
index f8074711b88..327f7f90a82 100644
--- a/conda/recipes/cudf/meta.yaml
+++ b/conda/recipes/cudf/meta.yaml
@@ -66,7 +66,7 @@ requirements:
     - pandas >=1.3,<1.6.0dev0
     - cupy >=12.0.0
     - numba >=0.56.4,<0.57
-    - numpy >=1.21,<1.24  # Temporarily upper bound numpy to avoid overflow deprecations
+    - numpy >=1.21
     - {{ pin_compatible('pyarrow', max_pin='x.x.x') }}
     - libcudf {{ version }}
     - fastavro >=0.22.0
diff --git a/dependencies.yaml b/dependencies.yaml
index 70d7f8c1ec8..b78766f6743 100644
--- a/dependencies.yaml
+++ b/dependencies.yaml
@@ -234,7 +234,7 @@ dependencies:
           # Hard pin the patch version used during the build. This must be kept
           # in sync with the version pinned in get_arrow.cmake.
           - pyarrow==11.0.0.*
-          - numpy>=1.21,<1.24  # Temporarily upper bound numpy to avoid overflow deprecations
+          - numpy>=1.21
   build_python:
     common:
       - output_types: [conda, requirements, pyproject]
diff --git a/python/cudf/pyproject.toml b/python/cudf/pyproject.toml
index d13324a7404..3685e4965a1 100644
--- a/python/cudf/pyproject.toml
+++ b/python/cudf/pyproject.toml
@@ -6,7 +6,7 @@ requires = [
     "cmake>=3.23.1,!=3.25.0",
     "cython>=0.29,<0.30",
     "ninja",
-    "numpy>=1.21,<1.24",
+    "numpy>=1.21",
     "protoc-wheel",
     "pyarrow==11.0.0.*",
     "rmm==23.6.*",
diff --git a/python/cudf_kafka/pyproject.toml b/python/cudf_kafka/pyproject.toml
index df0825c846a..d8b97f52864 100644
--- a/python/cudf_kafka/pyproject.toml
+++ b/python/cudf_kafka/pyproject.toml
@@ -4,7 +4,7 @@
 
 requires = [
     "cython>=0.29,<0.30",
-    "numpy>=1.21,<1.24",
+    "numpy>=1.21",
     "pyarrow==11.0.0.*",
     "setuptools",
     "wheel",

From f884eb768d65f818403c8af4b4e59a05bf538e36 Mon Sep 17 00:00:00 2001
From: Vyas Ramasubramani <vyasr@nvidia.com>
Date: Thu, 11 May 2023 15:32:19 -0700
Subject: [PATCH 06/14] One more place to unpin numpy

---
 conda/environments/all_cuda-118_arch-x86_64.yaml | 1 -
 dependencies.yaml                                | 2 +-
 python/cudf/pyproject.toml                       | 2 +-
 python/dask_cudf/pyproject.toml                  | 2 +-
 4 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/conda/environments/all_cuda-118_arch-x86_64.yaml b/conda/environments/all_cuda-118_arch-x86_64.yaml
index 56463ad87cc..e0980d7263c 100644
--- a/conda/environments/all_cuda-118_arch-x86_64.yaml
+++ b/conda/environments/all_cuda-118_arch-x86_64.yaml
@@ -50,7 +50,6 @@ dependencies:
 - notebook
 - numba>=0.56.4,<0.57
 - numpy>=1.21
-- numpy>=1.21,<1.24
 - numpydoc
 - nvcc_linux-64=11.8
 - nvtx>=0.2.1
diff --git a/dependencies.yaml b/dependencies.yaml
index b78766f6743..d7c847ed1f7 100644
--- a/dependencies.yaml
+++ b/dependencies.yaml
@@ -342,7 +342,7 @@ dependencies:
       - output_types: [conda, requirements, pyproject]
         packages:
           - fsspec>=0.6.0
-          - numpy>=1.21,<1.24  # Temporarily upper bound numpy to avoid overflow deprecations
+          - numpy>=1.21
           - pandas>=1.3,<1.6.0dev0
   run_cudf:
     common:
diff --git a/python/cudf/pyproject.toml b/python/cudf/pyproject.toml
index 3685e4965a1..2a686fe3016 100644
--- a/python/cudf/pyproject.toml
+++ b/python/cudf/pyproject.toml
@@ -32,7 +32,7 @@ dependencies = [
     "cupy-cuda11x>=12.0.0",
     "fsspec>=0.6.0",
     "numba>=0.56.4,<0.57",
-    "numpy>=1.21,<1.24",
+    "numpy>=1.21",
     "nvtx>=0.2.1",
     "packaging",
     "pandas>=1.3,<1.6.0dev0",
diff --git a/python/dask_cudf/pyproject.toml b/python/dask_cudf/pyproject.toml
index ff2a3f2d095..c6c43661e9e 100644
--- a/python/dask_cudf/pyproject.toml
+++ b/python/dask_cudf/pyproject.toml
@@ -23,7 +23,7 @@ dependencies = [
     "dask==2023.3.2",
     "distributed==2023.3.2.1",
     "fsspec>=0.6.0",
-    "numpy>=1.21,<1.24",
+    "numpy>=1.21",
     "pandas>=1.3,<1.6.0dev0",
 ] # This list was generated by `rapids-dependency-file-generator`. To make changes, edit ../../dependencies.yaml and run `rapids-dependency-file-generator`.
 classifiers = [

From 42d6a74736c947ceb78a6f3d82e0abce92a32907 Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Mon, 15 May 2023 07:46:46 -0400
Subject: [PATCH 07/14] filter warning

---
 python/cudf/cudf/tests/test_csv.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/python/cudf/cudf/tests/test_csv.py b/python/cudf/cudf/tests/test_csv.py
index 25f173aeac7..4a7502f729a 100644
--- a/python/cudf/cudf/tests/test_csv.py
+++ b/python/cudf/cudf/tests/test_csv.py
@@ -150,8 +150,8 @@ def make_all_numeric_extremes_dataframe():
         np_type = pdf_dtypes[gdf_dtype]
         if np.issubdtype(np_type, np.integer):
             itype = np.iinfo(np_type)
-            extremes = [itype.min, itype.max]
-            df[gdf_dtype] = np.array(extremes * 10, dtype=np_type)[:20]
+            extremes = [0, +1, -1, itype.min, itype.max]
+            df[gdf_dtype] = np.array(extremes * 4).astype(np_type)[:20]
         else:
             ftype = np.finfo(np_type)
             extremes = [
@@ -324,6 +324,7 @@ def test_csv_reader_dtype_dict(use_names):
     assert_eq(gdf, pdf)
 
 
+@pytest.mark.filterwarnings("ignore:invalid value encountered in cast")
 @pytest.mark.parametrize("use_names", [True, False])
 def test_csv_reader_dtype_extremes(use_names):
     # Save with the column header if not explicitly specifying a list of names

From d75986b63ca7f001d101c6a3ac0b5a8d0a619ecc Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Mon, 15 May 2023 07:50:39 -0400
Subject: [PATCH 08/14] Actually cast columns

---
 python/cudf/cudf/tests/test_feather.py |  5 ++++-
 python/cudf/cudf/tests/test_json.py    | 10 ++++------
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/python/cudf/cudf/tests/test_feather.py b/python/cudf/cudf/tests/test_feather.py
index 83aaf0a4407..12a325fa4e8 100644
--- a/python/cudf/cudf/tests/test_feather.py
+++ b/python/cudf/cudf/tests/test_feather.py
@@ -19,7 +19,10 @@ def pdf(request):
 
     # Create a pandas dataframe with random data of mixed types
     test_pdf = pd.DataFrame(
-        {f"col_{typ}": np.random.randint(0, nrows, nrows) for typ in types}
+        {
+            f"col_{typ}": np.random.randint(0, nrows, nrows).astype(typ)
+            for typ in types
+        }
     )
     # Delete the name of the column index, and rename the row index
     test_pdf.columns.name = None
diff --git a/python/cudf/cudf/tests/test_json.py b/python/cudf/cudf/tests/test_json.py
index ccf051b581f..43b0ca0119a 100644
--- a/python/cudf/cudf/tests/test_json.py
+++ b/python/cudf/cudf/tests/test_json.py
@@ -31,21 +31,19 @@ def make_numeric_dataframe(nrows, dtype):
 @pytest.fixture(params=[0, 1, 10, 100])
 def pdf(request):
     types = NUMERIC_TYPES + DATETIME_TYPES + ["bool"]
-    typer = {"col_" + val: val for val in types}
     nrows = request.param
 
     # Create a pandas dataframe with random data of mixed types
     test_pdf = pd.DataFrame(
-        {f"col_{typ}": np.random.randint(0, nrows, nrows) for typ in types}
+        {
+            f"col_{typ}": np.random.randint(0, nrows, nrows).astype(typ)
+            for typ in types
+        }
     )
     # Delete the name of the column index, and rename the row index
     test_pdf.columns.name = None
     test_pdf.index.name = "test_index"
 
-    # Cast all the column dtypes to objects, rename them, and then cast to
-    # appropriate types
-    test_pdf = test_pdf.astype("object").astype(typer)
-
     return test_pdf
 
 

From 2dfb93969701c9f08f7663c1c7d7b97e42941a01 Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Mon, 15 May 2023 08:06:42 -0400
Subject: [PATCH 09/14] Fix parquet casting

---
 python/cudf/cudf/tests/test_parquet.py | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/python/cudf/cudf/tests/test_parquet.py b/python/cudf/cudf/tests/test_parquet.py
index c41e5d16b2b..ebd226402c0 100644
--- a/python/cudf/cudf/tests/test_parquet.py
+++ b/python/cudf/cudf/tests/test_parquet.py
@@ -73,7 +73,10 @@ def simple_pdf(request):
 
     # Create a pandas dataframe with random data of mixed types
     test_pdf = pd.DataFrame(
-        {f"col_{typ}": np.random.randint(0, nrows, nrows) for typ in types},
+        {
+            f"col_{typ}": np.random.randint(0, nrows, nrows).astype(typ)
+            for typ in types
+        },
         # Need to ensure that this index is not a RangeIndex to get the
         # expected round-tripping behavior from Parquet reader/writer.
         index=pd.Index(list(range(nrows))),
@@ -112,8 +115,10 @@ def build_pdf(num_columns, day_resolution_timestamps):
 
     # Create a pandas dataframe with random data of mixed types
     test_pdf = pd.DataFrame(
-        {f"col_{typ}": np.random.randint(0, nrows, nrows) for typ in types},
-        columns=pd.Index([f"col_{typ}" for typ in types], name="foo"),
+        {
+            f"col_{typ}": np.random.randint(0, nrows, nrows).astype(typ)
+            for typ in types
+        },
         # Need to ensure that this index is not a RangeIndex to get the
         # expected round-tripping behavior from Parquet reader/writer.
         index=pd.Index(list(range(nrows))),

From 860f4396d8911353d2783f56749ffee3d86fe77c Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Mon, 15 May 2023 12:38:49 -0400
Subject: [PATCH 10/14] Use a filterwarning instead

---
 python/cudf/cudf/tests/test_rank.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/python/cudf/cudf/tests/test_rank.py b/python/cudf/cudf/tests/test_rank.py
index 0bccf02ce3c..f8a8903b518 100644
--- a/python/cudf/cudf/tests/test_rank.py
+++ b/python/cudf/cudf/tests/test_rank.py
@@ -125,9 +125,10 @@ def test_rank_error_arguments(pdf):
     np.full((3,), np.inf),
     np.full((3,), -np.inf),
 ]
-sort_dtype_args = [np.float32, np.float64]
+sort_dtype_args = [np.int32, np.int64, np.float32, np.float64]
 
 
+@pytest.mark.filterwarnings("ignore:invalid value encountered in cast")
 @pytest.mark.parametrize(
     "elem,dtype",
     list(
@@ -139,7 +140,7 @@ def test_rank_error_arguments(pdf):
 )
 def test_series_rank_combinations(elem, dtype):
     np.random.seed(0)
-    aa = np.fromiter(chain.from_iterable(elem), dtype=dtype)
+    aa = np.fromiter(chain.from_iterable(elem), np.float64).astype(dtype)
     gdf = DataFrame()
     df = pd.DataFrame()
     gdf["a"] = aa

From 8221628529eabf211d6d5695e2b65bf552b161b2 Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Mon, 15 May 2023 12:43:02 -0400
Subject: [PATCH 11/14] More filterwarnings

---
 python/cudf/cudf/tests/test_unaops.py | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/python/cudf/cudf/tests/test_unaops.py b/python/cudf/cudf/tests/test_unaops.py
index f821b06e07b..a7502051a78 100644
--- a/python/cudf/cudf/tests/test_unaops.py
+++ b/python/cudf/cudf/tests/test_unaops.py
@@ -77,15 +77,12 @@ def generate_valid_scalar_unaop_combos():
     return results
 
 
+@pytest.mark.filterwarnings("ignore:overflow encountered in scalar negative")
 @pytest.mark.parametrize("slr,dtype,op", generate_valid_scalar_unaop_combos())
 def test_scalar_unary_operations(slr, dtype, op):
     slr_host = np.array([slr])[0].astype(cudf.dtype(dtype))
     slr_device = cudf.Scalar(slr, dtype=dtype)
 
-    if op.__name__ == "neg" and np.dtype(dtype).kind == "u":
-        # TODO: what do we want to do here?
-        return
-
     expect = op(slr_host)
     got = op(slr_device)
 

From abdc0268dee772802ae2b9bf08a4925b13381af0 Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Mon, 15 May 2023 12:52:10 -0400
Subject: [PATCH 12/14] Shift, not abs

---
 python/cudf/cudf/utils/queryutils.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/python/cudf/cudf/utils/queryutils.py b/python/cudf/cudf/utils/queryutils.py
index aecbe4fd659..bc0ac9fb390 100644
--- a/python/cudf/cudf/utils/queryutils.py
+++ b/python/cudf/cudf/utils/queryutils.py
@@ -137,7 +137,8 @@ def query_compile(expr):
         key "args" is a sequence of name of the arguments.
     """
 
-    funcid = f"queryexpr_{np.uintp(abs(hash(expr))):x}"
+    # hash returns in the semi-open interval [-2**63, 2**63)
+    funcid = f"queryexpr_{(hash(expr) + 2**63):x}"
     # Load cache
     compiled = _cache.get(funcid)
     # Cache not found

From 37c9514a58102479e32de969fb332395037b12d4 Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Mon, 15 May 2023 15:37:45 -0400
Subject: [PATCH 13/14] More filterwarnings

---
 python/cudf/cudf/tests/test_csv.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/python/cudf/cudf/tests/test_csv.py b/python/cudf/cudf/tests/test_csv.py
index 4a7502f729a..b34340295f2 100644
--- a/python/cudf/cudf/tests/test_csv.py
+++ b/python/cudf/cudf/tests/test_csv.py
@@ -2150,6 +2150,7 @@ def test_default_integer_bitwidth_partial(
     )
 
 
+@pytest.mark.filterwarnings("ignore:invalid value encountered in cast")
 def test_default_integer_bitwidth_extremes(
     cudf_extreme_numeric_dataframe, default_integer_bitwidth
 ):

From e4b43ac6acca9213742260c0c7055c4a83e2454c Mon Sep 17 00:00:00 2001
From: Ashwin Srinath <shwina@users.noreply.github.com>
Date: Wed, 24 May 2023 15:27:30 -0400
Subject: [PATCH 14/14] Style

---
 python/cudf/cudf/__init__.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/python/cudf/cudf/__init__.py b/python/cudf/cudf/__init__.py
index 137419b30a6..de0f2d67add 100644
--- a/python/cudf/cudf/__init__.py
+++ b/python/cudf/cudf/__init__.py
@@ -88,7 +88,6 @@
 from cudf.utils.dtypes import _NA_REP
 from cudf.utils.utils import clear_cache, set_allocator
 
-
 cuda.set_memory_manager(RMMNumbaManager)
 cupy.cuda.set_allocator(rmm_cupy_allocator)