round-trip categorical pyarrow

Author: MarcoGorelli

doc/source/whatsnew/v2.0.1.rst

@@ -26,6 +26,7 @@ Bug fixes
 ~~~~~~~~~
 - Bug in :attr:`Series.dt.days` that would overflow ``int32`` number of days (:issue:`52391`)
 - Bug in :class:`arrays.DatetimeArray` constructor returning an incorrect unit when passed a non-nanosecond numpy datetime array (:issue:`52555`)
+- Bug in :func:`api.interchange.from_dataframe` was unnecessarily raising on-categorical dtypes (:issue:`49889`)
 - Bug in :func:`pandas.testing.assert_series_equal` where ``check_dtype=False`` would still raise for datetime or timedelta types with different resolutions (:issue:`52449`)
 - Bug in :func:`read_csv` casting PyArrow datetimes to NumPy when ``dtype_backend="pyarrow"`` and ``parse_dates`` is set causing a performance bottleneck in the process (:issue:`52546`)
 - Bug in :func:`to_datetime` and :func:`to_timedelta` when trying to convert numeric data with a :class:`ArrowDtype` (:issue:`52425`)

pandas/core/interchange/from_dataframe.py

@@ -7,7 +7,6 @@
 import numpy as np
 
 import pandas as pd
-from pandas.core.interchange.column import PandasColumn
 from pandas.core.interchange.dataframe_protocol import (
     Buffer,
     Column,
@@ -182,7 +181,7 @@ def categorical_column_to_series(col: Column) -> tuple[pd.Series, Any]:
 
     cat_column = categorical["categories"]
     # for mypy/pyright
-    assert isinstance(cat_column, PandasColumn), "categories must be a PandasColumn"
+    assert hasattr(cat_column, "_col"), "categories must have a `.col` attribute"
     categories = np.array(cat_column._col)
     buffers = col.get_buffers()
 

pandas/tests/interchange/test_impl.py

@@ -2,6 +2,7 @@
 import random
 
 import numpy as np
+import pyarrow as pa
 import pytest
 
 from pandas._libs.tslibs import iNaT
@@ -74,6 +75,19 @@ def test_categorical_dtype(data):
     tm.assert_frame_equal(df, from_dataframe(df.__dataframe__()))
 
 
+def test_categorical_pyarrow():
+    # GH 49889
+    arr = ["Mon", "Tue", "Mon", "Wed", "Mon", "Thu", "Fri", "Sat", "Sun"]
+    table = pa.table({"weekday": pa.array(arr).dictionary_encode()})
+    exchange_df = table.__dataframe__()
+    result = from_dataframe(exchange_df)
+    weekday = pd.Categorical(
+        arr, categories=["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"]
+    )
+    expected = pd.DataFrame({"weekday": weekday})
+    tm.assert_frame_equal(result, expected)
+
+
 @pytest.mark.parametrize(
     "data", [int_data, uint_data, float_data, bool_data, datetime_data]
 )