Backport PR pandas-dev#56952: DEPR: Make FutureWarning into DeprecationWarning for groupby.apply

Author: rhshadrach

pandas/core/groupby/groupby.py

@@ -1831,7 +1831,7 @@ def f(g):
                         message=_apply_groupings_depr.format(
                             type(self).__name__, "apply"
                         ),
-                        category=FutureWarning,
+                        category=DeprecationWarning,
                         stacklevel=find_stack_level(),
                     )
             except TypeError:

pandas/core/resample.py

@@ -2906,7 +2906,7 @@ def _apply(
     new_message = _apply_groupings_depr.format("DataFrameGroupBy", "resample")
     with rewrite_warning(
         target_message=target_message,
-        target_category=FutureWarning,
+        target_category=DeprecationWarning,
         new_message=new_message,
     ):
         result = grouped.apply(how, *args, include_groups=include_groups, **kwargs)

pandas/tests/extension/base/groupby.py

@@ -114,13 +114,13 @@ def test_groupby_extension_transform(self, data_for_grouping):
     def test_groupby_extension_apply(self, data_for_grouping, groupby_apply_op):
         df = pd.DataFrame({"A": [1, 1, 2, 2, 3, 3, 1, 4], "B": data_for_grouping})
         msg = "DataFrameGroupBy.apply operated on the grouping columns"
-        with tm.assert_produces_warning(FutureWarning, match=msg):
-            df.groupby("B", group_keys=False).apply(groupby_apply_op)
-        df.groupby("B", group_keys=False).A.apply(groupby_apply_op)
+        with tm.assert_produces_warning(DeprecationWarning, match=msg):
+            df.groupby("B", group_keys=False, observed=False).apply(groupby_apply_op)
+        df.groupby("B", group_keys=False, observed=False).A.apply(groupby_apply_op)
         msg = "DataFrameGroupBy.apply operated on the grouping columns"
-        with tm.assert_produces_warning(FutureWarning, match=msg):
-            df.groupby("A", group_keys=False).apply(groupby_apply_op)
-        df.groupby("A", group_keys=False).B.apply(groupby_apply_op)
+        with tm.assert_produces_warning(DeprecationWarning, match=msg):
+            df.groupby("A", group_keys=False, observed=False).apply(groupby_apply_op)
+        df.groupby("A", group_keys=False, observed=False).B.apply(groupby_apply_op)
 
     def test_groupby_apply_identity(self, data_for_grouping):
         df = pd.DataFrame({"A": [1, 1, 2, 2, 3, 3, 1, 4], "B": data_for_grouping})

pandas/tests/frame/test_stack_unstack.py

@@ -1825,7 +1825,7 @@ def test_unstack_bug(self, future_stack):
         )
 
         msg = "DataFrameGroupBy.apply operated on the grouping columns"
-        with tm.assert_produces_warning(FutureWarning, match=msg):
+        with tm.assert_produces_warning(DeprecationWarning, match=msg):
             result = df.groupby(["state", "exp", "barcode", "v"]).apply(len)
 
         unstacked = result.unstack()

pandas/tests/groupby/aggregate/test_other.py

@@ -502,15 +502,15 @@ def test_agg_timezone_round_trip():
 
     # GH#27110 applying iloc should return a DataFrame
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with tm.assert_produces_warning(DeprecationWarning, match=msg):
         assert ts == grouped.apply(lambda x: x.iloc[0]).iloc[0, 1]
 
     ts = df["B"].iloc[2]
     assert ts == grouped.last()["B"].iloc[0]
 
     # GH#27110 applying iloc should return a DataFrame
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with tm.assert_produces_warning(DeprecationWarning, match=msg):
         assert ts == grouped.apply(lambda x: x.iloc[-1]).iloc[0, 1]
 
 

pandas/tests/groupby/methods/test_value_counts.py

@@ -330,7 +330,7 @@ def test_against_frame_and_seriesgroupby(
     )
     if frame:
         # compare against apply with DataFrame value_counts
-        warn = FutureWarning if groupby == "column" else None
+        warn = DeprecationWarning if groupby == "column" else None
         msg = "DataFrameGroupBy.apply operated on the grouping columns"
         with tm.assert_produces_warning(warn, match=msg):
             expected = gp.apply(

pandas/tests/groupby/test_apply.py

@@ -14,12 +14,12 @@ def test_group_by_copy():
     ).set_index("name")
 
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with tm.assert_produces_warning(DeprecationWarning, match=msg):
         grp_by_same_value = df.groupby(["age"], group_keys=False).apply(
             lambda group: group
         )
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with tm.assert_produces_warning(DeprecationWarning, match=msg):
         grp_by_copy = df.groupby(["age"], group_keys=False).apply(
             lambda group: group.copy()
         )
@@ -54,9 +54,9 @@ def f_no_copy(x):
         return x.groupby("cat2")["rank"].min()
 
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with tm.assert_produces_warning(DeprecationWarning, match=msg):
         grpby_copy = df.groupby("cat1").apply(f_copy)
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with tm.assert_produces_warning(DeprecationWarning, match=msg):
         grpby_no_copy = df.groupby("cat1").apply(f_no_copy)
     tm.assert_series_equal(grpby_copy, grpby_no_copy)
 
@@ -68,14 +68,14 @@ def test_no_mutate_but_looks_like():
     df = pd.DataFrame({"key": [1, 1, 1, 2, 2, 2, 3, 3, 3], "value": range(9)})
 
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with tm.assert_produces_warning(DeprecationWarning, match=msg):
         result1 = df.groupby("key", group_keys=True).apply(lambda x: x[:].key)
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with tm.assert_produces_warning(DeprecationWarning, match=msg):
         result2 = df.groupby("key", group_keys=True).apply(lambda x: x.key)
     tm.assert_series_equal(result1, result2)
 
 
-def test_apply_function_with_indexing():
+def test_apply_function_with_indexing(warn_copy_on_write):
     # GH: 33058
     df = pd.DataFrame(
         {"col1": ["A", "A", "A", "B", "B", "B"], "col2": [1, 2, 3, 4, 5, 6]}
@@ -86,7 +86,9 @@ def fn(x):
         return x.col2
 
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with tm.assert_produces_warning(
+        DeprecationWarning, match=msg, raise_on_extra_warnings=not warn_copy_on_write
+    ):
         result = df.groupby(["col1"], as_index=False).apply(fn)
     expected = pd.Series(
         [1, 2, 0, 4, 5, 0],

pandas/tests/groupby/test_apply_mutate.py

@@ -125,7 +125,7 @@ def f(x):
         return x.drop_duplicates("person_name").iloc[0]
 
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with tm.assert_produces_warning(DeprecationWarning, match=msg):
         result = g.apply(f)
     expected = x.iloc[[0, 1]].copy()
     expected.index = Index([1, 2], name="person_id")
@@ -333,7 +333,7 @@ def test_apply(ordered):
     idx = MultiIndex.from_arrays([missing, dense], names=["missing", "dense"])
     expected = Series(1, index=idx)
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
-    with tm.assert_produces_warning(FutureWarning, match=msg):
+    with tm.assert_produces_warning(DeprecationWarning, match=msg):
         result = grouped.apply(lambda x: 1)
     tm.assert_series_equal(result, expected)
 
@@ -2050,7 +2050,7 @@ def test_category_order_apply(as_index, sort, observed, method, index_kind, orde
         df["a2"] = df["a"]
         df = df.set_index(keys)
     gb = df.groupby(keys, as_index=as_index, sort=sort, observed=observed)
-    warn = FutureWarning if method == "apply" and index_kind == "range" else None
+    warn = DeprecationWarning if method == "apply" and index_kind == "range" else None
     msg = "DataFrameGroupBy.apply operated on the grouping columns"
     with tm.assert_produces_warning(warn, match=msg):
         op_result = getattr(gb, method)(lambda x: x.sum(numeric_only=True))

pandas/tests/groupby/test_categorical.py

@@ -290,7 +290,7 @@ def test_count():
     for key in ["1st", "2nd", ["1st", "2nd"]]:
         left = df.groupby(key).count()
         msg = "DataFrameGroupBy.apply operated on the grouping columns"
-        with tm.assert_produces_warning(FutureWarning, match=msg):
+        with tm.assert_produces_warning(DeprecationWarning, match=msg):
             right = df.groupby(key).apply(DataFrame.count).drop(key, axis=1)
         tm.assert_frame_equal(left, right)