fix bfill, ffill and pad when calling with df.interpolate with column dtype string (pandas-dev#33956)

Author: CloseChoice

pandas/core/generic.py

@@ -6898,7 +6898,7 @@ def interpolate(
             )
 
         # create/use the index
-        if method == "linear":
+        if method in ["linear", "bfill", "ffill", "pad"]:
             # prior default
             index = np.arange(len(df.index))
         else:
@@ -6912,7 +6912,7 @@ def interpolate(
             if method not in methods and not is_numeric_or_datetime:
                 raise ValueError(
                     "Index column must be numeric or datetime type when "
-                    f"using {method} method other than linear. "
+                    f"using {method} method other than linear, bfill, ffill or pad. "
                     "Try setting a numeric or datetime index column before "
                     "interpolating."
                 )

pandas/tests/frame/methods/test_interpolate.py

@@ -284,3 +284,109 @@ def test_interp_time_inplace_axis(self, axis):
         result = expected.interpolate(axis=0, method="time")
         expected.interpolate(axis=0, method="time", inplace=True)
         tm.assert_frame_equal(result, expected)
+
+    def test_interp_ffill(self):
+        # GH 33956
+        df = DataFrame(
+            {
+                "A": [1.0, 2.0, 3.0, 4.0, np.nan, 5.0],
+                "B": [2.0, 4.0, 6.0, np.nan, 8.0, 10.0],
+                "C": [3.0, 6.0, 9.0, np.nan, np.nan, 30.0],
+            }
+        )
+        expected = DataFrame(
+            {
+                "A": [1.0, 2.0, 3.0, 4.0, 4.0, 5.0],
+                "B": [2.0, 4.0, 6.0, 6.0, 8.0, 10.0],
+                "C": [3.0, 6.0, 9.0, 9.0, 9.0, 30.0],
+            }
+        )
+        result = df.interpolate(method="ffill", axis=1)
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("axis", [0, 1])
+    def test_interp_ffill(self, axis):
+        # GH 33956
+        df = DataFrame(
+            {
+                "A": [1.0, 2.0, 3.0, 4.0, np.nan, 5.0],
+                "B": [2.0, 4.0, 6.0, np.nan, 8.0, 10.0],
+                "C": [3.0, 6.0, 9.0, np.nan, np.nan, 30.0],
+            }
+        )
+        if axis == 0:
+            expected = DataFrame(
+                {
+                    "A": [1.0, 2.0, 3.0, 4.0, np.nan, 5.0],
+                    "B": [2.0, 4.0, 6.0, 4.0, 8.0, 10.0],
+                    "C": [3.0, 6.0, 9.0, 4.0, 8.0, 30.0],
+                }
+            )
+        if axis == 1:
+            expected = DataFrame(
+                {
+                    "A": [1.0, 2.0, 3.0, 4.0, 4.0, 5.0],
+                    "B": [2.0, 4.0, 6.0, 6.0, 8.0, 10.0],
+                    "C": [3.0, 6.0, 9.0, 9.0, 9.0, 30.0],
+                }
+            )
+        result = df.interpolate(method="ffill", axis=axis)
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("axis", [0, 1])
+    def test_interp_bfill(self, axis):
+        # GH 33956
+        df = DataFrame(
+            {
+                "A": [1.0, 2.0, 3.0, 4.0, np.nan, 5.0],
+                "B": [2.0, 4.0, 6.0, np.nan, 8.0, 10.0],
+                "C": [3.0, 6.0, 9.0, np.nan, np.nan, 30.0],
+            }
+        )
+        if axis == 0:
+            expected = DataFrame(
+                {
+                    "A": [1.0, 2.0, 3.0, 4.0, 8.0, 5.0],
+                    "B": [2.0, 4.0, 6.0, np.nan, 8.0, 10.0],
+                    "C": [3.0, 6.0, 9.0, np.nan, np.nan, 30.0],
+                }
+            )
+        if axis == 1:
+            expected = DataFrame(
+                {
+                    "A": [1.0, 2.0, 3.0, 4.0, 5.0, 5.0],
+                    "B": [2.0, 4.0, 6.0, 8.0, 8.0, 10.0],
+                    "C": [3.0, 6.0, 9.0, 30.0, 30.0, 30.0],
+                }
+            )
+        result = df.interpolate(method="bfill", axis=axis)
+        tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("axis", [0, 1])
+    def test_interp_pad(self, axis):
+        # GH 33956
+        df = DataFrame(
+            {
+                "A": [1.0, 2.0, 3.0, 4.0, np.nan, 5.0],
+                "B": [2.0, 4.0, 6.0, np.nan, 8.0, 10.0],
+                "C": [3.0, 6.0, 9.0, np.nan, np.nan, 30.0],
+            }
+        )
+        if axis == 0:
+            expected = DataFrame(
+                {
+                    "A": [1.0, 2.0, 3.0, 4.0, np.nan, 5.0],
+                    "B": [2.0, 4.0, 6.0, 4.0, 8.0, 10.0],
+                    "C": [3.0, 6.0, 9.0, 4.0, 8.0, 30.0],
+                }
+            )
+        if axis == 1:
+            expected = DataFrame(
+                {
+                    "A": [1.0, 2.0, 3.0, 4.0, 4.0, 5.0],
+                    "B": [2.0, 4.0, 6.0, 6.0, 8.0, 10.0],
+                    "C": [3.0, 6.0, 9.0, 9.0, 9.0, 30.0],
+                }
+            )
+        result = df.interpolate(method="pad", axis=axis)
+        tm.assert_frame_equal(result, expected)