code/src/data_preprocessing.py

@@ -35,8 +35,8 @@ def complement_pairs(n, prefix, extension):
         if a != orig_a:                # skip original a
             yield (filename, [a, a + 25]) # use yield instead of return to return a generator of tuples
 
-def generate_df_tuples(total_dfs, prefix, extension, first_col_start, last_col_offset, 
-                      group_size=5, special_groups=None, group=True):
+def generate_df_tuples(prefix: str, total_dfs: int=30, extension: str="TXT", first_col_start: int=1, last_col_offset: int=25, 
+                      group_size: int=5, special_groups: list=None, group: bool=True):
     """
     Generate a structured list of tuples containing DataFrame references and column indices.