astype keeps nan when converting into string

Author: makbigc

doc/source/whatsnew/v1.0.0.rst

@@ -145,7 +145,7 @@ Indexing
 Missing
 ^^^^^^^
 
--
+- When converting into string, :meth:`Series.astype` will keep ``np.nan`` as missing value (:issue:`25353`)
 -
 
 MultiIndex

pandas/core/internals/blocks.py

@@ -621,9 +621,12 @@ def _astype(self, dtype, copy=False, errors="raise", **kwargs):
                 else:
                     values = self.get_values(dtype=dtype)
 
+                skipna = kwargs.pop("skipna", True)
                 # _astype_nansafe works fine with 1-d only
                 vals1d = values.ravel()
-                values = astype_nansafe(vals1d, dtype, copy=True, **kwargs)
+                values = astype_nansafe(
+                    vals1d, dtype, copy=True, skipna=skipna, **kwargs
+                )
 
             # TODO(extension)
             # should we make this attribute?

pandas/tests/frame/test_dtypes.py

@@ -627,13 +627,13 @@ def test_astype_str(self):
         assert_frame_equal(result, expected)
 
     def test_astype_str_float(self):
-        # see gh-11302
+        # GH 25353
         result = DataFrame([np.NaN]).astype(str)
-        expected = DataFrame(["nan"])
-
+        expected = DataFrame([np.nan], dtype=object)
         assert_frame_equal(result, expected)
-        result = DataFrame([1.12345678901234567890]).astype(str)
 
+        # see gh-11302
+        result = DataFrame([1.12345678901234567890]).astype(str)
         # < 1.14 truncates
         # >= 1.14 preserves the full repr
         val = "1.12345678901" if _np_version_under1p14 else "1.1234567890123457"

pandas/tests/reductions/test_reductions.py

@@ -1105,7 +1105,10 @@ def test_mode_numerical_nan(self, dropna, expected):
 
     @pytest.mark.parametrize(
         "dropna, expected1, expected2, expected3",
-        [(True, ["b"], ["bar"], ["nan"]), (False, ["b"], [np.nan], ["nan"])],
+        [
+            (True, ["b"], ["bar"], Series(["bar"])),
+            (False, ["b"], [np.nan], Series([np.nan], dtype=object)),
+        ],
     )
     def test_mode_str_obj(self, dropna, expected1, expected2, expected3):
         # Test string and object types.
@@ -1127,7 +1130,6 @@ def test_mode_str_obj(self, dropna, expected1, expected2, expected3):
 
         s = Series(data, dtype=object).astype(str)
         result = s.mode(dropna)
-        expected3 = Series(expected3, dtype=str)
         tm.assert_series_equal(result, expected3)
 
     @pytest.mark.parametrize(

pandas/tests/series/test_dtypes.py

@@ -147,7 +147,7 @@ def test_astype_datetime64tz(self):
     )
     def test_astype_str_map(self, dtype, series):
         # see gh-4405
-        result = series.astype(dtype)
+        result = series.astype(dtype, skipna=False)
         expected = series.map(str)
         tm.assert_series_equal(result, expected)
 
@@ -171,6 +171,16 @@ def test_astype_str_cast(self):
         expected = Series([str("1 days 00:00:00.000000000")])
         tm.assert_series_equal(s, expected)
 
+    @pytest.mark.parametrize(
+        "skipna, expected",
+        [(True, Series(["1", "a", np.nan])), (False, Series(["1", "a", "nan"]))],
+    )
+    def test_astype_str(self, skipna, expected):
+        # GH 25353
+        ser = Series([1, "a", np.nan])
+        result = ser.astype(str, skipna=skipna)
+        tm.assert_series_equal(result, expected)
+
     def test_astype_unicode(self):
         # see gh-7758: A bit of magic is required to set
         # default encoding to utf-8