src/etl/hierarchy_parser.py

#!/usr/bin/env python3
"""
Kit Hierarchy Parser - Converts CSV hierarchy data to optimized formats

This module provides functions to:
1. Parse Kit_Composition_and_relation.csv
2. Generate JSON hierarchy structure  
3. Create production order CSV
4. Build DAG for optimization constraints
"""

import pandas as pd
import json
from typing import Dict, List, Tuple, Set
from collections import defaultdict, deque


class KitHierarchyParser:
    """
    Parses kit composition data and creates hierarchy structures
    for production order optimization.
    """
    
    def __init__(self, csv_path: str = "data/real_data_excel/converted_csv/Kit_Composition_and_relation.csv"):
        self.csv_path = csv_path
        self.df = None
        self.hierarchy_json = {}
        self.production_order_csv = []
        self.dependency_graph = {'nodes': set(), 'edges': set()}
        
    def load_data(self):
        """Load and clean the CSV data"""
        self.df = pd.read_csv(self.csv_path)
        print(f"Loaded {len(self.df)} rows from {self.csv_path}")
        
    def parse_hierarchy(self) -> Dict:
        """
        Parse the hierarchy from CSV into JSON structure
        Returns: Nested dictionary representing the hierarchy
        """
        if self.df is None:
            self.load_data()
            
        # Get unique relationships
        relationships = self.df[['Master Kit', 'Master Kit  Description', 
                                'Sub kit', 'Sub kit description', 
                                'Prepack', 'Prepack Description']].drop_duplicates()
        
        hierarchy = defaultdict(lambda: {
            'name': '',
            'type': 'master',
            'subkits': defaultdict(lambda: {
                'name': '',
                'type': 'subkit', 
                'prepacks': [],
                'dependencies': []
            }),
            'dependencies': []
        })
        
        for _, row in relationships.iterrows():
            master_id = row['Master Kit']
            master_desc = row['Master Kit  Description']
            subkit_id = row['Sub kit'] 
            subkit_desc = row['Sub kit description']
            prepack_id = row['Prepack']
            prepack_desc = row['Prepack Description']
            
            if pd.notna(master_id):
                # Set master info
                hierarchy[master_id]['name'] = master_desc if pd.notna(master_desc) else ''
                
                if pd.notna(subkit_id):
                    # Set subkit info
                    hierarchy[master_id]['subkits'][subkit_id]['name'] = subkit_desc if pd.notna(subkit_desc) else ''
                    
                    # Add subkit to master dependencies
                    if subkit_id not in hierarchy[master_id]['dependencies']:
                        hierarchy[master_id]['dependencies'].append(subkit_id)
                    
                    if pd.notna(prepack_id):
                        # Set prepack info
                        if prepack_id not in hierarchy[master_id]['subkits'][subkit_id]['prepacks']:
                            hierarchy[master_id]['subkits'][subkit_id]['prepacks'].append(prepack_id)
                        
                        # Add prepack to subkit dependencies
                        if prepack_id not in hierarchy[master_id]['subkits'][subkit_id]['dependencies']:
                            hierarchy[master_id]['subkits'][subkit_id]['dependencies'].append(prepack_id)
                            
                elif pd.notna(prepack_id):
                    # Handle direct master-prepack relationship (no subkit)
                    # Add direct_prepacks list to hierarchy if it doesn't exist
                    if 'direct_prepacks' not in hierarchy[master_id]:
                        hierarchy[master_id]['direct_prepacks'] = []
                    
                    # Add prepack directly to master
                    if prepack_id not in hierarchy[master_id]['direct_prepacks']:
                        hierarchy[master_id]['direct_prepacks'].append(prepack_id)
                    
                    # Add prepack to master dependencies
                    if prepack_id not in hierarchy[master_id]['dependencies']:
                        hierarchy[master_id]['dependencies'].append(prepack_id)
        
        # Convert defaultdict to regular dict for JSON serialization
        self.hierarchy_json = json.loads(json.dumps(hierarchy, default=dict))
        return self.hierarchy_json



def main():
    """Demo the hierarchy parser"""
    parser = KitHierarchyParser()
    
    print("🔄 Parsing kit hierarchy...")
    hierarchy = parser.parse_hierarchy()

    #export to json
    with open('data/hierarchy_exports/kit_hierarchy.json', 'w') as f:
        json.dump(hierarchy, f,indent=4)
    
    print(f"📊 Found {len(hierarchy)} master kits")
    


if __name__ == "__main__":
    main()