PERF: avoid NumPy fallback when casting Arrow int/string to string (#63401)

Co-authored-by: Claude Opus 4.5 <[email protected]>

Author: fangchenli

pandas/core/arrays/string_arrow.py

@@ -210,6 +210,26 @@ def _from_sequence(
 result=scalars._data
 result=lib.ensure_string_array(result, copy=copy, convert_na_value=False)
 pa_arr=pa.array(result, mask=na_values, type=pa.large_string())
+elifisinstance(scalars, ArrowExtensionArray):
+pa_type=scalars._pa_array.type
+# Use PyArrow's native cast for integer, string, and boolean types.
+# Float has different representation in PyArrow: 1.0 -> "1" instead
+# of "1.0", and uses different scientific notation (1e+10 vs 1e10).
+# Boolean needs capitalize (true -> True, false -> False).
+if (
+pa.types.is_integer(pa_type)
+orpa.types.is_large_string(pa_type)
+orpa.types.is_string(pa_type)
+orpa.types.is_boolean(pa_type)
+ ):
+pa_arr=pc.cast(scalars._pa_array, pa.large_string())
+ifpa.types.is_boolean(pa_type):
+pa_arr=pc.utf8_capitalize(pa_arr)
+else:
+# Fall back for types where PyArrow's string representation
+# differs from Python's str()
+result=lib.ensure_string_array(scalars, copy=copy)
+pa_arr=pa.array(result, type=pa.large_string(), from_pandas=True)
 elifisinstance(scalars, (pa.Array, pa.ChunkedArray)):
 pa_arr=pc.cast(scalars, pa.large_string())
 else:

pandas/tests/copy_view/test_astype.py

@@ -3,8 +3,6 @@
 importnumpyasnp
 importpytest
 
-frompandas.compatimportHAS_PYARROW
-
 frompandasimport (
 DataFrame,
 Series,
@@ -218,10 +216,12 @@ def test_convert_dtypes(using_infer_string):
 df_orig=df.copy()
 df2=df.convert_dtypes()
 
-ifHAS_PYARROW:
-assertnottm.shares_memory(get_array(df2, "a"), get_array(df, "a"))
-else:
+ifusing_infer_string:
+# String column is already Arrow-backed, so memory is shared
 asserttm.shares_memory(get_array(df2, "a"), get_array(df, "a"))
+else:
+# String column converts from object to Arrow, no memory sharing
+assertnottm.shares_memory(get_array(df2, "a"), get_array(df, "a"))
 asserttm.shares_memory(get_array(df2, "d"), get_array(df, "d"))
 asserttm.shares_memory(get_array(df2, "b"), get_array(df, "b"))
 asserttm.shares_memory(get_array(df2, "c"), get_array(df, "c"))