e5a532a8bc
- Introduced `test_nlp_extractor.py` with unit tests for the InstitutionExtractor, covering various extraction patterns (ISIL, Wikidata, VIAF, city names) and ensuring proper classification of institutions (museum, library, archive). - Added tests for extracted entities and result handling to validate the extraction process. - Created `test_partnership_rdf_integration.py` to validate the end-to-end process of extracting partnerships from a conversation and exporting them to RDF format. - Implemented tests for temporal properties in partnerships and ensured compliance with W3C Organization Ontology patterns. - Verified that extracted partnerships are correctly linked with PROV-O provenance metadata.
500 lines
18 KiB
Python
Executable file
500 lines
18 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
"""
|
|
Enrich Latin American institutions using fuzzy name matching in Wikidata.
|
|
|
|
This script addresses low coverage in Brazil (1%), Mexico (21%), and Chile (29%)
|
|
by querying Wikidata for heritage institutions using name-based searches.
|
|
|
|
Strategy:
|
|
1. Find institutions without Wikidata IDs in target countries
|
|
2. Query Wikidata for museums/archives/libraries in each country
|
|
3. Fuzzy match names (normalized)
|
|
4. Apply high-confidence matches (>0.85)
|
|
|
|
Countries:
|
|
- Brazil (BR, Q155): 1% → 15-25% expected
|
|
- Mexico (MX, Q96): 21% → 35-45% expected
|
|
- Chile (CL, Q298): 29% → 40-50% expected
|
|
"""
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
from typing import Any, Optional
|
|
from datetime import datetime, timezone
|
|
import time
|
|
import yaml
|
|
from difflib import SequenceMatcher
|
|
import re
|
|
|
|
sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
|
|
|
|
from SPARQLWrapper import SPARQLWrapper, JSON as SPARQL_JSON # type: ignore
|
|
|
|
|
|
# Country configurations
|
|
COUNTRIES = {
|
|
'BR': {'name': 'Brazil', 'qid': 'Q155', 'flag': '🇧🇷'},
|
|
'MX': {'name': 'Mexico', 'qid': 'Q96', 'flag': '🇲🇽'},
|
|
'CL': {'name': 'Chile', 'qid': 'Q298', 'flag': '🇨🇱'}
|
|
}
|
|
|
|
|
|
def normalize_name(name: str) -> str:
|
|
"""Normalize institution name for fuzzy matching."""
|
|
# Lowercase
|
|
name = name.lower()
|
|
|
|
# Remove common prefixes/suffixes (multilingual)
|
|
# Spanish
|
|
name = re.sub(r'^(fundación|museo|biblioteca|archivo|centro)\s+', '', name)
|
|
name = re.sub(r'\s+(museo|biblioteca|archivo|nacional|regional|municipal)$', '', name)
|
|
# Portuguese
|
|
name = re.sub(r'^(fundação|museu|biblioteca|arquivo|centro)\s+', '', name)
|
|
name = re.sub(r'\s+(museu|biblioteca|arquivo|nacional|estadual|municipal)$', '', name)
|
|
# English
|
|
name = re.sub(r'^(foundation|museum|library|archive|center|centre)\s+', '', name)
|
|
name = re.sub(r'\s+(museum|library|archive|national|regional|municipal)$', '', name)
|
|
|
|
# Remove punctuation
|
|
name = re.sub(r'[^\w\s]', ' ', name)
|
|
|
|
# Normalize whitespace
|
|
name = ' '.join(name.split())
|
|
|
|
return name
|
|
|
|
|
|
def similarity_score(name1: str, name2: str) -> float:
|
|
"""Calculate similarity between two names (0-1)."""
|
|
norm1 = normalize_name(name1)
|
|
norm2 = normalize_name(name2)
|
|
return SequenceMatcher(None, norm1, norm2).ratio()
|
|
|
|
|
|
def query_wikidata_institutions(
|
|
sparql: SPARQLWrapper,
|
|
country_qid: str,
|
|
institution_types: list[str]
|
|
) -> dict[str, dict[str, Any]]:
|
|
"""
|
|
Query Wikidata for heritage institutions in a specific country.
|
|
|
|
country_qid: Wikidata QID for country (Q155=Brazil, Q96=Mexico, Q298=Chile)
|
|
institution_types: List of Wikidata QIDs for institution types
|
|
Q33506 - museum
|
|
Q7075 - library
|
|
Q166118 - archive
|
|
"""
|
|
|
|
types_values = " ".join(f"wd:{qid}" for qid in institution_types)
|
|
|
|
query = f"""
|
|
SELECT DISTINCT ?item ?itemLabel ?itemDescription ?isil ?viaf ?coords ?website ?inception ?typeLabel
|
|
WHERE {{
|
|
VALUES ?type {{ {types_values} }}
|
|
|
|
?item wdt:P31 ?type . # instance of museum/library/archive
|
|
?item wdt:P17 wd:{country_qid} . # country
|
|
|
|
OPTIONAL {{ ?item wdt:P791 ?isil . }}
|
|
OPTIONAL {{ ?item wdt:P214 ?viaf . }}
|
|
OPTIONAL {{ ?item wdt:P625 ?coords . }}
|
|
OPTIONAL {{ ?item wdt:P856 ?website . }}
|
|
OPTIONAL {{ ?item wdt:P571 ?inception . }}
|
|
|
|
SERVICE wikibase:label {{ bd:serviceParam wikibase:language "es,pt,en" . }}
|
|
}}
|
|
LIMIT 2000
|
|
"""
|
|
|
|
sparql.setQuery(query)
|
|
|
|
try:
|
|
raw_results = sparql.query().convert()
|
|
bindings = raw_results.get("results", {}).get("bindings", []) if isinstance(raw_results, dict) else []
|
|
|
|
# Parse results into dict keyed by QID
|
|
results = {}
|
|
for binding in bindings:
|
|
item_uri = binding.get("item", {}).get("value", "")
|
|
qid = item_uri.split("/")[-1] if item_uri else None
|
|
|
|
if not qid or not qid.startswith("Q"):
|
|
continue
|
|
|
|
result = {
|
|
"qid": qid,
|
|
"name": binding.get("itemLabel", {}).get("value", ""),
|
|
"description": binding.get("itemDescription", {}).get("value", ""),
|
|
"type": binding.get("typeLabel", {}).get("value", ""),
|
|
"identifiers": {}
|
|
}
|
|
|
|
if "isil" in binding:
|
|
result["identifiers"]["ISIL"] = binding["isil"]["value"]
|
|
|
|
if "viaf" in binding:
|
|
result["identifiers"]["VIAF"] = binding["viaf"]["value"]
|
|
|
|
if "website" in binding:
|
|
result["identifiers"]["Website"] = binding["website"]["value"]
|
|
|
|
if "inception" in binding:
|
|
result["founding_date"] = binding["inception"]["value"].split("T")[0]
|
|
|
|
if "coords" in binding:
|
|
coords_str = binding["coords"]["value"]
|
|
if coords_str.startswith("Point("):
|
|
lon, lat = coords_str[6:-1].split()
|
|
result["latitude"] = float(lat)
|
|
result["longitude"] = float(lon)
|
|
|
|
results[qid] = result
|
|
|
|
return results
|
|
|
|
except Exception as e:
|
|
print(f"\n❌ Error querying Wikidata: {e}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
return {}
|
|
|
|
|
|
def institution_type_compatible(inst_name: str, wd_type: str) -> bool:
|
|
"""Check if institution types are compatible (avoid museum/archive mismatches)."""
|
|
inst_lower = inst_name.lower()
|
|
wd_lower = wd_type.lower()
|
|
|
|
# Define type keywords (multilingual)
|
|
museum_keywords = ['museum', 'museo', 'museu', 'musée']
|
|
archive_keywords = ['archief', 'archive', 'archivo', 'arquivo']
|
|
library_keywords = ['bibliotheek', 'library', 'biblioteca', 'bibliothèque']
|
|
|
|
# Check if institution name contains type keyword
|
|
inst_is_museum = any(kw in inst_lower for kw in museum_keywords)
|
|
inst_is_archive = any(kw in inst_lower for kw in archive_keywords)
|
|
inst_is_library = any(kw in inst_lower for kw in library_keywords)
|
|
|
|
# Check if Wikidata type contains type keyword
|
|
wd_is_museum = any(kw in wd_lower for kw in museum_keywords)
|
|
wd_is_archive = any(kw in wd_lower for kw in archive_keywords)
|
|
wd_is_library = any(kw in wd_lower for kw in library_keywords)
|
|
|
|
# If both have explicit types, they must match
|
|
if inst_is_museum and not wd_is_museum:
|
|
return False
|
|
if inst_is_archive and not wd_is_archive:
|
|
return False
|
|
if inst_is_library and not wd_is_library:
|
|
return False
|
|
|
|
return True
|
|
|
|
|
|
def fuzzy_match_institutions(
|
|
institutions: list[dict[str, Any]],
|
|
wikidata_results: dict[str, dict[str, Any]],
|
|
threshold: float = 0.85
|
|
) -> list[tuple[int, str, float, dict[str, Any]]]:
|
|
"""
|
|
Fuzzy match institutions with Wikidata results.
|
|
|
|
Returns: List of (institution_idx, qid, confidence_score, wd_data)
|
|
"""
|
|
matches = []
|
|
|
|
for idx, inst in enumerate(institutions):
|
|
inst_name = inst.get("name", "")
|
|
if not inst_name:
|
|
continue
|
|
|
|
# Skip if already has real Wikidata ID
|
|
has_wikidata = any(
|
|
id_obj.get("identifier_scheme") == "Wikidata" and
|
|
id_obj.get("identifier_value", "").startswith("Q") and
|
|
int(id_obj.get("identifier_value", "Q999999999")[1:]) < 100000000
|
|
for id_obj in inst.get("identifiers", [])
|
|
)
|
|
if has_wikidata:
|
|
continue
|
|
|
|
# Find best match
|
|
best_score = 0.0
|
|
best_qid = None
|
|
best_data = None
|
|
|
|
for qid, wd_data in wikidata_results.items():
|
|
wd_name = wd_data.get("name", "")
|
|
wd_type = wd_data.get("type", "")
|
|
if not wd_name:
|
|
continue
|
|
|
|
# Check type compatibility
|
|
if not institution_type_compatible(inst_name, wd_type):
|
|
continue
|
|
|
|
score = similarity_score(inst_name, wd_name)
|
|
if score > best_score:
|
|
best_score = score
|
|
best_qid = qid
|
|
best_data = wd_data
|
|
|
|
# Only include matches above threshold
|
|
if best_score >= threshold and best_qid and best_data:
|
|
matches.append((idx, best_qid, best_score, best_data))
|
|
|
|
return matches
|
|
|
|
|
|
def enrich_institution(inst: dict[str, Any], wd_data: dict[str, Any]) -> bool:
|
|
"""Enrich an institution with Wikidata data. Returns True if enriched."""
|
|
enriched = False
|
|
|
|
if "identifiers" not in inst or not inst["identifiers"]:
|
|
inst["identifiers"] = []
|
|
|
|
identifiers_list = inst["identifiers"]
|
|
existing_schemes = {i.get("identifier_scheme", "") for i in identifiers_list if isinstance(i, dict)}
|
|
|
|
# Add Wikidata ID (or replace synthetic Q-number)
|
|
wikidata_idx = None
|
|
for i, id_obj in enumerate(identifiers_list):
|
|
if isinstance(id_obj, dict) and id_obj.get("identifier_scheme") == "Wikidata":
|
|
wikidata_idx = i
|
|
break
|
|
|
|
if wikidata_idx is not None:
|
|
# Replace existing (possibly synthetic) Wikidata ID
|
|
old_value = identifiers_list[wikidata_idx].get("identifier_value", "")
|
|
if old_value != wd_data["qid"]:
|
|
identifiers_list[wikidata_idx] = {
|
|
"identifier_scheme": "Wikidata",
|
|
"identifier_value": wd_data["qid"],
|
|
"identifier_url": f"https://www.wikidata.org/wiki/{wd_data['qid']}"
|
|
}
|
|
enriched = True
|
|
else:
|
|
# Add new Wikidata ID
|
|
identifiers_list.append({
|
|
"identifier_scheme": "Wikidata",
|
|
"identifier_value": wd_data["qid"],
|
|
"identifier_url": f"https://www.wikidata.org/wiki/{wd_data['qid']}"
|
|
})
|
|
enriched = True
|
|
|
|
# Add other identifiers
|
|
wd_identifiers = wd_data.get("identifiers", {})
|
|
for scheme, value in wd_identifiers.items():
|
|
if scheme not in existing_schemes:
|
|
id_obj = {
|
|
"identifier_scheme": scheme,
|
|
"identifier_value": value
|
|
}
|
|
|
|
if scheme == "VIAF":
|
|
id_obj["identifier_url"] = f"https://viaf.org/viaf/{value}"
|
|
elif scheme == "Website":
|
|
id_obj["identifier_url"] = value
|
|
|
|
identifiers_list.append(id_obj)
|
|
enriched = True
|
|
|
|
# Add founding date
|
|
if "founding_date" in wd_data and not inst.get("founding_date"):
|
|
inst["founding_date"] = wd_data["founding_date"]
|
|
enriched = True
|
|
|
|
# Add coordinates if missing
|
|
if "latitude" in wd_data and "longitude" in wd_data:
|
|
locations = inst.get("locations", [])
|
|
if isinstance(locations, list) and len(locations) > 0:
|
|
first_loc = locations[0]
|
|
if isinstance(first_loc, dict) and first_loc.get("latitude") is None:
|
|
first_loc["latitude"] = wd_data["latitude"]
|
|
first_loc["longitude"] = wd_data["longitude"]
|
|
enriched = True
|
|
|
|
# Update provenance
|
|
if enriched:
|
|
prov = inst.get("provenance", {})
|
|
if isinstance(prov, dict):
|
|
existing_method = prov.get("extraction_method", "")
|
|
if existing_method:
|
|
prov["extraction_method"] = f"{existing_method} + Wikidata enrichment (fuzzy name match)"
|
|
else:
|
|
prov["extraction_method"] = "Wikidata enrichment (fuzzy name match)"
|
|
|
|
return enriched
|
|
|
|
|
|
def process_country(
|
|
institutions: list[dict[str, Any]],
|
|
country_code: str,
|
|
sparql: SPARQLWrapper
|
|
) -> tuple[int, int]:
|
|
"""
|
|
Process a single country's institutions.
|
|
|
|
Returns: (institutions_without_wikidata, enriched_count)
|
|
"""
|
|
country_info = COUNTRIES[country_code]
|
|
|
|
print(f"\n{'='*80}")
|
|
print(f"{country_info['flag']} {country_info['name'].upper()} ({country_code})")
|
|
print(f"{'='*80}\n")
|
|
|
|
# Filter institutions for this country
|
|
country_institutions_idx = [
|
|
idx for idx, inst in enumerate(institutions)
|
|
if inst.get('locations', [{}])[0].get('country') == country_code
|
|
]
|
|
|
|
print(f"📊 Found {len(country_institutions_idx):,} {country_info['name']} institutions")
|
|
|
|
# Count those without real Wikidata
|
|
without_wikidata = [
|
|
idx for idx in country_institutions_idx
|
|
if not any(
|
|
id_obj.get("identifier_scheme") == "Wikidata" and
|
|
id_obj.get("identifier_value", "").startswith("Q") and
|
|
int(id_obj.get("identifier_value", "Q999999999")[1:]) < 100000000
|
|
for id_obj in institutions[idx].get("identifiers", [])
|
|
)
|
|
]
|
|
|
|
current_coverage = (len(country_institutions_idx) - len(without_wikidata)) / len(country_institutions_idx) * 100 if country_institutions_idx else 0
|
|
print(f"✅ With Wikidata: {len(country_institutions_idx) - len(without_wikidata):,} ({current_coverage:.1f}%)")
|
|
print(f"❓ Without Wikidata: {len(without_wikidata):,}\n")
|
|
|
|
if not without_wikidata:
|
|
print("✨ All institutions already have Wikidata IDs!")
|
|
return 0, 0
|
|
|
|
# Query Wikidata
|
|
print(f"🔍 Querying Wikidata for {country_info['name']} museums, libraries, and archives...")
|
|
print(" (This may take 30-60 seconds)\n")
|
|
|
|
institution_types = ["Q33506", "Q7075", "Q166118"] # museum, library, archive
|
|
wikidata_results = query_wikidata_institutions(sparql, country_info['qid'], institution_types)
|
|
|
|
print(f"✅ Found {len(wikidata_results):,} {country_info['name']} institutions in Wikidata\n")
|
|
|
|
if not wikidata_results:
|
|
print("⚠️ No Wikidata results, skipping fuzzy matching")
|
|
return len(without_wikidata), 0
|
|
|
|
# Fuzzy match
|
|
print("🔗 Fuzzy matching names (threshold: 0.85)...\n")
|
|
|
|
country_insts = [institutions[idx] for idx in without_wikidata]
|
|
matches = fuzzy_match_institutions(country_insts, wikidata_results, threshold=0.85)
|
|
|
|
print(f"✨ Found {len(matches):,} high-confidence matches\n")
|
|
|
|
# Show sample matches
|
|
if matches:
|
|
print(f"{'='*80}")
|
|
print(f"📋 SAMPLE MATCHES (Top 5)")
|
|
print(f"{'='*80}")
|
|
for i, (local_idx, qid, score, wd_data) in enumerate(matches[:5]):
|
|
inst = country_insts[local_idx]
|
|
print(f"\n{i+1}. Confidence: {score:.3f}")
|
|
print(f" Local: {inst.get('name')} ({inst.get('locations', [{}])[0].get('city', 'Unknown')})")
|
|
print(f" Wikidata: {wd_data.get('name')} ({wd_data.get('qid')})")
|
|
print(f" Type: {wd_data.get('type', 'Unknown')}")
|
|
if "ISIL" in wd_data.get("identifiers", {}):
|
|
print(f" ISIL: {wd_data['identifiers']['ISIL']}")
|
|
|
|
print(f"\n{'='*80}\n")
|
|
|
|
# Apply all matches
|
|
print("✅ Applying all matches...\n")
|
|
enriched_count = 0
|
|
|
|
for local_idx, qid, score, wd_data in matches:
|
|
global_idx = without_wikidata[local_idx]
|
|
if enrich_institution(institutions[global_idx], wd_data):
|
|
enriched_count += 1
|
|
|
|
new_coverage = (len(country_institutions_idx) - len(without_wikidata) + enriched_count) / len(country_institutions_idx) * 100 if country_institutions_idx else 0
|
|
print(f"✨ Enriched {enriched_count:,} institutions")
|
|
print(f"📈 Coverage: {current_coverage:.1f}% → {new_coverage:.1f}%\n")
|
|
|
|
return len(without_wikidata), enriched_count
|
|
else:
|
|
print("❌ No matches found. Try lowering threshold.\n")
|
|
return len(without_wikidata), 0
|
|
|
|
|
|
def main():
|
|
base_dir = Path(__file__).parent.parent
|
|
input_file = base_dir / "data" / "instances" / "global" / "global_heritage_institutions_wikidata_enriched.yaml"
|
|
output_file = base_dir / "data" / "instances" / "global" / "global_heritage_institutions_latam_enriched.yaml"
|
|
|
|
print("="*80)
|
|
print("🌎 LATIN AMERICA INSTITUTIONS FUZZY MATCHING")
|
|
print("="*80)
|
|
print(f"\n📖 Loading dataset...\n")
|
|
|
|
start_time = time.time()
|
|
|
|
with open(input_file, 'r', encoding='utf-8') as f:
|
|
institutions = yaml.safe_load(f)
|
|
|
|
load_time = time.time() - start_time
|
|
print(f"✅ Loaded {len(institutions):,} institutions in {load_time:.1f}s")
|
|
|
|
# Setup SPARQL
|
|
sparql = SPARQLWrapper("https://query.wikidata.org/sparql")
|
|
sparql.setReturnFormat(SPARQL_JSON)
|
|
sparql.setMethod('POST')
|
|
sparql.addCustomHttpHeader("User-Agent", "GLAM-Extractor/0.2")
|
|
|
|
# Process each country
|
|
total_without_wikidata = 0
|
|
total_enriched = 0
|
|
|
|
for country_code in ['BR', 'MX', 'CL']:
|
|
without, enriched = process_country(institutions, country_code, sparql)
|
|
total_without_wikidata += without
|
|
total_enriched += enriched
|
|
|
|
# Rate limiting - be nice to Wikidata
|
|
if country_code != 'CL': # Don't sleep after last country
|
|
print("⏸️ Waiting 5 seconds (Wikidata rate limiting)...\n")
|
|
time.sleep(5)
|
|
|
|
# Write output
|
|
print("="*80)
|
|
print("💾 WRITING ENRICHED DATASET")
|
|
print("="*80 + "\n")
|
|
|
|
header = f"""---
|
|
# Global Heritage Institutions - Latin America Fuzzy Match Enriched
|
|
# Generated: {datetime.now(timezone.utc).isoformat()}
|
|
#
|
|
# Total institutions: {len(institutions):,}
|
|
# Latin America institutions processed: {sum(len([i for i in institutions if i.get('locations', [{}])[0].get('country') == cc]) for cc in ['BR', 'MX', 'CL']):,}
|
|
# New Latin America matches: {total_enriched:,}
|
|
|
|
"""
|
|
|
|
with open(output_file, 'w', encoding='utf-8') as f:
|
|
f.write(header)
|
|
yaml.dump(institutions, f, allow_unicode=True, default_flow_style=False, sort_keys=False, width=120)
|
|
|
|
print(f"✅ Complete! Output: {output_file}\n")
|
|
|
|
# Final report
|
|
print("="*80)
|
|
print("📊 FINAL ENRICHMENT REPORT")
|
|
print("="*80)
|
|
print(f"\n✨ Results:")
|
|
print(f" Total institutions enriched: {total_enriched:,}")
|
|
print(f" Latin America institutions without Wikidata: {total_without_wikidata - total_enriched:,}")
|
|
print(f"\n⏱️ Total processing time: {(time.time()-start_time)/60:.1f} minutes")
|
|
print("="*80 + "\n")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|