ARROW-15370: [Python] Fix regression in empty table to_pandas conversion

This is a revert of ARROW-10643 (apache#12081), but I think the bug fix of that PR is less important than getting this regression fixed (I left the test that was added, but with an xfail) Closes apache#12189 from jorisvandenbossche/ARROW-15370 Authored-by: Joris Van den Bossche <[email protected]> Signed-off-by: Krisztián Szűcs <[email protected]>
davidhao3300 · Jan 19, 2022 · 657d21a · 657d21a
1 parent 3f98301
commit 657d21a
Show file tree

Hide file tree

Showing 2 changed files with 19 additions and 1 deletion.
diff --git a/python/pyarrow/pandas_compat.py b/python/pyarrow/pandas_compat.py
@@ -934,7 +934,7 @@ def _reconstruct_index(table, index_descriptors, all_columns):
                                                     descr['stop'],
                                                     step=descr['step'],
                                                     name=index_name)
-            if len(table) > 0 and len(index_level) != len(table):
+            if len(index_level) != len(table):
                 # Possibly the result of munged metadata
                 continue
         else:

diff --git a/python/pyarrow/tests/test_table.py b/python/pyarrow/tests/test_table.py
@@ -339,6 +339,7 @@ def test_chunked_array_to_pandas_preserve_name():
         tm.assert_series_equal(result, expected)
 
 
+@pytest.mark.xfail
 @pytest.mark.pandas
 def test_table_roundtrip_to_pandas_empty_dataframe():
     # https://issues.apache.org/jira/browse/ARROW-10643
@@ -348,10 +349,27 @@ def test_table_roundtrip_to_pandas_empty_dataframe():
     table = pa.table(data)
     result = table.to_pandas()
 
+    # TODO the conversion results in a table with 0 rows if the original
+    # DataFrame has a RangeIndex (i.e. no index column in the converted
+    # Arrow table)
+    assert table.num_rows == 10
     assert data.shape == (10, 0)
     assert result.shape == (10, 0)
 
 
+@pytest.mark.pandas
+def test_to_pandas_empty_table():
+    # https://issues.apache.org/jira/browse/ARROW-15370
+    import pandas as pd
+    import pandas.testing as tm
+
+    df = pd.DataFrame({'a': [1, 2], 'b': [0.1, 0.2]})
+    table = pa.table(df)
+    result = table.schema.empty_table().to_pandas()
+    assert result.shape == (0, 2)
+    tm.assert_frame_equal(result, df.iloc[:0])
+
+
 @pytest.mark.pandas
 @pytest.mark.nopandas
 def test_chunked_array_asarray():