ENH: Add ignore_index for df.drop_duplicates

doc/source/whatsnew/v1.0.0.rst

@@ -208,6 +208,7 @@ Other enhancements
 - :func:`to_parquet` now appropriately handles the ``schema`` argument for user defined schemas in the pyarrow engine. (:issue: `30270`)
 - DataFrame constructor preserve `ExtensionArray` dtype with `ExtensionArray` (:issue:`11363`)
 
+- :meth:`DataFrame.drop_duplicates` has gained ``ignore_index`` keyword to reset index (:issue:`30114`)
 
 Build Changes
 ^^^^^^^^^^^^^

pandas/core/frame.py

@@ -4587,6 +4587,7 @@ def drop_duplicates(
         subset: Optional[Union[Hashable, Sequence[Hashable]]] = None,
         keep: Union[str, bool] = "first",
         inplace: bool = False,
+        ignore_index: bool = False,
     ) -> Optional["DataFrame"]:
         """
         Return DataFrame with duplicate rows removed.
@@ -4606,6 +4607,10 @@ def drop_duplicates(
             - False : Drop all duplicates.
         inplace : bool, default False
             Whether to drop duplicates in place or to return a copy.
+        ignore_index : bool, default False
+            If True, the resulting axis will be labeled 0, 1, …, n - 1.
+
+            .. versionadded:: 1.0.0
 
         Returns
         -------
@@ -4621,9 +4626,16 @@ def drop_duplicates(
         if inplace:
             (inds,) = (-duplicated)._ndarray_values.nonzero()
             new_data = self._data.take(inds)
+
+            if ignore_index:
+                new_data.axes[1] = ibase.default_index(len(inds))
             self._update_inplace(new_data)
         else:
-            return self[-duplicated]
+            result = self[-duplicated]
+
+            if ignore_index:
+                result.index = ibase.default_index(sum(-duplicated))
+            return result
 
         return None
 

pandas/tests/frame/test_duplicates.py

@@ -477,3 +477,46 @@ def test_drop_duplicates_inplace():
     expected = orig2.drop_duplicates(["A", "B"], keep=False)
     result = df2
     tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "origin_dict, output_dict, ignore_index, output_index",
+    [
+        ({"A": [2, 2, 3]}, {"A": [2, 3]}, True, [0, 1]),
+        ({"A": [2, 2, 3]}, {"A": [2, 3]}, False, [0, 2]),
+        ({"A": [2, 2, 3], "B": [2, 2, 4]}, {"A": [2, 3], "B": [2, 4]}, True, [0, 1]),
+        ({"A": [2, 2, 3], "B": [2, 2, 4]}, {"A": [2, 3], "B": [2, 4]}, False, [0, 2]),
+    ],
+)
+def test_drop_duplicates_ignore_index_inplace_false(
+    origin_dict, output_dict, ignore_index, output_index
+):
+    # GH 30114
+    df = DataFrame(origin_dict)
+    result = df.drop_duplicates(ignore_index=ignore_index)
+
+    expected = DataFrame(output_dict, index=output_index)
+    tm.assert_frame_equal(result, expected)
+
+    # to verify if original dataframe is not mutated
+    tm.assert_frame_equal(df, DataFrame(origin_dict))
+
+
+@pytest.mark.parametrize(
+    "origin_dict, output_dict, ignore_index, output_index",
+    [
+        ({"A": [2, 2, 3]}, {"A": [2, 3]}, True, [0, 1]),
+        ({"A": [2, 2, 3]}, {"A": [2, 3]}, False, [0, 2]),
+        ({"A": [2, 2, 3], "B": [2, 2, 4]}, {"A": [2, 3], "B": [2, 4]}, True, [0, 1]),
+        ({"A": [2, 2, 3], "B": [2, 2, 4]}, {"A": [2, 3], "B": [2, 4]}, False, [0, 2]),
+    ],
+)
+def test_drop_duplicates_ignore_index_inplace_true(
+    origin_dict, output_dict, ignore_index, output_index
+):
+    # GH 30114, to check if correct when inplace is True
+    df = DataFrame(origin_dict)
+    df.drop_duplicates(ignore_index=ignore_index, inplace=True)
+
+    expected = DataFrame(output_dict, index=output_index)
+    tm.assert_frame_equal(df, expected)