change pyarrow dtype of date32 and date64 to day and ms granularity

Author: nli307

pandas/core/dtypes/common.py

@@ -1872,11 +1872,6 @@ def pandas_dtype(dtype) -> DtypeObj:
             result = result()
         return result
 
-    # try a pyarrow dtype
-    from pandas.core.dtypes.dtypes import ArrowDtype
-    if isinstance(dtype, ArrowDtype):
-        return ArrowDtype(dtype)
-
     # try a numpy dtype
     # raise a consistent TypeError if failed
     try:

pandas/core/dtypes/dtypes.py

@@ -2277,12 +2277,18 @@ def name(self) -> str:  # type: ignore[override]
     @cache_readonly
     def numpy_dtype(self) -> np.dtype:
         """Return an instance of the related numpy dtype"""
-        if pa.types.is_date32(self.pyarrow_dtype) or pa.types.is_date64(
-            self.pyarrow_dtype
-        ):
-            # date32 and date64 are pyarrow timestamps but do not have a
-            # corresponding numpy dtype.
-            return np.dtype(object)
+        if pa.types.is_date32(self.pyarrow_dtype):
+            # pa.timestamp(unit).to_pandas_dtype() returns ns units
+            # regardless of the pyarrow timestamp units.
+            # This can be removed if/when pyarrow addresses it:
+            # https://github.com/apache/arrow/issues/34462
+            return np.dtype("datetime64[D]")
+        if pa.types.is_date64(self.pyarrow_dtype):
+            # pa.timestamp(unit).to_pandas_dtype() returns ns units
+            # regardless of the pyarrow timestamp units.
+            # This can be removed if/when pyarrow addresses it:
+            # https://github.com/apache/arrow/issues/34462
+            return np.dtype("datetime64[ms]")
         if pa.types.is_timestamp(self.pyarrow_dtype):
             # pa.timestamp(unit).to_pandas_dtype() returns ns units
             # regardless of the pyarrow timestamp units.
@@ -2459,18 +2465,6 @@ def _get_common_dtype(self, dtypes: list[DtypeObj]) -> DtypeObj | None:
 
         null_dtype = type(self)(pa.null())
 
-        # Cover cases where numpy does not have a corresponding dtype, but
-        # only one non-null dtype is received, or all dtypes are null.
-        single_dtype = {
-            dtype
-            for dtype in dtypes
-            if dtype != null_dtype
-        }
-        if len(single_dtype) == 0:
-            return null_dtype
-        if len(single_dtype) == 1:
-            return single_dtype.pop()
-
         new_dtype = find_common_type(
             [
                 dtype.numpy_dtype if isinstance(dtype, ArrowDtype) else dtype