This is an automated email from the ASF dual-hosted git repository.

jorisvandenbossche pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git


The following commit(s) were added to refs/heads/main by this push:
     new 5c772af5c6 GH-35845: [CI][Python] Fix usage of assert_frame_equal in 
test_hdfs.py (#35842)
5c772af5c6 is described below

commit 5c772af5c6684dfcd70fc9bf7f7e96a98b93c580
Author: Joris Van den Bossche <[email protected]>
AuthorDate: Wed May 31 16:02:31 2023 +0200

    GH-35845: [CI][Python] Fix usage of assert_frame_equal in test_hdfs.py 
(#35842)
    
    _add empty comment_
    * Closes: #35845
    
    Authored-by: Joris Van den Bossche <[email protected]>
    Signed-off-by: Joris Van den Bossche <[email protected]>
---
 python/pyarrow/pandas-shim.pxi    |  4 ----
 python/pyarrow/tests/test_hdfs.py | 27 +++++++++++++++------------
 2 files changed, 15 insertions(+), 16 deletions(-)

diff --git a/python/pyarrow/pandas-shim.pxi b/python/pyarrow/pandas-shim.pxi
index f7e0ceccbd..7dc5d590a7 100644
--- a/python/pyarrow/pandas-shim.pxi
+++ b/python/pyarrow/pandas-shim.pxi
@@ -225,10 +225,6 @@ cdef class _PandasAPIShim(object):
             return obj.array
         return obj.values
 
-    def assert_frame_equal(self, *args, **kwargs):
-        self._check_import()
-        return self._pd.util.testing.assert_frame_equal
-
     def get_rangeindex_attribute(self, level, name):
         # public start/stop/step attributes added in pandas 0.25.0
         self._check_import()
diff --git a/python/pyarrow/tests/test_hdfs.py 
b/python/pyarrow/tests/test_hdfs.py
index c71353b45f..1f5f10f7d9 100644
--- a/python/pyarrow/tests/test_hdfs.py
+++ b/python/pyarrow/tests/test_hdfs.py
@@ -26,7 +26,6 @@ import numpy as np
 import pytest
 
 import pyarrow as pa
-from pyarrow.pandas_compat import _pandas_api
 from pyarrow.tests import util
 from pyarrow.tests.parquet.common import _test_dataframe
 from pyarrow.tests.parquet.test_dataset import (
@@ -35,6 +34,12 @@ from pyarrow.tests.parquet.test_dataset import (
 )
 from pyarrow.util import guid
 
+try:
+    from pandas.testing import assert_frame_equal
+except ImportError:
+    pass
+
+
 # ----------------------------------------------------------------------
 # HDFS tests
 
@@ -317,10 +322,10 @@ class HdfsTestCases:
         expected = self._write_multiple_hdfs_pq_files(tmpdir)
         result = self.hdfs.read_parquet(tmpdir)
 
-        _pandas_api.assert_frame_equal(result.to_pandas()
-                                       .sort_values(by='index')
-                                       .reset_index(drop=True),
-                                       expected.to_pandas())
+        assert_frame_equal(
+            result.to_pandas().sort_values(by='index').reset_index(drop=True),
+            expected.to_pandas()
+        )
 
     @pytest.mark.pandas
     @pytest.mark.parquet
@@ -335,10 +340,10 @@ class HdfsTestCases:
         path = _get_hdfs_uri(tmpdir)
         result = pq.read_table(path)
 
-        _pandas_api.assert_frame_equal(result.to_pandas()
-                                       .sort_values(by='index')
-                                       .reset_index(drop=True),
-                                       expected.to_pandas())
+        assert_frame_equal(
+            result.to_pandas().sort_values(by='index').reset_index(drop=True),
+            expected.to_pandas()
+        )
 
     @pytest.mark.pandas
     @pytest.mark.parquet
@@ -361,7 +366,7 @@ class HdfsTestCases:
             path, filesystem=self.hdfs, use_legacy_dataset=True
         ).to_pandas()
 
-        _pandas_api.assert_frame_equal(result, df)
+        assert_frame_equal(result, df)
 
     @pytest.mark.parquet
     @pytest.mark.pandas
@@ -420,8 +425,6 @@ def _get_hdfs_uri(path):
 @pytest.mark.parquet
 @pytest.mark.fastparquet
 def test_fastparquet_read_with_hdfs():
-    from pandas.testing import assert_frame_equal
-
     check_libhdfs_present()
     try:
         import snappy  # noqa

Reply via email to