Update PyArrow conversion and arrow/parquet tests for pyarrow 19.0

Author: jorisvandenbossche

pandas/compat/__init__.py

@@ -34,6 +34,7 @@
     pa_version_under16p0,
     pa_version_under17p0,
     pa_version_under18p0,
+    pa_version_under19p0,
 )
 
 if TYPE_CHECKING:
@@ -166,4 +167,5 @@ def is_ci_environment() -> bool:
     "pa_version_under16p0",
     "pa_version_under17p0",
     "pa_version_under18p0",
+    "pa_version_under19p0",
 ]

pandas/compat/pyarrow.py

@@ -18,6 +18,7 @@
     pa_version_under16p0 = _palv < Version("16.0.0")
     pa_version_under17p0 = _palv < Version("17.0.0")
     pa_version_under18p0 = _palv < Version("18.0.0")
+    pa_version_under19p0 = _palv < Version("19.0.0")
     HAS_PYARROW = True
 except ImportError:
     pa_version_under10p1 = True
@@ -30,4 +31,5 @@
     pa_version_under16p0 = True
     pa_version_under17p0 = True
     pa_version_under18p0 = True
+    pa_version_under19p0 = True
     HAS_PYARROW = False

pandas/io/_util.py

@@ -10,7 +10,10 @@
 from pandas._config import using_string_dtype
 
 from pandas._libs import lib
-from pandas.compat import pa_version_under18p0
+from pandas.compat import (
+    pa_version_under18p0,
+    pa_version_under19p0,
+)
 from pandas.compat._optional import import_optional_dependency
 
 import pandas as pd
@@ -77,7 +80,10 @@ def arrow_table_to_pandas(
     elif dtype_backend == "pyarrow":
         types_mapper = pd.ArrowDtype
     elif using_string_dtype():
-        types_mapper = _arrow_string_types_mapper()
+        if pa_version_under19p0:
+            types_mapper = _arrow_string_types_mapper()
+        else:
+            types_mapper = None
     elif dtype_backend is lib.no_default or dtype_backend == "numpy":
         types_mapper = None
     else:

pandas/tests/arrays/string_/test_string.py

@@ -10,7 +10,10 @@
 
 from pandas._config import using_string_dtype
 
-from pandas.compat.pyarrow import pa_version_under12p0
+from pandas.compat.pyarrow import (
+    pa_version_under12p0,
+    pa_version_under19p0,
+)
 
 from pandas.core.dtypes.common import is_dtype_equal
 
@@ -539,7 +542,7 @@ def test_arrow_roundtrip(dtype, string_storage, using_infer_string):
         assert table.field("a").type == "large_string"
     with pd.option_context("string_storage", string_storage):
         result = table.to_pandas()
-    if dtype.na_value is np.nan and not using_string_dtype():
+    if dtype.na_value is np.nan and not using_infer_string:
         assert result["a"].dtype == "object"
     else:
         assert isinstance(result["a"].dtype, pd.StringDtype)
@@ -553,6 +556,20 @@ def test_arrow_roundtrip(dtype, string_storage, using_infer_string):
         assert result.loc[2, "a"] is result["a"].dtype.na_value
 
 
+def test_arrow_from_string(using_infer_string):
+    # not roundtrip,  but starting with pyarrow table without pandas metadata
+    pa = pytest.importorskip("pyarrow")
+    table = pa.table({"a": pa.array(["a", "b", None], type=pa.string())})
+
+    result = table.to_pandas()
+
+    if using_infer_string and not pa_version_under19p0:
+        expected = pd.DataFrame({"a": ["a", "b", None]}, dtype="str")
+    else:
+        expected = pd.DataFrame({"a": ["a", "b", None]}, dtype="object")
+    tm.assert_frame_equal(result, expected)
+
+
 @pytest.mark.filterwarnings("ignore:Passing a BlockManager:DeprecationWarning")
 def test_arrow_load_from_zero_chunks(dtype, string_storage, using_infer_string):
     # GH-41040

pandas/tests/io/test_parquet.py

@@ -17,6 +17,7 @@
     pa_version_under13p0,
     pa_version_under15p0,
     pa_version_under17p0,
+    pa_version_under19p0,
 )
 
 import pandas as pd
@@ -254,8 +255,10 @@ def test_invalid_engine(df_compat):
         check_round_trip(df_compat, "foo", "bar")
 
 
-def test_options_py(df_compat, pa):
+def test_options_py(df_compat, pa, using_infer_string):
     # use the set option
+    if using_infer_string and not pa_version_under19p0:
+        df_compat.columns = df_compat.columns.astype("str")
 
     with pd.option_context("io.parquet.engine", "pyarrow"):
         check_round_trip(df_compat)
@@ -784,18 +787,21 @@ def test_unsupported_float16_cleanup(self, pa, path_type):
 
     def test_categorical(self, pa):
         # supported in >= 0.7.0
-        df = pd.DataFrame()
-        df["a"] = pd.Categorical(list("abcdef"))
-
-        # test for null, out-of-order values, and unobserved category
-        df["b"] = pd.Categorical(
-            ["bar", "foo", "foo", "bar", None, "bar"],
-            dtype=pd.CategoricalDtype(["foo", "bar", "baz"]),
-        )
-
-        # test for ordered flag
-        df["c"] = pd.Categorical(
-            ["a", "b", "c", "a", "c", "b"], categories=["b", "c", "d"], ordered=True
+        df = pd.DataFrame(
+            {
+                "a": pd.Categorical(list("abcdef")),
+                # test for null, out-of-order values, and unobserved category
+                "b": pd.Categorical(
+                    ["bar", "foo", "foo", "bar", None, "bar"],
+                    dtype=pd.CategoricalDtype(["foo", "bar", "baz"]),
+                ),
+                # test for ordered flag
+                "c": pd.Categorical(
+                    ["a", "b", "c", "a", "c", "b"],
+                    categories=["b", "c", "d"],
+                    ordered=True,
+                ),
+            }
         )
 
         check_round_trip(df, pa)
@@ -858,11 +864,13 @@ def test_s3_roundtrip_for_dir(
             repeat=1,
         )
 
-    def test_read_file_like_obj_support(self, df_compat):
+    def test_read_file_like_obj_support(self, df_compat, using_infer_string):
         pytest.importorskip("pyarrow")
         buffer = BytesIO()
         df_compat.to_parquet(buffer)
         df_from_buf = read_parquet(buffer)
+        if using_infer_string and not pa_version_under19p0:
+            df_compat.columns = df_compat.columns.astype("str")
         tm.assert_frame_equal(df_compat, df_from_buf)
 
     def test_expand_user(self, df_compat, monkeypatch):
@@ -929,7 +937,7 @@ def test_additional_extension_arrays(self, pa, using_infer_string):
                 "c": pd.Series(["a", None, "c"], dtype="string"),
             }
         )
-        if using_infer_string:
+        if using_infer_string and pa_version_under19p0:
             check_round_trip(df, pa, expected=df.astype({"c": "str"}))
         else:
             check_round_trip(df, pa)
@@ -943,7 +951,10 @@ def test_pyarrow_backed_string_array(self, pa, string_storage, using_infer_strin
         df = pd.DataFrame({"a": pd.Series(["a", None, "c"], dtype="string[pyarrow]")})
         with pd.option_context("string_storage", string_storage):
             if using_infer_string:
-                expected = df.astype("str")
+                if pa_version_under19p0:
+                    expected = df.astype("str")
+                else:
+                    expected = df.astype(f"string[{string_storage}]")
                 expected.columns = expected.columns.astype("str")
             else:
                 expected = df.astype(f"string[{string_storage}]")