TST: fix groupby xfails (#41387)

Author: jbrockmendel

pandas/tests/groupby/test_groupby.py

@@ -1738,6 +1738,7 @@ def test_pivot_table_values_key_error():
 )
 def test_empty_groupby(columns, keys, values, method, op, request):
     # GH8093 & GH26411
+    override_dtype = None
 
     if isinstance(values, Categorical) and len(keys) == 1 and method == "apply":
         mark = pytest.mark.xfail(raises=TypeError, match="'str' object is not callable")
@@ -1784,12 +1785,9 @@ def test_empty_groupby(columns, keys, values, method, op, request):
         and op in ["sum", "prod"]
         and method != "apply"
     ):
-        mark = pytest.mark.xfail(
-            raises=AssertionError, match="(DataFrame|Series) are different"
-        )
-        request.node.add_marker(mark)
+        # We expect to get Int64 back for these
+        override_dtype = "Int64"
 
-    override_dtype = None
     if isinstance(values[0], bool) and op in ("prod", "sum") and method != "apply":
         # sum/product of bools is an integer
         override_dtype = "int64"

pandas/tests/groupby/test_rank.py

@@ -11,7 +11,6 @@
     concat,
 )
 import pandas._testing as tm
-from pandas.core.base import DataError
 
 
 def test_rank_apply():
@@ -462,21 +461,32 @@ def test_rank_avg_even_vals(dtype, upper):
     tm.assert_frame_equal(result, exp_df)
 
 
-@pytest.mark.xfail(reason="Works now, needs tests")
 @pytest.mark.parametrize("ties_method", ["average", "min", "max", "first", "dense"])
 @pytest.mark.parametrize("ascending", [True, False])
 @pytest.mark.parametrize("na_option", ["keep", "top", "bottom"])
 @pytest.mark.parametrize("pct", [True, False])
 @pytest.mark.parametrize(
     "vals", [["bar", "bar", "foo", "bar", "baz"], ["bar", np.nan, "foo", np.nan, "baz"]]
 )
-def test_rank_object_raises(ties_method, ascending, na_option, pct, vals):
+def test_rank_object_dtype(ties_method, ascending, na_option, pct, vals):
     df = DataFrame({"key": ["foo"] * 5, "val": vals})
+    mask = df["val"].isna()
 
-    with pytest.raises(DataError, match="No numeric types to aggregate"):
-        df.groupby("key").rank(
-            method=ties_method, ascending=ascending, na_option=na_option, pct=pct
-        )
+    gb = df.groupby("key")
+    res = gb.rank(method=ties_method, ascending=ascending, na_option=na_option, pct=pct)
+
+    # construct our expected by using numeric values with the same ordering
+    if mask.any():
+        df2 = DataFrame({"key": ["foo"] * 5, "val": [0, np.nan, 2, np.nan, 1]})
+    else:
+        df2 = DataFrame({"key": ["foo"] * 5, "val": [0, 0, 2, 0, 1]})
+
+    gb2 = df2.groupby("key")
+    alt = gb2.rank(
+        method=ties_method, ascending=ascending, na_option=na_option, pct=pct
+    )
+
+    tm.assert_frame_equal(res, alt)
 
 
 @pytest.mark.parametrize("na_option", [True, "bad", 1])