BUG: process Int64 as ints for preservable ops, not as float64

Author: qwhelan

doc/source/whatsnew/v1.1.0.rst

@@ -406,6 +406,7 @@ Other
 - :meth:`IntegerArray.astype` now supports ``datetime64`` dtype (:issue:32538`)
 - Fixed bug in :func:`pandas.testing.assert_series_equal` where dtypes were checked for ``Interval`` and ``ExtensionArray`` operands when ``check_dtype`` was ``False`` (:issue:`32747`)
 - Bug in :meth:`DataFrame.__dir__` caused a segfault when using unicode surrogates in a column name (:issue:`25509`)
+- :meth:`IntegerArray.min` and :meth:`IntegerArray.max` no longer roundtrip through ``np.float64`` values, fixing precision for large integers (:issue:`32652`)
 
 .. ---------------------------------------------------------------------------
 

pandas/core/arrays/integer.py

@@ -560,10 +560,13 @@ def _reduce(self, name: str, skipna: bool = True, **kwargs):
         data = self._data
         mask = self._mask
 
+        preservable_ops = ["min", "max"]
+
         # coerce to a nan-aware float if needed
         # (we explicitly use NaN within reductions)
         if self._hasna:
-            data = self.to_numpy("float64", na_value=np.nan)
+            if name not in preservable_ops or not skipna:
+                data = self.to_numpy("float64", na_value=np.nan)
 
         op = getattr(nanops, "nan" + name)
         result = op(data, axis=0, skipna=skipna, mask=mask, **kwargs)
@@ -577,9 +580,11 @@ def _reduce(self, name: str, skipna: bool = True, **kwargs):
 
         # if we have a preservable numeric op,
         # provide coercion back to an integer type if possible
-        elif name in ["sum", "min", "max", "prod"]:
+        elif name in preservable_ops + ["sum", "prod"]:
             # GH#31409 more performant than casting-then-checking
             result = com.cast_scalar_indexer(result)
+            if isinstance(result, np.integer):
+                result = int(result)
 
         return result
 

pandas/core/nanops.py

@@ -183,11 +183,17 @@ def _get_fill_value(
         if fill_value_typ is None:
             return iNaT
         else:
-            if fill_value_typ == "+inf":
-                # need the max int here
-                return _int64_max
-            else:
-                return iNaT
+            dtype = getattr(dtype, "numpy_dtype", dtype)
+            try:
+                if fill_value_typ == "+inf":
+                    return np.iinfo(dtype).max
+                else:
+                    return np.iinfo(dtype).min
+            except ValueError:
+                if fill_value_typ == "+inf":
+                    return _int64_max
+                else:
+                    iNaT
 
 
 def _maybe_get_mask(

pandas/tests/extension/test_integer.py

@@ -238,7 +238,11 @@ def check_reduce(self, s, op_name, skipna):
         # overwrite to ensure pd.NA is tested instead of np.nan
         # https://github.com/pandas-dev/pandas/issues/30958
         result = getattr(s, op_name)(skipna=skipna)
-        expected = getattr(s.astype("float64"), op_name)(skipna=skipna)
+        preserved_ops = ["min", "max"]
+        if skipna and op_name in preserved_ops:
+            expected = getattr(s.dropna(), op_name)(skipna=True)
+        else:
+            expected = getattr(s.astype("float64"), op_name)(skipna=skipna)
         if np.isnan(expected):
             expected = pd.NA
         tm.assert_almost_equal(result, expected)