apacheGH-37333: [Python] Replace pandas.util.testing.rands with vendo…

…red version (apache#42089) ### Rationale for this change Fixes apache#37333. ### What changes are included in this PR? - Replaces the calls to `pandas.util.testing.rands` with existing `pyarrow.tests.util.rands` - Updated benchmarks.rst to remove a mention of the now-deprecated `asv dev` command. ### Are these changes tested? I tested locally in a freshly-created python venv and a conda environment and the benchmarks run without error. ### Are there any user-facing changes? No. * GitHub Issue: apache#37333 Authored-by: Bryce Mecum <[email protected]> Signed-off-by: Joris Van den Bossche <[email protected]>
assignUser · Jun 12, 2024 · 383ffe0 · 383ffe0
1 parent 832880a
commit 383ffe0
Show file tree

Hide file tree

Showing 4 changed files with 4 additions and 6 deletions.
diff --git a/docs/source/python/benchmarks.rst b/docs/source/python/benchmarks.rst
@@ -27,8 +27,7 @@ run with `ASV`_.  You'll need to install the ``asv`` package first
 Running the benchmarks
 ----------------------
 
-To run the benchmarks for a locally-built Arrow, run ``asv dev`` or
-``asv run --python=same``.
+To run the benchmarks for a locally-built Arrow, run ``asv run --python=same``.
 
 We use conda environments as part of running the benchmarks. To use the ``asv``
 setup, you must set the ``$CONDA_HOME`` environment variable to point to the

diff --git a/python/benchmarks/common.py b/python/benchmarks/common.py
@@ -26,7 +26,6 @@
 
 import pyarrow as pa
 
-
 KILOBYTE = 1 << 10
 MEGABYTE = KILOBYTE * KILOBYTE
 

diff --git a/python/benchmarks/convert_pandas.py b/python/benchmarks/convert_pandas.py
@@ -17,9 +17,9 @@
 
 import numpy as np
 import pandas as pd
-import pandas.util.testing as tm
 
 import pyarrow as pa
+from pyarrow.tests.util import rands
 
 
 class PandasConversionsBase(object):
@@ -60,7 +60,7 @@ class ToPandasStrings(object):
 
     def setup(self, uniqueness, total):
         nunique = int(total * uniqueness)
-        unique_values = [tm.rands(self.string_length) for i in range(nunique)]
+        unique_values = [rands(self.string_length) for i in range(nunique)]
         values = unique_values * (total // nunique)
         self.arr = pa.array(values, type=pa.string())
         self.table = pa.Table.from_arrays([self.arr], ['f0'])

diff --git a/python/benchmarks/parquet.py b/python/benchmarks/parquet.py
@@ -15,14 +15,14 @@
 # specific language governing permissions and limitations
 # under the License.
 
-from pandas.util.testing import rands
 import numpy as np
 
 import pyarrow as pa
 try:
     import pyarrow.parquet as pq
 except ImportError:
     pq = None
+from pyarrow.tests.util import rands
 
 
 class ParquetWriteBinary(object):