Address review comments

Author: fjetter

doc/source/whatsnew/v0.25.0.rst

@@ -29,46 +29,39 @@ Backwards incompatible API changes
 GroupBy.apply on ``DataFrame`` evaluates first group only once
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-(:issue:`2936`, :issue:`2656`, :issue:`7739`, :issue:`10519`, :issue:`12155`,
-:issue:`20084`, :issue:`21417`)
-
 The implementation of ``DataFrame.groupby.apply`` previously evaluated func
 consistently twice on the first group to infer if it is safe to use a fast
 code path. Particularly for functions with side effects, this was an undesired
 behavior and may have led to surprises.
 
 Now every group is evaluated only a single time.
 
-Previous behavior:
-
-.. code-block:: ipython
+.. ipython:: python
 
-    In [2]: df = pd.DataFrame({"a": ["x", "y"], "b": [1, 2]})
+    df = pd.DataFrame({"a": ["x", "y"], "b": [1, 2]})
+    df
 
-    In [3]: side_effects = []
+    side_effects = []
+    def func(group):
+        side_effects.append(group.name)
+        return group
+    df.groupby("a").apply(func)
 
-    In [4]: def func_fast_apply(group):
-    ...:     side_effects.append(group.name)
-    ...:     return len(group)
-    ...:
+Previous behavior:
 
-    In [5]: df.groupby("a").apply(func_fast_apply)
+.. code-block:: ipython
 
     In [6]: assert side_effects == ["x", "x", "y"]
 
 New behavior:
 
 .. ipython:: python
 
-    df = pd.DataFrame({"a": ["x", "y"], "b": [1, 2]})
+    assert side_effects == ["x", "y"]
 
-    side_effects = []
-    def func(group):
-        side_effects.append(group.name)
-        return group
 
-    df.groupby("a").apply(func)
-    assert side_effects == ["x", "y"]
+(:issue:`2936`, :issue:`2656`, :issue:`7739`, :issue:`10519`, :issue:`12155`,
+:issue:`20084`, :issue:`21417`)
 
 
 .. _whatsnew_0250.api.other:

pandas/tests/groupby/test_apply.py

@@ -107,20 +107,22 @@ def f(g):
 
 
 def test_group_apply_once_per_group():
-    # GH24748 ,GH2936, GH2656, GH7739, GH10519, GH12155, GH20084, GH21417
-    df = pd.DataFrame({'a': [0, 0, 1, 1, 2, 2], 'b': np.arange(6)})
+    # GH2936, GH7739, GH10519, GH2656, GH12155, GH20084, GH21417
+    df = pd.DataFrame({"a": [0, 0, 1, 1, 2, 2], "b": np.arange(6)})
 
     names = []
 
     def f_copy(group):
         names.append(group.name)
         return group.copy()
+
     df.groupby("a").apply(f_copy)
     assert names == [0, 1, 2]
 
     def f_nocopy(group):
         names.append(group.name)
         return group
+
     names = []
     # this takes the slow apply path
     df.groupby("a").apply(f_nocopy)

pandas/tests/groupby/test_groupby.py

@@ -1420,30 +1420,18 @@ def foo(x):
 
 def test_group_name_available_in_inference_pass():
     # gh-15062
-    # GH24748 ,GH2936, GH2656, GH7739, GH10519, GH12155, GH20084, GH21417
     df = pd.DataFrame({'a': [0, 0, 1, 1, 2, 2], 'b': np.arange(6)})
 
     names = []
 
-    def f_fast(group):
+    def f(group):
         names.append(group.name)
         return group.copy()
+    df.groupby('a', sort=False, group_keys=False).apply(f)
 
-    df.groupby('a', sort=False, group_keys=False).apply(f_fast)
-
-    # every group should appear once, i.e. apply is called once per group
     expected_names = [0, 1, 2]
     assert names == expected_names
 
-    names_slow = []
-
-    def f_slow(group):
-        names_slow.append(group.name)
-        return group
-
-    df.groupby('a', sort=False, group_keys=False).apply(f_slow)
-    assert names_slow == [0, 1, 2]
-
 
 def test_no_dummy_key_names(df):
     # see gh-1291