Only apply first row once in fast apply

Author: fjetter

pandas/_libs/reduction.pyx

@@ -507,17 +507,6 @@ def apply_frame_axis0(object frame, object f, object names,
 
     results = []
 
-    # Need to infer if our low-level mucking is going to cause a segfault
-    if n > 0:
-        chunk = frame.iloc[starts[0]:ends[0]]
-        object.__setattr__(chunk, 'name', names[0])
-        try:
-            result = f(chunk)
-            if result is chunk:
-                raise InvalidApply('Function unsafe for fast apply')
-        except:
-            raise InvalidApply('Let this error raise above us')
-
     slider = BlockSlider(frame)
 
     mutated = False
@@ -527,13 +516,23 @@ def apply_frame_axis0(object frame, object f, object names,
             slider.move(starts[i], ends[i])
 
             item_cache.clear()  # ugh
-
-            object.__setattr__(slider.dummy, 'name', names[i])
-            piece = f(slider.dummy)
+            chunk = slider.dummy
+            object.__setattr__(chunk, 'name', names[i])
+
+            # Need to infer if our low-level mucking is going to cause a segfault
+            if i == 0:
+                try:
+                    piece = f(chunk)
+                    if piece is chunk:
+                        raise InvalidApply('Function unsafe for fast apply')
+                except:
+                    raise InvalidApply('Let this error raise above us')
+            else:
+                piece = f(chunk)
 
             # I'm paying the price for index-sharing, ugh
             try:
-                if piece.index is slider.dummy.index:
+                if piece.index is chunk.index:
                     piece = piece.copy(deep='all')
                 else:
                     mutated = True

pandas/tests/groupby/test_groupby.py

@@ -1397,7 +1397,7 @@ def f(group):
     df.groupby('a', sort=False, group_keys=False).apply(f)
     # we expect 2 zeros because we call ``f`` once to see if a faster route
     # can be used.
-    expected_names = [0, 0, 1, 2]
+    expected_names = [0, 1, 2]
     assert names == expected_names