add pyarrow autogenerated prefix

hedeershowk · hedeershowk · commit cf5288c41c4c · 2023-09-12T23:53:45.000-04:00
diff --git a/pandas/io/parsers/arrow_parser_wrapper.py b/pandas/io/parsers/arrow_parser_wrapper.py
@@ -100,6 +100,12 @@ def _get_pyarrow_options(self) -> None:
             )
         }
         self.convert_options["strings_can_be_null"] = "" in self.kwds["null_values"]
+        # autogenerated column names are prefixed with 'f' in pyarrow.csv
+        if self.header is None and "include_columns" in self.convert_options:
+            self.convert_options["include_columns"] = [
+                f"f{n}" for n in self.convert_options["include_columns"]
+            ]
+
         self.read_options = {
             "autogenerate_column_names": self.header is None,
             "skip_rows": self.header

Original file line number	Diff line number	Diff line change
`@@ -100,6 +100,12 @@ def _get_pyarrow_options(self) -> None:`
`100`	`100`	`)`
`101`	`101`	`}`
`102`	`102`	`self.convert_options["strings_can_be_null"] = "" in self.kwds["null_values"]`
	`103`	`+ # autogenerated column names are prefixed with 'f' in pyarrow.csv`
	`104`	`+ if self.header is None and "include_columns" in self.convert_options:`
	`105`	`+ self.convert_options["include_columns"] = [`
	`106`	`+ f"f{n}" for n in self.convert_options["include_columns"]`
	`107`	`+ ]`
	`108`	`+`
`103`	`109`	`self.read_options = {`
`104`	`110`	`"autogenerate_column_names": self.header is None,`
`105`	`111`	`"skip_rows": self.header`