Simplify test

Author: MarcoGorelli

pandas/core/groupby/generic.py

@@ -1148,6 +1148,7 @@ def nunique(self, dropna=True):
         val = self.obj._internal_get_values()
 
         # GH 27951
+        # temporary fix while we wait for NumPy bug 12629 to be fixed
         val[isna(val)] = np.datetime64("NaT")
 
         try:

pandas/tests/groupby/test_function.py

@@ -1026,77 +1026,38 @@ def test_nunique_with_timegrouper():
 
 
 @pytest.mark.parametrize(
-    "data, dropna, expected",
+    "key, data, dropna, expected",
     [
         (
-            DataFrame(
-                {
-                    "key": ["x", "x", "x", "x", "x"],
-                    "data": [
-                        Timestamp("2019-01-01 00:00:00"),
-                        NaT,
-                        Timestamp("2019-01-01 00:00:00"),
-                        NaT,
-                        Timestamp("2019-01-01 00:00:00"),
-                    ],
-                }
-            ),
+            ["x", "x", "x"],
+            [Timestamp("2019-01-01"), NaT, Timestamp("2019-01-01")],
             True,
             Series([1], index=pd.Index(["x"], name="key"), name="data"),
         ),
         (
-            DataFrame(
-                {
-                    "key": ["x", "x", "x", "x", "x"],
-                    "data": [
-                        dt.date(2019, 1, 1),
-                        NaT,
-                        dt.date(2019, 1, 1),
-                        NaT,
-                        dt.date(2019, 1, 1),
-                    ],
-                }
-            ),
+            ["x", "x", "x"],
+            [dt.date(2019, 1, 1), NaT, dt.date(2019, 1, 1)],
             True,
             Series([1], index=pd.Index(["x"], name="key"), name="data"),
         ),
         (
-            DataFrame(
-                {
-                    "key": ["x", "x", "x", "y", "y"],
-                    "data": [
-                        dt.date(2019, 1, 1),
-                        NaT,
-                        dt.date(2019, 1, 1),
-                        NaT,
-                        dt.date(2019, 1, 1),
-                    ],
-                }
-            ),
+            ["x", "x", "x", "y", "y"],
+            [dt.date(2019, 1, 1), NaT, dt.date(2019, 1, 1), NaT, dt.date(2019, 1, 1)],
             False,
             Series([2, 2], index=pd.Index(["x", "y"], name="key"), name="data"),
         ),
         (
-            DataFrame(
-                {
-                    "key": ["x", "x", "x", "x", "y"],
-                    "data": [
-                        dt.date(2019, 1, 1),
-                        NaT,
-                        dt.date(2019, 1, 1),
-                        NaT,
-                        dt.date(2019, 1, 1),
-                    ],
-                }
-            ),
+            ["x", "x", "x", "x", "y"],
+            [dt.date(2019, 1, 1), NaT, dt.date(2019, 1, 1), NaT, dt.date(2019, 1, 1)],
             False,
             Series([2, 1], index=pd.Index(["x", "y"], name="key"), name="data"),
         ),
     ],
 )
-def test_nunique_with_NaT(data, dropna, expected):
+def test_nunique_with_NaT(key, data, dropna, expected):
     # GH 27951
-    result = data.groupby(["key"])["data"].nunique(dropna=dropna)
+    df = pd.DataFrame({"key": key, "data": data})
+    result = df.groupby(["key"])["data"].nunique(dropna=dropna)
     tm.assert_series_equal(result, expected)