differences in Series.map with defaultdict with different dtypes (#49011)

Author: dannyi96

doc/source/whatsnew/v2.0.0.rst

@@ -222,7 +222,7 @@ Indexing
 Missing
 ^^^^^^^
 - Bug in :meth:`Index.equals` raising ``TypeError`` when :class:`Index` consists of tuples that contain ``NA`` (:issue:`48446`)
--
+- Bug in :meth:`Series.map` caused incorrect result when data has NaNs and defaultdict mapping was used (:issue:`48813`)
 
 MultiIndex
 ^^^^^^^^^^

pandas/core/base.py

@@ -830,7 +830,9 @@ def _map_values(self, mapper, na_action=None):
                 # If a dictionary subclass defines a default value method,
                 # convert mapper to a lookup function (GH #15999).
                 dict_with_default = mapper
-                mapper = lambda x: dict_with_default[x]
+                mapper = lambda x: dict_with_default[
+                    np.nan if isinstance(x, float) and np.isnan(x) else x
+                ]
             else:
                 # Dictionary does not have a default. Thus it's safe to
                 # convert to an Series for efficiency.

pandas/tests/apply/test_series_apply.py

@@ -598,6 +598,36 @@ def test_map_dict_na_key():
     tm.assert_series_equal(result, expected)
 
 
+@pytest.mark.parametrize("na_action", [None, "ignore"])
+def test_map_defaultdict_na_key(na_action):
+    # GH 48813
+    s = Series([1, 2, np.nan])
+    default_map = defaultdict(lambda: "missing", {1: "a", 2: "b", np.nan: "c"})
+    result = s.map(default_map, na_action=na_action)
+    expected = Series({0: "a", 1: "b", 2: "c" if na_action is None else np.nan})
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("na_action", [None, "ignore"])
+def test_map_defaultdict_missing_key(na_action):
+    # GH 48813
+    s = Series([1, 2, np.nan])
+    default_map = defaultdict(lambda: "missing", {1: "a", 2: "b", 3: "c"})
+    result = s.map(default_map, na_action=na_action)
+    expected = Series({0: "a", 1: "b", 2: "missing" if na_action is None else np.nan})
+    tm.assert_series_equal(result, expected)
+
+
+@pytest.mark.parametrize("na_action", [None, "ignore"])
+def test_map_defaultdict_unmutated(na_action):
+    # GH 48813
+    s = Series([1, 2, np.nan])
+    default_map = defaultdict(lambda: "missing", {1: "a", 2: "b", np.nan: "c"})
+    expected_default_map = default_map.copy()
+    s.map(default_map, na_action=na_action)
+    assert default_map == expected_default_map
+
+
 @pytest.mark.parametrize("arg_func", [dict, Series])
 def test_map_dict_ignore_na(arg_func):
     # GH#47527
@@ -613,7 +643,7 @@ def test_map_defaultdict_ignore_na():
     mapping = defaultdict(int, {1: 10, np.nan: 42})
     ser = Series([1, np.nan, 2])
     result = ser.map(mapping)
-    expected = Series([10, 0, 0])
+    expected = Series([10, 42, 0])
     tm.assert_series_equal(result, expected)