isco.py

"""This module provides functionality for creating a hierarchy tree and a mapping from ISCO code to node name."""

import csv


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)

    Args:
    - file: A string representing the path to the CSV file containing the 4-digit ISCO-08 codes.

    Returns:
    - A dictionary where keys are ISCO-08 unit codes and values are sets of their parent codes.
    """
    isco_hierarchy = {}

    with open(file, newline="") as csvfile:
        reader = csv.DictReader(csvfile)
        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]
            isco_hierarchy[unit_code] = {minor_code, major_code, sub_major_code}

    return isco_hierarchy


# Example usage:
# hierarchy_dict = create_hierarchy_dict("ISCO_structure.csv")
# print(hierarchy)