Backport PR #33462 on branch 1.0.x (BUG: None converted to NaN after groupby first and last) (#33998)

Co-authored-by: JDkuba <[email protected]>

Author: simonjayhawkins

doc/source/whatsnew/v1.0.4.rst

@@ -15,7 +15,7 @@ including other versions of pandas.
 
 Fixed regressions
 ~~~~~~~~~~~~~~~~~
-- 
+- Bug in :meth:`GroupBy.first` and :meth:`GroupBy.last` where None is not preserved in object dtype (:issue:`32800`)
 - 
 
 .. _whatsnew_104.bug_fixes:

pandas/_libs/groupby.pyx

@@ -892,7 +892,9 @@ def group_last(rank_t[:, :] out,
             for j in range(K):
                 val = values[i, j]
 
-                if not checknull(val):
+                # None should not be treated like other NA-like
+                # so that it won't be converted to nan
+                if not checknull(val) or val is None:
                     # NB: use _treat_as_na here once
                     #  conditional-nogil is available.
                     nobs[lab, j] += 1
@@ -983,7 +985,9 @@ def group_nth(rank_t[:, :] out,
             for j in range(K):
                 val = values[i, j]
 
-                if not checknull(val):
+                # None should not be treated like other NA-like
+                # so that it won't be converted to nan
+                if not checknull(val) or val is None:
                     # NB: use _treat_as_na here once
                     #  conditional-nogil is available.
                     nobs[lab, j] += 1

pandas/tests/groupby/test_nth.py

@@ -94,6 +94,17 @@ def test_nth_with_na_object(index, nulls_fixture):
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.parametrize("method", ["first", "last"])
+def test_first_last_with_None(method):
+    # https://github.com/pandas-dev/pandas/issues/32800
+    # None should be preserved as object dtype
+    df = pd.DataFrame.from_dict({"id": ["a"], "value": [None]})
+    groups = df.groupby("id", as_index=False)
+    result = getattr(groups, method)()
+
+    tm.assert_frame_equal(result, df)
+
+
 def test_first_last_nth_dtypes(df_mixed_floats):
 
     df = df_mixed_floats.copy()