DEPR: Deprecate mangle_dupe_cols (#48137)

* DEPR: Deprecate mangle_dupe_cols

* Add read_table to whatsnew

Author: datapythonista

doc/source/whatsnew/v1.5.0.rst

@@ -847,6 +847,7 @@ Other Deprecations
 - Deprecated the ``inplace`` keyword in :meth:`DataFrame.set_index`, use ``df = df.set_index(..., copy=False)`` instead (:issue:`48115`)
 - Deprecated the ``sort_columns`` argument in :meth:`DataFrame.plot` and :meth:`Series.plot` (:issue:`47563`).
 - Deprecated positional arguments for all but the first argument of :meth:`DataFrame.to_stata` and :func:`read_stata`, use keyword arguments instead (:issue:`48128`).
+- Deprecated the ``mangle_dupe_cols`` argument in :func:`read_csv`, :func:`read_fwf`, :func:`read_table` and :func:`read_excel`. The argument was never implemented, and a new argument where the renaming pattern can be specified will be added instead (:issue:`47718`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_150.performance:

pandas/io/excel/_base.py

@@ -42,6 +42,7 @@
 from pandas.errors import EmptyDataError
 from pandas.util._decorators import (
     Appender,
+    deprecate_kwarg,
     deprecate_nonkeyword_arguments,
     doc,
 )
@@ -280,6 +281,11 @@
     Duplicate columns will be specified as 'X', 'X.1', ...'X.N', rather than
     'X'...'X'. Passing in False will cause data to be overwritten if there
     are duplicate names in the columns.
+
+    .. deprecated:: 1.5.0
+        Not implemented, and a new argument to specify the pattern for the
+        names of duplicated columns will be added instead
+
 {storage_options}
 
     .. versionadded:: 1.2.0
@@ -433,6 +439,7 @@ def read_excel(
 
 
 @doc(storage_options=_shared_docs["storage_options"])
+@deprecate_kwarg(old_arg_name="mangle_dupe_cols", new_arg_name=None)
 @deprecate_nonkeyword_arguments(allowed_args=["io", "sheet_name"], version="2.0")
 @Appender(_read_excel_doc)
 def read_excel(

pandas/io/parsers/readers.py

@@ -39,6 +39,7 @@
 )
 from pandas.util._decorators import (
     Appender,
+    deprecate_kwarg,
     deprecate_nonkeyword_arguments,
 )
 from pandas.util._exceptions import find_stack_level
@@ -163,6 +164,10 @@
     Duplicate columns will be specified as 'X', 'X.1', ...'X.N', rather than
     'X'...'X'. Passing in False will cause data to be overwritten if there
     are duplicate names in the columns.
+
+    .. deprecated:: 1.5.0
+        Not implemented, and a new argument to specify the pattern for the
+        names of duplicated columns will be added instead
 dtype : Type name or dict of column -> type, optional
     Data type for data or columns. E.g. {{'a': np.float64, 'b': np.int32,
     'c': 'Int64'}}
@@ -846,6 +851,7 @@ def read_csv(
     ...
 
 
+@deprecate_kwarg(old_arg_name="mangle_dupe_cols", new_arg_name=None)
 @deprecate_nonkeyword_arguments(version=None, allowed_args=["filepath_or_buffer"])
 @Appender(
     _doc_read_csv_and_table.format(
@@ -1184,6 +1190,7 @@ def read_table(
     ...
 
 
+@deprecate_kwarg(old_arg_name="mangle_dupe_cols", new_arg_name=None)
 @deprecate_nonkeyword_arguments(version=None, allowed_args=["filepath_or_buffer"])
 @Appender(
     _doc_read_csv_and_table.format(

pandas/tests/io/excel/test_writers.py

@@ -973,9 +973,12 @@ def test_duplicated_columns(self, path):
         tm.assert_frame_equal(result, expected)
 
         # Explicitly, we pass in the parameter.
-        result = pd.read_excel(
-            path, sheet_name="test1", index_col=0, mangle_dupe_cols=True
-        )
+        with tm.assert_produces_warning(
+            FutureWarning, match="the 'mangle_dupe_cols' keyword is deprecated"
+        ):
+            result = pd.read_excel(
+                path, sheet_name="test1", index_col=0, mangle_dupe_cols=True
+            )
         tm.assert_frame_equal(result, expected)
 
         # see gh-11007, gh-10970
@@ -996,8 +999,13 @@ def test_duplicated_columns(self, path):
         tm.assert_frame_equal(result, expected)
 
         msg = "Setting mangle_dupe_cols=False is not supported yet"
-        with pytest.raises(ValueError, match=msg):
-            pd.read_excel(path, sheet_name="test1", header=None, mangle_dupe_cols=False)
+        with tm.assert_produces_warning(
+            FutureWarning, match="the 'mangle_dupe_cols' keyword is deprecated"
+        ):
+            with pytest.raises(ValueError, match=msg):
+                pd.read_excel(
+                    path, sheet_name="test1", header=None, mangle_dupe_cols=False
+                )
 
     def test_swapped_columns(self, path):
         # Test for issue #5427.

pandas/tests/io/parser/test_mangle_dupes.py

@@ -21,7 +21,15 @@ def test_basic(all_parsers, kwargs):
     parser = all_parsers
 
     data = "a,a,b,b,b\n1,2,3,4,5"
-    result = parser.read_csv(StringIO(data), sep=",", **kwargs)
+    if "mangle_dupe_cols" in kwargs:
+        with tm.assert_produces_warning(
+            FutureWarning,
+            match="the 'mangle_dupe_cols' keyword is deprecated",
+            check_stacklevel=False,
+        ):
+            result = parser.read_csv(StringIO(data), sep=",", **kwargs)
+    else:
+        result = parser.read_csv(StringIO(data), sep=",", **kwargs)
 
     expected = DataFrame([[1, 2, 3, 4, 5]], columns=["a", "a.1", "b", "b.1", "b.2"])
     tm.assert_frame_equal(result, expected)

pandas/tests/io/parser/test_unsupported.py

@@ -37,8 +37,11 @@ def test_mangle_dupe_cols_false(self):
         msg = "is not supported"
 
         for engine in ("c", "python"):
-            with pytest.raises(ValueError, match=msg):
-                read_csv(StringIO(data), engine=engine, mangle_dupe_cols=False)
+            with tm.assert_produces_warning(
+                FutureWarning, match="the 'mangle_dupe_cols' keyword is deprecated"
+            ):
+                with pytest.raises(ValueError, match=msg):
+                    read_csv(StringIO(data), engine=engine, mangle_dupe_cols=False)
 
     def test_c_engine(self):
         # see gh-6607