PERF: Improve conversion in read_csv when string option is set (#56046)

pandas-dev · Nov 30, 2023 · 4f080b8 · 4f080b8
1 parent eb7a8c8
commit 4f080b8
Showing 1 changed file with 9 additions and 1 deletion.
diff --git a/pandas/io/parsers/arrow_parser_wrapper.py b/pandas/io/parsers/arrow_parser_wrapper.py
@@ -295,7 +295,15 @@ def read(self) -> DataFrame:
             dtype_mapping[pa.null()] = pd.Int64Dtype()
             frame = table.to_pandas(types_mapper=dtype_mapping.get)
         elif using_pyarrow_string_dtype():
-            frame = table.to_pandas(types_mapper=arrow_string_types_mapper())
+
+            def types_mapper(dtype):
+                dtype_dict = self.kwds["dtype"]
+                if dtype_dict is not None and dtype_dict.get(dtype, None) is not None:
+                    return dtype_dict.get(dtype)
+                return arrow_string_types_mapper()(dtype)
+
+            frame = table.to_pandas(types_mapper=types_mapper)
+
         else:
             if isinstance(self.kwds.get("dtype"), dict):
                 frame = table.to_pandas(types_mapper=self.kwds["dtype"].get)