BUG: fix DataFrame.apply returning wrong result when dealing with dtype (#28773)

doc/source/whatsnew/v1.0.0.rst

@@ -876,11 +876,11 @@ Other
 - Bug in :meth:`DataFrame.append` that raised ``IndexError`` when appending with empty list (:issue:`28769`)
 - Fix :class:`AbstractHolidayCalendar` to return correct results for
   years after 2030 (now goes up to 2200) (:issue:`27790`)
+- Bug in :meth:`DataFrame.apply` returning wrong result in some cases when dtype was involved in passed function (:issue:`28773`)
 - Fixed :class:`IntegerArray` returning ``inf`` rather than ``NaN`` for operations dividing by 0 (:issue:`27398`)
 - Fixed ``pow`` operations for :class:`IntegerArray` when the other value is ``0`` or ``1`` (:issue:`29997`)
 - Bug in :meth:`Series.count` raises if use_inf_as_na is enabled (:issue:`29478`)
 
-
 .. _whatsnew_1000.contributors:
 
 Contributors

pandas/core/frame.py

@@ -6564,16 +6564,63 @@ def apply(self, func, axis=0, raw=False, result_type=None, args=(), **kwds):
         """
         from pandas.core.apply import frame_apply
 
-        op = frame_apply(
-            self,
-            func=func,
-            axis=axis,
-            raw=raw,
-            result_type=result_type,
-            args=args,
-            kwds=kwds,
-        )
-        return op.get_result()
+        # Old apply function, which will be used for each part of DataFrame
+        def partial_apply(dataframe):
+            op = frame_apply(
+                dataframe,
+                func=func,
+                axis=axis,
+                raw=raw,
+                result_type=result_type,
+                args=args,
+                kwds=kwds,
+            )
+            return op.get_result()
+
+        def get_dtype(dataframe, column):
+            return dataframe.dtypes.values[column]
+
+        if axis == 0 or axis == "index":
+            if self.shape[1] == 0:
+                return partial_apply(self)
+
+            frame = self.iloc[:, [0]]
+            result = partial_apply(frame)
+            if isinstance(result, Series):
+                results = result.values
+            else:
+                results = result
+
+            i = 1
+            while i < self.shape[1]:
+                type = get_dtype(self, i)
+                j = i + 1
+
+                # While the dtype of column is the same as previous ones,
+                # they are handled together
+                while j < self.shape[1] and pandas.core.dtypes.common.is_dtype_equal(
+                    type, get_dtype(self, j)
+                ):
+                    j += 1
+                frame = self.iloc[:, i:j]
+                i = j
+                result = partial_apply(frame)
+
+                if isinstance(result, Series):
+                    results = np.append(results, result.values)
+                else:
+                    for k in range(result.shape[0], results.shape[0]):
+                        result.loc[k, :] = np.nan
+                    for k in range(results.shape[0], result.shape[0]):
+                        results.loc[k, :] = np.nan
+                    results = pandas.concat([results, result], axis=1)
+
+            if isinstance(result, Series):
+                return Series(results, index=self.columns)
+            else:
+                return results
+        else:
+            return partial_apply(self)
 
     def applymap(self, func):
         """

pandas/tests/frame/test_apply.py

@@ -691,6 +691,12 @@ def test_apply_dup_names_multi_agg(self):
 
         tm.assert_frame_equal(result, expected)
 
+    def test_apply_get_dtype(self):
+        # GH 28773
+        df = DataFrame({"col_1": [1, 2, 3], "col_2": ["hi", "there", "friend"]})
+        expected = Series(data=["int64", "object"], index=["col_1", "col_2"])
+        tm.assert_series_equal(df.apply(lambda x: x.dtype), expected)
+
 
 class TestInferOutputShape:
     # the user has supplied an opaque UDF where