Code change based on JR reviews

pandas-dev · jreback · May 9, 2020 · Dec 3, 2018 · Jan 19, 2019 · Jul 30, 2019
commit b0e3cce4dc203ac1ccf6917e2169db21aa59035b
diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
@@ -635,7 +635,7 @@ def factorize(
             uniques, codes, na_sentinel=na_sentinel, assume_unique=True, verify=False
         )
     if not dropna and (codes == na_sentinel).any():
-        uniques = np.append(uniques, [np.nan])
+        uniques = np.append(uniques, [None])
         codes = np.where(codes == na_sentinel, len(uniques) - 1, codes)
 
     uniques = _reconstruct_data(uniques, dtype, original)

@@ -5649,7 +5649,7 @@ def update(
 Captive      210.0
 Wild         185.0
 
-We can also choose to include NaN in group keys or not by defining
+We can also choose to include NaN in group keys or not by setting
 `dropna` parameter:
 
 >>> l = [[1, 2, 3], [1, None, 4], [2, 1, 3], [1, 2, 2]]

diff --git a/pandas/core/generic.py b/pandas/core/generic.py
@@ -7347,9 +7347,9 @@ def clip(
 
             .. versionadded:: 0.23.0
         dropna : bool, default True
-            If True, and if group keys contain NaN values, NaN values together
+            If True, and if group keys contain NA values, NA values together
             with row/column will be dropped.
-            If False, NaN values will also be treated as the key in groups
+            If False, NA values will also be treated as the key in groups
 
             .. versionadded:: 1.0.0
-            .. versionadded:: 1.0.0
+            .. versionadded:: 1.1.0
-            .. versionadded:: 1.0.0
+            .. versionadded:: 1.1.0
 

diff --git a/pandas/tests/groupby/test_groupby.py b/pandas/tests/groupby/test_groupby.py
@@ -2025,146 +2025,3 @@ def test_groupby_crash_on_nunique(axis):
         expected = expected.T
 
     tm.assert_frame_equal(result, expected)
-
-
-@pytest.mark.parametrize(
-    "dropna, tuples, outputs",
-    [
-        (
-            True,
-            [["A", "B"], ["B", "A"]],
-            {"c": [13.0, 123.23], "d": [13.0, 123.0], "e": [13.0, 1.0]},
-        ),
-        (
-            False,
-            [["A", "B"], ["A", np.nan], ["B", "A"]],
-            {
-                "c": [13.0, 12.3, 123.23],
-                "d": [13.0, 233.0, 123.0],
-                "e": [13.0, 12.0, 1.0],
-            },
-        ),
-    ],
-)
-def test_groupby_dropna_multi_index_dataframe(dropna, tuples, outputs):
-    # GH 3729
-    df_list = [
-        ["A", "B", 12, 12, 12],
-        ["A", None, 12.3, 233.0, 12],
-        ["B", "A", 123.23, 123, 1],
-        ["A", "B", 1, 1, 1.0],
-    ]
-    df = pd.DataFrame(df_list, columns=["a", "b", "c", "d", "e"])
-    grouped = df.g
F438
roupby(["a", "b"], dropna=dropna).sum()
-
-    mi = pd.MultiIndex.from_tuples(tuples, names=list("ab"))
-    expected = pd.DataFrame(outputs, index=mi)
-
-    tm.assert_frame_equal(grouped, expected, check_index_type=False)
-
-
-@pytest.mark.parametrize(
-    "dropna, idx, outputs",
-    [
-        (True, ["A", "B"], {"b": [123.23, 13.0], "c": [123.0, 13.0], "d": [1.0, 13.0]}),
-        (
-            False,
-            ["A", "B", np.nan],
-            {
-                "b": [123.23, 13.0, 12.3],
-                "c": [123.0, 13.0, 233.0],
-                "d": [1.0, 13.0, 12.0],
-            },
-        ),
-    ],
-)
-def test_groupby_dropna_normal_index_dataframe(dropna, idx, outputs):
-    # GH 3729
-    df_list = [
-        ["B", 12, 12, 12],
-        [None, 12.3, 233.0, 12],
-        ["A", 123.23, 123, 1],
-        ["B", 1, 1, 1.0],
-    ]
-    df = pd.DataFrame(df_list, columns=["a", "b", "c", "d"])
-    grouped = df.groupby("a", dropna=dropna).sum()
-
-    expected = pd.DataFrame(outputs, index=pd.Index(idx, dtype="object", name="a"))
-
-    tm.assert_frame_equal(grouped, expected, check_index_type=False)
-
-
-@pytest.mark.parametrize(
-    "dropna, idx, expected",
-    [
-        (True, ["a", "a", "b", np.nan], pd.Series([3, 3], index=["a", "b"])),
-        (
-            False,
-            ["a", "a", "b", np.nan],
-            pd.Series([3, 3, 3], index=["a", "b", np.nan]),
-        ),
-    ],
-)
-def test_groupby_dropna_series_level(dropna, idx, expected):
-    ser = pd.Series([1, 2, 3, 3], index=idx)
-
-    result = ser.groupby(level=0, dropna=dropna).sum()
-    tm.assert_series_equal(result, expected)
-
-
-@pytest.mark.parametrize(
-    "dropna, expected",
-    [
-        (True, pd.Series([210.0, 350.0], index=["a", "b"], name="Max Speed")),
-        (
-            False,
-            pd.Series([210.0, 350.0, 20.0], index=["a", "b", np.nan], name="Max Speed"),
-        ),
-    ],
-)
-def test_groupby_dropna_series_by(dropna, expected):
-    ser = pd.Series(
-        [390.0, 350.0, 30.0, 20.0],
-        index=["Falcon", "Falcon", "Parrot", "Parrot"],
-        name="Max Speed",
-    )
-
-    result = ser.groupby(["a", "b", "a", np.nan], dropna=dropna).mean()
-    tm.assert_series_equal(result, expected)
-
-
-@pytest.mark.parametrize(
-    "dropna, tuples, outputs",
-    [
-        (
-            True,
-            [["A", "B"], ["B", "A"]],
-            {"c": [13.0, 123.23], "d": [12.0, 123.0], "e": [1.0, 1.0]},
-        ),
-        (
-            False,
-            [["A", "B"], ["A", np.nan], ["B", "A"]],
-            {
-                "c": [13.0, 12.3, 123.23],
-                "d": [12.0, 233.0, 123.0],
-                "e": [1.0, 12.0, 1.0],
-            },
-        ),
-    ],
-)
-def test_groupby_dropna_multi_index_dataframe_agg(dropna, tuples, outputs):
-    # GH 3729
-    df_list = [
-        ["A", "B", 12, 12, 12],
-        ["A", None, 12.3, 233.0, 12],
-        ["B", "A", 123.23, 123, 1],
-        ["A", "B", 1, 1, 1.0],
-    ]
-    df = pd.DataFrame(df_list, columns=["a", "b", "c", "d", "e"])
-    agg_dict = {"c": sum, "d": max, "e": "min"}
-    grouped = df.groupby(["a", "b"], dropna=dropna).agg(agg_dict)
-
-    mi = pd.MultiIndex.from_tuples(tuples, names=list("ab"))
-    expected = pd.DataFrame(outputs, index=mi)
-    
-    tm.assert_frame_equal(grouped, expected, check_index_type=False)