test period case, fix most xfails

Author: jbrockmendel

pandas/tests/groupby/test_groupby.py

@@ -1858,6 +1858,7 @@ def test_pivot_table_values_key_error():
         Categorical([0]),
         [to_datetime(0)],
         date_range(0, 1, 1, tz="US/Eastern"),
+        pd.period_range("2016-01-01", periods=3, freq="D"),
         pd.array([0], dtype="Int64"),
         pd.array([0], dtype="Float64"),
         pd.array([False], dtype="boolean"),
@@ -1870,6 +1871,7 @@ def test_pivot_table_values_key_error():
         "cat",
         "dt64",
         "dt64tz",
+        "period",
         "Int64",
         "Float64",
         "boolean",
@@ -1886,13 +1888,6 @@ def test_empty_groupby(
     override_dtype = None
 
     if (
-        isinstance(values, Categorical)
-        and not isinstance(columns, list)
-        and op in ["sum", "prod", "skew"]
-    ):
-        # handled below GH#41291
-        pass
-    elif (
         isinstance(values, Categorical)
         and len(keys) == 1
         and op in ["idxmax", "idxmin"]
@@ -1901,18 +1896,8 @@ def test_empty_groupby(
             raises=ValueError, match="attempt to get arg(min|max) of an empty sequence"
         )
         request.node.add_marker(mark)
-    elif isinstance(values, Categorical) and len(keys) == 1 and op in ["sum", "prod"]:
-        mark = pytest.mark.xfail(
-            raises=AssertionError, match="(DataFrame|Series) are different"
-        )
-        request.node.add_marker(mark)
-    elif isinstance(values, Categorical) and len(keys) == 2 and op in ["sum"]:
-        mark = pytest.mark.xfail(
-            raises=AssertionError, match="(DataFrame|Series) are different"
-        )
-        request.node.add_marker(mark)
 
-    elif isinstance(values, BooleanArray) and op in ["sum", "prod"]:
+    if isinstance(values, BooleanArray) and op in ["sum", "prod"]:
         # We expect to get Int64 back for these
         override_dtype = "Int64"
 
@@ -1936,6 +1921,26 @@ def get_result(**kwargs):
         else:
             return getattr(gb, method)(op, **kwargs)
 
+    def get_categorical_invalid_expected():
+        # Categorical is special without 'observed=True', we get an NaN entry
+        #  corresponding to the unobserved group. If we passed observed=True
+        #  to groupby, expected would just be 'df.set_index(keys)[columns]'
+        #  as below
+        lev = Categorical([0], dtype=values.dtype)
+        if len(keys) != 1:
+            idx = MultiIndex.from_product([lev, lev], names=keys)
+        else:
+            # all columns are dropped, but we end up with one row
+            # Categorical is special without 'observed=True'
+            idx = Index(lev, name=keys[0])
+
+        expected = DataFrame([], columns=[], index=idx)
+        return expected
+
+    is_per = isinstance(df.dtypes[0], pd.PeriodDtype)
+    is_dt64 = df.dtypes[0].kind == "M"
+    is_cat = isinstance(values, Categorical)
+
     if isinstance(values, Categorical) and not values.ordered and op in ["min", "max"]:
         msg = f"Cannot perform {op} with non-ordered Categorical"
         with pytest.raises(TypeError, match=msg):
@@ -1944,43 +1949,23 @@ def get_result(**kwargs):
         if isinstance(columns, list):
             # i.e. DataframeGroupBy, not SeriesGroupBy
             result = get_result(numeric_only=True)
-
-            # Categorical is special without 'observed=True', we get an NaN entry
-            #  corresponding to the unobserved group. If we passed observed=True
-            #  to groupby, expected would just be 'df.set_index(keys)[columns]'
-            #  as below
-            lev = Categorical([0], dtype=values.dtype)
-            if len(keys) != 1:
-                idx = MultiIndex.from_product([lev, lev], names=keys)
-            else:
-                # all columns are dropped, but we end up with one row
-                # Categorical is special without 'observed=True'
-                idx = Index(lev, name=keys[0])
-
-            expected = DataFrame([], columns=[], index=idx)
+            expected = get_categorical_invalid_expected()
             tm.assert_equal(result, expected)
         return
 
     if columns == "C":
         # i.e. SeriesGroupBy
         if op in ["prod", "sum", "skew"]:
             # ops that require more than just ordered-ness
-            if df.dtypes[0].kind == "M":
+            if is_dt64 or is_cat or is_per:
                 # GH#41291
                 # datetime64 -> prod and sum are invalid
                 if op == "skew":
                     msg = "does not support reduction 'skew'"
-                else:
+                elif is_dt64:
                     msg = "datetime64 type does not support"
-                with pytest.raises(TypeError, match=msg):
-                    get_result()
-
-                return
-        if op in ["prod", "sum", "skew"]:
-            if isinstance(values, Categorical):
-                # GH#41291
-                if op == "skew":
-                    msg = f"does not support reduction '{op}'"
+                elif is_per:
+                    msg = "Period type does not support"
                 else:
                     msg = "category type does not support"
                 with pytest.raises(TypeError, match=msg):
@@ -1991,48 +1976,29 @@ def get_result(**kwargs):
         # ie. DataFrameGroupBy
         if op in ["prod", "sum"]:
             # ops that require more than just ordered-ness
-            if df.dtypes[0].kind == "M":
+            if is_dt64 or is_per or is_cat:
                 # GH#41291
                 # datetime64 -> prod and sum are invalid
-                with pytest.raises(TypeError, match="datetime64 type does not support"):
-                    get_result()
-                result = get_result(numeric_only=True)
-
-                # with numeric_only=True, these are dropped, and we get
-                # an empty DataFrame back
-                expected = df.set_index(keys)[[]]
-                tm.assert_equal(result, expected)
-                return
+                if is_dt64:
+                    msg = "datetime64 type does not support"
+                elif is_per:
+                    msg = "Period type does not support"
+                else:
+                    msg = "category type does not support"
 
-            elif isinstance(values, Categorical):
-                # GH#41291
-                # Categorical doesn't implement sum or prod
-                with pytest.raises(TypeError, match="category type does not support"):
+                with pytest.raises(TypeError, match=msg):
                     get_result()
                 result = get_result(numeric_only=True)
 
                 # with numeric_only=True, these are dropped, and we get
                 # an empty DataFrame back
                 expected = df.set_index(keys)[[]]
-                if len(keys) != 1 and op == "prod":
-                    # TODO: why just prod and not sum?
-                    # Categorical is special without 'observed=True'
-                    lev = Categorical([0], dtype=values.dtype)
-                    mi = MultiIndex.from_product([lev, lev], names=["A", "B"])
-                    expected = DataFrame([], columns=[], index=mi)
-
-                tm.assert_equal(result, expected)
-                return
-
-            elif df.dtypes[0] == object:
-                result = get_result()
-                expected = df.set_index(keys)[["C"]]
+                if is_cat:
+                    expected = get_categorical_invalid_expected()
                 tm.assert_equal(result, expected)
                 return
 
-        if op == "skew" and (
-            isinstance(values, Categorical) or df.dtypes[0].kind == "M"
-        ):
+        if op == "skew" and (is_cat or is_dt64 or is_per):
             msg = "|".join(
                 [
                     "Categorical is not ordered",