Deprecate non-keyword arguments for drop_duplicates. (pandas-dev#41500)

* ENH: Deprecate non-keyword arguments for drop_duplicates.

* leave newline

* ENH: Deprecate non-keyword arguments for drop_duplicates.

* ENH: Deprecate non-keyword arguments for drop_duplicates.

* ENH: Deprecate non-keyword arguments for drop_duplicates.

* ENH: Deprecate non-keyword arguments for drop_duplicates.

* ENH: Deprecate non-keyword arguments for drop_duplicates.

* ENH: Deprecate non-keyword arguments for drop_duplicates.

* ENH: Deprecate non-keyword arguments for drop_duplicates.

* remove redundant line

* ENH: Deprecate non-keyword arguments for drop_duplicates.

Co-authored-by: Marco Gorelli <[email protected]>

Author: 2 people

doc/source/whatsnew/v1.3.0.rst

@@ -680,6 +680,7 @@ Deprecations
 - Deprecated using ``usecols`` with out of bounds indices for ``read_csv`` with ``engine="c"`` (:issue:`25623`)
 - Deprecated special treatment of lists with first element a Categorical in the :class:`DataFrame` constructor; pass as ``pd.DataFrame({col: categorical, ...})`` instead (:issue:`38845`)
 - Deprecated passing arguments as positional (except for ``"method"``) in :meth:`DataFrame.interpolate` and :meth:`Series.interpolate` (:issue:`41485`)
+- Deprecated passing arguments as positional in :meth:`DataFrame.drop_duplicates` (except for ``subset``), :meth:`Series.drop_duplicates`, :meth:`Index.drop_duplicates` and :meth:`MultiIndex.drop_duplicates`(:issue:`41485`)
 - Deprecated passing arguments (apart from ``value``) as positional in :meth:`DataFrame.fillna` and :meth:`Series.fillna` (:issue:`41485`)
 - Deprecated construction of :class:`Series` or :class:`DataFrame` with ``DatetimeTZDtype`` data and ``datetime64[ns]`` dtype.  Use ``Series(data).dt.tz_localize(None)`` instead (:issue:`41555`,:issue:`33401`)
 

pandas/core/frame.py

@@ -6007,6 +6007,7 @@ def dropna(
         else:
             return result
 
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self", "subset"])
     def drop_duplicates(
         self,
         subset: Hashable | Sequence[Hashable] | None = None,

pandas/core/indexes/base.py

@@ -54,6 +54,7 @@
 from pandas.util._decorators import (
     Appender,
     cache_readonly,
+    deprecate_nonkeyword_arguments,
     doc,
 )
 
@@ -2651,7 +2652,7 @@ def unique(self: _IndexT, level: Hashable | None = None) -> _IndexT:
         result = super().unique()
         return self._shallow_copy(result)
 
-    @final
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self"])
     def drop_duplicates(self: _IndexT, keep: str_t | bool = "first") -> _IndexT:
         """
         Return Index with duplicate values removed.

pandas/core/indexes/multi.py

@@ -41,6 +41,7 @@
 from pandas.util._decorators import (
     Appender,
     cache_readonly,
+    deprecate_nonkeyword_arguments,
     doc,
 )
 
@@ -3775,6 +3776,10 @@ def isin(self, values, level=None) -> np.ndarray:
                 return np.zeros(len(levs), dtype=np.bool_)
             return levs.isin(values)
 
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self"])
+    def drop_duplicates(self, keep: str | bool = "first") -> MultiIndex:
+        return super().drop_duplicates(keep=keep)
+
     # ---------------------------------------------------------------
     # Arithmetic/Numeric Methods - Disabled
 

pandas/core/series.py

@@ -2057,6 +2057,7 @@ def drop_duplicates(self, *, inplace: Literal[True]) -> None:
     def drop_duplicates(self, keep=..., inplace: bool = ...) -> Series | None:
         ...
 
+    @deprecate_nonkeyword_arguments(version=None, allowed_args=["self"])
     def drop_duplicates(self, keep="first", inplace=False) -> Series | None:
         """
         Return Series with duplicate values removed.

pandas/tests/frame/methods/test_drop_duplicates.py

@@ -471,3 +471,17 @@ def test_drop_duplicates_non_boolean_ignore_index(arg):
     msg = '^For argument "ignore_index" expected type bool, received type .*.$'
     with pytest.raises(ValueError, match=msg):
         df.drop_duplicates(ignore_index=arg)
+
+
+def test_drop_duplicates_pos_args_deprecation():
+    # GH#41485
+    df = DataFrame({"a": [1, 1, 2], "b": [1, 1, 3], "c": [1, 1, 3]})
+    msg = (
+        "In a future version of pandas all arguments of "
+        "DataFrame.drop_duplicates except for the argument 'subset' "
+        "will be keyword-only"
+    )
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        result = df.drop_duplicates(["b", "c"], "last")
+    expected = DataFrame({"a": [1, 2], "b": [1, 3], "c": [1, 3]}, index=[1, 2])
+    tm.assert_frame_equal(expected, result)

pandas/tests/indexes/multi/test_duplicates.py

@@ -306,3 +306,16 @@ def test_duplicated_drop_duplicates():
     assert duplicated.dtype == bool
     expected = MultiIndex.from_arrays(([2, 3, 2, 3], [1, 1, 2, 2]))
     tm.assert_index_equal(idx.drop_duplicates(keep=False), expected)
+
+
+def test_multi_drop_duplicates_pos_args_deprecation():
+    # GH#41485
+    idx = MultiIndex.from_arrays([[1, 2, 3, 1], [1, 2, 3, 1]])
+    msg = (
+        "In a future version of pandas all arguments of "
+        "MultiIndex.drop_duplicates will be keyword-only"
+    )
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        result = idx.drop_duplicates("last")
+    expected = MultiIndex.from_arrays([[2, 3, 1], [2, 3, 1]])
+    tm.assert_index_equal(expected, result)

pandas/tests/indexes/test_base.py

@@ -1738,3 +1738,17 @@ def test_construct_from_memoryview(klass, extra_kwargs):
     result = klass(memoryview(np.arange(2000, 2005)), **extra_kwargs)
     expected = klass(range(2000, 2005), **extra_kwargs)
     tm.assert_index_equal(result, expected)
+
+
+def test_drop_duplicates_pos_args_deprecation():
+    # GH#41485
+    idx = Index([1, 2, 3, 1])
+    msg = (
+        "In a future version of pandas all arguments of "
+        "Index.drop_duplicates will be keyword-only"
+    )
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        idx.drop_duplicates("last")
+        result = idx.drop_duplicates("last")
+    expected = Index([2, 3, 1])
+    tm.assert_index_equal(expected, result)

pandas/tests/series/methods/test_drop_duplicates.py

@@ -223,3 +223,16 @@ def test_drop_duplicates_categorical_bool(self, ordered):
         return_value = sc.drop_duplicates(keep=False, inplace=True)
         assert return_value is None
         tm.assert_series_equal(sc, tc[~expected])
+
+
+def test_drop_duplicates_pos_args_deprecation():
+    # GH#41485
+    s = Series(["a", "b", "c", "b"])
+    msg = (
+        "In a future version of pandas all arguments of "
+        "Series.drop_duplicates will be keyword-only"
+    )
+    with tm.assert_produces_warning(FutureWarning, match=msg):
+        result = s.drop_duplicates("last")
+    expected = Series(["a", "c", "b"], index=[0, 2, 3])
+    tm.assert_series_equal(expected, result)