suggested edits

Author: debnathshoham

pandas/io/parsers/base_parser.py

@@ -532,6 +532,9 @@ def _convert_to_ndarrays(
             conv_f = None if converters is None else converters.get(c, None)
             if isinstance(dtypes, dict):
                 cast_type = dtypes.get(c, None)
+                if cast_type is None and c.split(".")[-1].isnumeric:
+                    orig_c = ".".join(c.split(".")[:-1])
+                    cast_type = dtypes.get(orig_c, None)
             else:
                 # single dtype or None
                 cast_type = dtypes

pandas/io/parsers/python_parser.py

@@ -25,7 +25,6 @@
 )
 
 from pandas.core.dtypes.common import is_integer
-from pandas.core.dtypes.inference import is_dict_like
 
 from pandas.io.parsers.base_parser import (
     ParserBase,
@@ -81,10 +80,7 @@ def __init__(self, f: FilePathOrBuffer | list, **kwds):
         self.verbose = kwds["verbose"]
         self.converters = kwds["converters"]
 
-        if isinstance(kwds["dtype"], dict):
-            self.dtype = kwds["dtype"].copy()
-        else:
-            self.dtype = kwds["dtype"]
+        self.dtype = kwds["dtype"]
         self.thousands = kwds["thousands"]
         self.decimal = kwds["decimal"]
 
@@ -420,21 +416,13 @@ def _infer_columns(self):
                     counts: DefaultDict = defaultdict(int)
 
                     for i, col in enumerate(this_columns):
-                        old_col = col
                         cur_count = counts[col]
 
                         if cur_count > 0:
                             while cur_count > 0:
                                 counts[col] = cur_count + 1
                                 col = f"{col}.{cur_count}"
                                 cur_count = counts[col]
-                            if (
-                                self.dtype is not None
-                                and is_dict_like(self.dtype)
-                                and self.dtype.get(old_col) is not None
-                                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

pandas/tests/io/data/excel/test_common_headers.ods

@@ -576,8 +576,11 @@ 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()
+        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"  # GH 42462
         tm.assert_frame_equal(result, expected)
 
     def test_reader_spaces(self, read_ext):
@@ -1278,24 +1281,6 @@ def test_ignore_chartsheets_by_int(self, request, read_ext):
         ):
             pd.read_excel("chartsheet" + read_ext, sheet_name=1)
 
-    def test_dtype_dict_unchanged_with_duplicate_columns(self, read_ext):
-        # GH 42462
-
-        filename = "test_common_headers" + read_ext
-        dtype_dict = {"a": str, "b": str, "c": str}
-        dtype_dict_copy = dtype_dict.copy()
-        result = pd.read_excel(filename, dtype=dtype_dict)
-        expected = DataFrame(
-            {
-                "a": ["1", "2", "3"],
-                "a.1": ["1", "2", "3"],
-                "b": ["b1", "b2", "b3"],
-                "c": ["c1", "c2", "c3"],
-            }
-        )
-        assert dtype_dict == dtype_dict_copy, "dtype dict changed"
-        tm.assert_frame_equal(result, expected)
-
 
 class TestExcelFileRead:
     @pytest.fixture(autouse=True)

pandas/tests/io/data/excel/test_common_headers.xls

@@ -245,8 +245,11 @@ 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}
+    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"  # GH 42462
     tm.assert_frame_equal(result, expected)