BUG: Series.setitem losing precision when enlarging (pandas-dev#47342)

Author: phofl

doc/source/whatsnew/v1.5.0.rst

@@ -884,6 +884,7 @@ Indexing
 - Bug in :meth:`DataFrame.loc` when setting values to a column and right hand side is a dictionary (:issue:`47216`)
 - Bug in :meth:`Series.__setitem__` with ``datetime64[ns]`` dtype, an all-``False`` boolean mask, and an incompatible value incorrectly casting to ``object`` instead of retaining ``datetime64[ns]`` dtype (:issue:`45967`)
 - Bug in :meth:`Index.__getitem__`  raising ``ValueError`` when indexer is from boolean dtype with ``NA`` (:issue:`45806`)
+- Bug in :meth:`Series.__setitem__` losing precision when enlarging :class:`Series` with scalar (:issue:`32346`)
 - Bug in :meth:`Series.mask` with ``inplace=True`` or setting values with a boolean mask with small integer dtypes incorrectly raising (:issue:`45750`)
 - Bug in :meth:`DataFrame.mask` with ``inplace=True`` and ``ExtensionDtype`` columns incorrectly raising (:issue:`45577`)
 - Bug in getting a column from a DataFrame with an object-dtype row index with datetime-like values: the resulting Series now preserves the exact object-dtype Index from the parent DataFrame (:issue:`42950`)

pandas/core/indexing.py

@@ -22,7 +22,10 @@
 from pandas.util._decorators import doc
 from pandas.util._exceptions import find_stack_level
 
-from pandas.core.dtypes.cast import can_hold_element
+from pandas.core.dtypes.cast import (
+    can_hold_element,
+    maybe_promote,
+)
 from pandas.core.dtypes.common import (
     is_array_like,
     is_bool_dtype,
@@ -42,7 +45,9 @@
 )
 from pandas.core.dtypes.missing import (
     infer_fill_value,
+    is_valid_na_for_dtype,
     isna,
+    na_value_for_dtype,
 )
 
 from pandas.core import algorithms as algos
@@ -2087,8 +2092,23 @@ def _setitem_with_indexer_missing(self, indexer, value):
                     # We get only here with loc, so can hard code
                     return self._setitem_with_indexer(new_indexer, value, "loc")
 
-            # this preserves dtype of the value
-            new_values = Series([value])._values
+            # this preserves dtype of the value and of the object
+            if is_valid_na_for_dtype(value, self.obj.dtype):
+                value = na_value_for_dtype(self.obj.dtype, compat=False)
+                new_dtype = maybe_promote(self.obj.dtype, value)[0]
+            elif isna(value):
+                new_dtype = None
+            elif not self.obj.empty and not is_object_dtype(self.obj.dtype):
+                # We should not cast, if we have object dtype because we can
+                # set timedeltas into object series
+                curr_dtype = self.obj.dtype
+                curr_dtype = getattr(curr_dtype, "numpy_dtype", curr_dtype)
+                new_dtype = maybe_promote(curr_dtype, value)[0]
+            else:
+                new_dtype = None
+
+            new_values = Series([value], dtype=new_dtype)._values
+
             if len(self.obj._values):
                 # GH#22717 handle casting compatibility that np.concatenate
                 #  does incorrectly

pandas/tests/series/indexing/test_setitem.py

@@ -535,6 +535,33 @@ def test_setitem_not_contained(self, string_series):
         expected = concat([string_series, app])
         tm.assert_series_equal(ser, expected)
 
+    def test_setitem_keep_precision(self, any_numeric_ea_dtype):
+        # GH#32346
+        ser = Series([1, 2], dtype=any_numeric_ea_dtype)
+        ser[2] = 10
+        expected = Series([1, 2, 10], dtype=any_numeric_ea_dtype)
+        tm.assert_series_equal(ser, expected)
+
+    @pytest.mark.parametrize("indexer", [1, 2])
+    @pytest.mark.parametrize(
+        "na, target_na, dtype, target_dtype",
+        [
+            (NA, NA, "Int64", "Int64"),
+            (NA, np.nan, "int64", "float64"),
+            (NaT, NaT, "int64", "object"),
+            (np.nan, NA, "Int64", "Int64"),
+            (np.nan, NA, "Float64", "Float64"),
+            (np.nan, np.nan, "int64", "float64"),
+        ],
+    )
+    def test_setitem_enlarge_with_na(self, na, target_na, dtype, target_dtype, indexer):
+        # GH#32346
+        ser = Series([1, 2], dtype=dtype)
+        ser[indexer] = na
+        expected_values = [1, target_na] if indexer == 1 else [1, 2, target_na]
+        expected = Series(expected_values, dtype=target_dtype)
+        tm.assert_series_equal(ser, expected)
+
 
 def test_setitem_scalar_into_readonly_backing_data():
     # GH#14359: test that you cannot mutate a read only buffer