Refactored create_hierarchy_dict function to include weights for parent nodes in ISCO-08 structure

isco.py

@@ -6,15 +6,14 @@ import requests
 
 def create_hierarchy_dict(file: str) -> dict:
     """
-    Creates a dictionary where keys are nodes and values are sets of parent nodes representing the group level hierarchy of the ISCO-08 structure.
-    The function assumes that the input CSV file has a column named 'unit' with the 4-digit ISCO-08 codes.
-    A csv file with the ISCO-08 structure can be downloaded from the International Labour Organization (ILO) at [https://www.ilo.org/ilostat-files/ISCO/newdocs-08-2021/ISCO-08/ISCO-08 EN.csv](https://www.ilo.org/ilostat-files/ISCO/newdocs-08-2021/ISCO-08/ISCO-08%20EN.csv)
+    Creates a dictionary where keys are nodes and values are dictionaries of their parent nodes with distance as weights,
+    representing the group level hierarchy of the ISCO-08 structure.
 
     Args:
     - file: A string representing the path to the CSV file containing the 4-digit ISCO-08 codes. It can be a local path or a web URL.
 
     Returns:
-    - A dictionary where keys are ISCO-08 unit codes and values are sets of their parent codes.
+    - A dictionary where keys are ISCO-08 unit codes and values are dictionaries of their parent codes with distances.
     """
     isco_hierarchy = {}
 
@@ -31,7 +30,12 @@ def create_hierarchy_dict(file: str) -> dict:
         minor_code = unit_code[0:3]
         sub_major_code = unit_code[0:2]
         major_code = unit_code[0]
-        isco_hierarchy[unit_code] = {minor_code, major_code, sub_major_code}
+
+        # Assign weights, higher for closer ancestors
+        weights = {minor_code: 0.75, sub_major_code: 0.5, major_code: 0.25}
+
+        # Store ancestors with their weights
+        isco_hierarchy[unit_code] = weights
 
     return isco_hierarchy