| """This module provides functionality for creating a hierarchy tree and a mapping from ISCO code to node name.""" | |
| import csv | |
| import requests | |
| def create_hierarchy_dict(file: str) -> dict: | |
| """ | |
| 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 dictionaries of their parent codes with distances. | |
| """ | |
| isco_hierarchy = {} | |
| if file.startswith("http://") or file.startswith("https://"): | |
| response = requests.get(file) | |
| lines = response.text.splitlines() | |
| else: | |
| with open(file, newline="") as csvfile: | |
| lines = csvfile.readlines() | |
| reader = csv.DictReader(lines) | |
| for row in reader: | |
| unit_code = row["unit"].zfill(4) | |
| minor_code = unit_code[0:3] | |
| sub_major_code = unit_code[0:2] | |
| major_code = unit_code[0] | |
| # 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 | |
| # Example usage: | |
| # hierarchy_dict = create_hierarchy_dict("ISCO_structure.csv") | |
| # print(hierarchy) | |