Skip to content

[SPARK-54938][PYTHON][TEST][FOLLOW-UP] Fix test_pyarrow_array_type_inference for pandas >= 3 #55125

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
zhengruifeng wants to merge 1 commit into from
+11 −3
Closed

[SPARK-54938][PYTHON][TEST][FOLLOW-UP] Fix test_pyarrow_array_type_inference for pandas >= 3 #55125

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 11 additions & 3 deletions python/pyspark/tests/upstream/pyarrow/test_pyarrow_array_type_inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -295,6 +295,10 @@ def test_pandas_series_numpy_backed(self):
import numpy as np
import pandas as pd
import pyarrow as pa
from pyspark.loose_version import LooseVersion

# pandas >= 3 infers large_string instead of string for object-dtype string Series
string_type = pa.large_string() if LooseVersion(pd.__version__) >= "3.0.0" else pa.string()

sg = ZoneInfo("Asia/Singapore")
la = "America/Los_Angeles"
Expand All @@ -315,7 +319,7 @@ def test_pandas_series_numpy_backed(self):
(pd.Series([np.inf, 1.0, 2.0]), pa.float64()),
(pd.Series([-np.inf, 1.0, 2.0]), pa.float64()),
# String
(pd.Series(["a", "b", "c"]), pa.string()),
(pd.Series(["a", "b", "c"]), string_type),
# Boolean
(pd.Series([True, False, True]), pa.bool_()),
# Temporal
Expand Down Expand Up @@ -356,6 +360,10 @@ def test_pandas_series_nullable_extension(self):
import numpy as np
import pandas as pd
import pyarrow as pa
from pyspark.loose_version import LooseVersion

# pandas >= 3 uses pyarrow-backed StringDtype, which infers large_string
string_type = pa.large_string() if LooseVersion(pd.__version__) >= "3.0.0" else pa.string()

cases = [
# Integer
Expand All @@ -379,8 +387,8 @@ def test_pandas_series_nullable_extension(self):
(pd.Series([True, False, True], dtype=pd.BooleanDtype()), pa.bool_()),
(pd.Series([True, False, None], dtype=pd.BooleanDtype()), pa.bool_()),
# String
(pd.Series(["a", "b", "c"], dtype=pd.StringDtype()), pa.string()),
(pd.Series(["a", "b", None], dtype=pd.StringDtype()), pa.string()),
(pd.Series(["a", "b", "c"], dtype=pd.StringDtype()), string_type),
(pd.Series(["a", "b", None], dtype=pd.StringDtype()), string_type),
]
self._run_inference_tests(cases)

Expand Down