glam/scripts/enrich_mexico_batch01.py

#!/usr/bin/env python3
"""
Mexican Wikidata Enrichment - Batch 1
Add Wikidata identifiers to 6 national priority institutions.

Institutions:
1. Museo Nacional de Antropología (Q524249, VIAF: 139462066)
2. Museo Nacional de Arte (Q1138147, VIAF: 137951343)
3. Biblioteca Nacional de México (Q5495070, ISIL: MX-MXBN, VIAF: 147873206)
4. Cineteca Nacional (Q1092492)
5. Fototeca Nacional (Q66432183)
6. Instituto Nacional de Antropología e Historia (Q901361, VIAF: 139735572)
"""

import yaml
from datetime import datetime, timezone
from pathlib import Path

# Define enrichment data
BATCH_1_ENRICHMENTS = {
    "Museo Nacional de Antropología": {
        "wikidata": "Q524249",
        "viaf": "139462066",
        "confidence": 0.98,
        "notes": "Verified via SPARQL query and VIAF match"
    },
    "Museo Nacional de Arte (MUNAL)": {
        "wikidata": "Q1138147",
        "viaf": "137951343",
        "confidence": 0.98,
        "notes": "Verified via SPARQL query and VIAF match"
    },
    "Biblioteca Nacional de México": {
        "wikidata": "Q5495070",
        "viaf": "147873206",
        "isil": "MX-MXBN",
        "confidence": 0.98,
        "notes": "Verified via SPARQL query, VIAF, and ISIL registry match"
    },
    "Cineteca Nacional": {
        "wikidata": "Q1092492",
        "confidence": 0.95,
        "notes": "Verified via SPARQL query"
    },
    "Fototeca Nacional": {
        "wikidata": "Q66432183",
        "confidence": 0.95,
        "notes": "Verified via SPARQL query"
    },
    "Instituto Nacional de Antropología e Historia": {
        "wikidata": "Q901361",
        "viaf": "139735572",
        "confidence": 0.98,
        "notes": "Verified via SPARQL query and VIAF match"
    }
}


def add_enrichment_identifiers(institution: dict, enrichment: dict) -> dict:
    """Add Wikidata, VIAF, and ISIL identifiers to institution record."""
    
    # Ensure identifiers list exists
    if 'identifiers' not in institution or institution['identifiers'] is None:
        institution['identifiers'] = []
    
    # Add Wikidata identifier
    if 'wikidata' in enrichment:
        q_number = enrichment['wikidata']
        institution['identifiers'].append({
            'identifier_scheme': 'Wikidata',
            'identifier_value': q_number,
            'identifier_url': f'https://www.wikidata.org/wiki/{q_number}'
        })
    
    # Add VIAF identifier
    if 'viaf' in enrichment:
        viaf_id = enrichment['viaf']
        institution['identifiers'].append({
            'identifier_scheme': 'VIAF',
            'identifier_value': viaf_id,
            'identifier_url': f'https://viaf.org/viaf/{viaf_id}'
        })
    
    # Add ISIL identifier
    if 'isil' in enrichment:
        isil_code = enrichment['isil']
        institution['identifiers'].append({
            'identifier_scheme': 'ISIL',
            'identifier_value': isil_code,
            'identifier_url': f'https://isil.org/{isil_code}'
        })
    
    # Update provenance metadata
    current_time = datetime.now(timezone.utc).isoformat()
    
    if 'provenance' not in institution:
        institution['provenance'] = {}
    
    # Add enrichment metadata
    if 'enrichment_history' not in institution['provenance']:
        institution['provenance']['enrichment_history'] = []
    
    enrichment_entry = {
        'enrichment_date': current_time,
        'enrichment_method': 'Wikidata SPARQL query + VIAF cross-reference',
        'identifiers_added': [],
        'confidence_score': enrichment['confidence'],
        'notes': enrichment['notes']
    }
    
    if 'wikidata' in enrichment:
        enrichment_entry['identifiers_added'].append(f"Wikidata:{enrichment['wikidata']}")
    if 'viaf' in enrichment:
        enrichment_entry['identifiers_added'].append(f"VIAF:{enrichment['viaf']}")
    if 'isil' in enrichment:
        enrichment_entry['identifiers_added'].append(f"ISIL:{enrichment['isil']}")
    
    institution['provenance']['enrichment_history'].append(enrichment_entry)
    
    return institution


def main():
    """Main enrichment workflow."""
    
    # Load YAML file
    yaml_path = Path('/Users/kempersc/apps/glam/data/instances/mexico/mexican_institutions_geocoded.yaml')
    
    print("Loading Mexican institutions YAML file...")
    with open(yaml_path, 'r', encoding='utf-8') as f:
        institutions = yaml.safe_load(f)
    
    print(f"Loaded {len(institutions)} institutions")
    
    # Track enrichment statistics
    enriched_count = 0
    not_found = []
    
    # Enrich each institution
    for institution in institutions:
        institution_name = institution.get('name', '')
        
        if institution_name in BATCH_1_ENRICHMENTS:
            enrichment = BATCH_1_ENRICHMENTS[institution_name]
            
            print(f"\nEnriching: {institution_name}")
            print(f"  - Wikidata: {enrichment.get('wikidata', 'N/A')}")
            print(f"  - VIAF: {enrichment.get('viaf', 'N/A')}")
            print(f"  - ISIL: {enrichment.get('isil', 'N/A')}")
            
            institution = add_enrichment_identifiers(institution, enrichment)
            enriched_count += 1
    
    # Check for missing institutions
    for name in BATCH_1_ENRICHMENTS.keys():
        found = any(inst.get('name') == name for inst in institutions)
        if not found:
            not_found.append(name)
    
    if not_found:
        print("\n⚠️  Warning: Could not find these institutions in YAML:")
        for name in not_found:
            print(f"  - {name}")
    
    # Save enriched YAML
    print(f"\n✅ Enriched {enriched_count} institutions")
    print(f"Writing to {yaml_path}...")
    
    with open(yaml_path, 'w', encoding='utf-8') as f:
        yaml.dump(institutions, f, 
                  default_flow_style=False, 
                  allow_unicode=True,
                  sort_keys=False,
                  width=1000)
    
    print("✅ Batch 1 enrichment complete!")
    
    # Generate statistics
    total_wikidata = sum(1 for inst in institutions 
                         if any(i.get('identifier_scheme') == 'Wikidata' 
                               for i in inst.get('identifiers', [])))
    
    coverage = (total_wikidata / len(institutions)) * 100
    
    print(f"\n📊 Current Wikidata Coverage:")
    print(f"   {total_wikidata}/{len(institutions)} institutions ({coverage:.1f}%)")


if __name__ == '__main__':
    main()