refactor DataHarmonizer

alphastats/DataSet.py

@@ -65,7 +65,9 @@ def __init__(
         self._check_loader(loader=loader)
 
         # fill data from loader
-        self.rawinput: pd.DataFrame = DataHarmonizer(loader).get_rawinput()
+        self.rawinput: pd.DataFrame = DataHarmonizer(loader).get_harmonized_rawinput(
+            loader.rawinput
+        )
         self.filter_columns: List[str] = loader.filter_columns
 
         self.software: str = loader.software

alphastats/dataset_harmonizer.py

@@ -10,17 +10,17 @@ class DataHarmonizer:
     """Harmonize input data to a common format."""
 
     def __init__(self, loader: BaseLoader):
-        self._rawinput = loader.rawinput
-        self._index_column = loader.index_column
+        self._rename_dict = {loader.index_column: Cols.INDEX}
 
-    def get_rawinput(self) -> pd.DataFrame:
+    def get_harmonized_rawinput(self, rawinput: pd.DataFrame) -> pd.DataFrame:
         """Harmonize the rawinput data to a common format."""
-        if Cols.INDEX in self._rawinput.columns:
-            raise ValueError(
-                f"Column name {Cols.INDEX} already exists in rawinput. Please rename the column."
-            )
+        for target_name in self._rename_dict.values():
+            if target_name in rawinput.columns:
+                raise ValueError(
+                    f"Column name {target_name} already exists in rawinput. Please rename the column."
+                )
 
-        return self._rawinput.rename(
-            columns={self._index_column: Cols.INDEX},
+        return rawinput.rename(
+            columns=self._rename_dict,
             errors="raise",
         )