Merge remote-tracking branch 'upstream/2.3.x' into string-dtype-2.3.x-downcast-string

Author: jorisvandenbossche

.circleci/config.yml

@@ -15,7 +15,6 @@ jobs:
       - checkout
       - run: .circleci/setup_env.sh
       - run: |
-          sudo apt-get update && sudo apt-get install -y libegl1 libopengl0
           PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH \
           LD_PRELOAD=$HOME/miniconda3/envs/pandas-dev/lib/libgomp.so.1:$LD_PRELOAD \
           ci/run_tests.sh

pandas/core/dtypes/cast.py

@@ -1606,7 +1606,10 @@ def construct_1d_object_array_from_listlike(values: Collection) -> np.ndarray:
     """
     # numpy will try to interpret nested lists as further dimensions in np.array(),
     # hence explicitly making a 1D array using np.fromiter
-    return np.fromiter(values, dtype="object", count=len(values))
+    result = np.empty(len(values), dtype="object")
+    for i, obj in enumerate(values):
+        result[i] = obj
+    return result
 
 
 def maybe_cast_to_integer_array(arr: list | np.ndarray, dtype: np.dtype) -> np.ndarray:

pandas/tests/extension/test_arrow.py

@@ -1637,7 +1637,7 @@ def test_from_arrow_respecting_given_dtype():
 
 def test_from_arrow_respecting_given_dtype_unsafe():
     array = pa.array([1.5, 2.5], type=pa.float64())
-    with pytest.raises(pa.ArrowInvalid, match="Float value 1.5 was truncated"):
+    with tm.external_error_raised(pa.ArrowInvalid):
         array.to_pandas(types_mapper={pa.float64(): ArrowDtype(pa.int64())}.get)
 
 

pandas/tests/io/test_fsspec.py

@@ -5,6 +5,8 @@
 
 from pandas._config import using_string_dtype
 
+from pandas.compat import HAS_PYARROW
+
 from pandas import (
     DataFrame,
     date_range,
@@ -168,7 +170,9 @@ def test_excel_options(fsspectest):
     assert fsspectest.test[0] == "read"
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string) fastparquet")
+@pytest.mark.xfail(
+    using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string) fastparquet"
+)
 def test_to_parquet_new_file(cleared_fs, df1):
     """Regression test for writing to a not-yet-existent GCS Parquet file."""
     pytest.importorskip("fastparquet")

pandas/tests/io/test_gcs.py

@@ -7,8 +7,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.compat.pyarrow import pa_version_under17p0
 
 from pandas import (
@@ -196,7 +194,6 @@ def test_to_csv_compression_encoding_gcs(
     tm.assert_frame_equal(df, read_df)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string) fastparquet")
 def test_to_parquet_gcs_new_file(monkeypatch, tmpdir):
     """Regression test for writing to a not-yet-existent GCS Parquet file."""
     pytest.importorskip("fastparquet")