Backport PR pandas-dev#42508: read_excel() modifies provided types dict when accessing file with duplicate column

Author: debnathshoham

doc/source/whatsnew/v1.3.2.rst

@@ -30,6 +30,7 @@ Fixed regressions
 
 Bug fixes
 ~~~~~~~~~
+- Bug in :meth:`pandas.read_excel` modifies the dtypes dictionary when reading a file with duplicate columns (:issue:`42462`)
 - 1D slices over extension types turn into N-dimensional slices over ExtensionArrays (:issue:`42430`)
 - :meth:`.Styler.hide_columns` now hides the index name header row as well as column headers (:issue:`42101`)
 

pandas/io/parsers/python_parser.py

@@ -4,6 +4,7 @@
     abc,
     defaultdict,
 )
+from copy import copy
 import csv
 from io import StringIO
 import re
@@ -81,7 +82,7 @@ def __init__(self, f: FilePathOrBuffer | list, **kwds):
         self.verbose = kwds["verbose"]
         self.converters = kwds["converters"]
 
-        self.dtype = kwds["dtype"]
+        self.dtype = copy(kwds["dtype"])
         self.thousands = kwds["thousands"]
         self.decimal = kwds["decimal"]
 
@@ -432,7 +433,6 @@ def _infer_columns(self):
                                 and self.dtype.get(col) is None
                             ):
                                 self.dtype.update({col: self.dtype.get(old_col)})
-
                         this_columns[i] = col
                         counts[col] = cur_count + 1
                 elif have_mi_columns:

pandas/tests/io/excel/test_readers.py

@@ -576,8 +576,12 @@ def test_reader_dtype_str(self, read_ext, dtype, expected):
     def test_dtype_mangle_dup_cols(self, read_ext, dtypes, exp_value):
         # GH#35211
         basename = "df_mangle_dup_col_dtypes"
-        result = pd.read_excel(basename + read_ext, dtype={"a": str, **dtypes})
+        dtype_dict = {"a": str, **dtypes}
+        dtype_dict_copy = dtype_dict.copy()
+        # GH#42462
+        result = pd.read_excel(basename + read_ext, dtype=dtype_dict)
         expected = DataFrame({"a": ["1"], "a.1": [exp_value]})
+        assert dtype_dict == dtype_dict_copy, "dtype dict changed"
         tm.assert_frame_equal(result, expected)
 
     def test_reader_spaces(self, read_ext):

pandas/tests/io/parser/dtypes/test_dtypes_basic.py

@@ -245,8 +245,12 @@ def test_dtype_mangle_dup_cols(all_parsers, dtypes, exp_value):
     # GH#35211
     parser = all_parsers
     data = """a,a\n1,1"""
-    result = parser.read_csv(StringIO(data), dtype={"a": str, **dtypes})
+    dtype_dict = {"a": str, **dtypes}
+    # GH#42462
+    dtype_dict_copy = dtype_dict.copy()
+    result = parser.read_csv(StringIO(data), dtype=dtype_dict)
     expected = DataFrame({"a": ["1"], "a.1": [exp_value]})
+    assert dtype_dict == dtype_dict_copy, "dtype dict changed"
     tm.assert_frame_equal(result, expected)