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.
423 lines
15 KiB
Python
Executable file
423 lines
15 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
"""
|
|
Enrich Dutch institutions using fuzzy name matching in Wikidata.
|
|
|
|
This script addresses the low Dutch coverage (4.8%) by querying Wikidata for
|
|
Dutch heritage institutions using name-based searches rather than ISIL codes.
|
|
|
|
Strategy:
|
|
1. Find Dutch institutions without Wikidata IDs
|
|
2. Query Wikidata for museums/archives/libraries in Netherlands
|
|
3. Fuzzy match names (normalized)
|
|
4. Manual verification for high-confidence matches (>0.85)
|
|
"""
|
|
|
|
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
|
|
|
|
|
|
def normalize_name(name: str) -> str:
|
|
"""Normalize institution name for fuzzy matching."""
|
|
# Lowercase
|
|
name = name.lower()
|
|
|
|
# Remove common prefixes/suffixes
|
|
name = re.sub(r'^(stichting|gemeentearchief|regionaal archief|museum)\s+', '', name)
|
|
name = re.sub(r'\s+(archief|museum|bibliotheek|library|archive)$', '', 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_dutch_institutions(sparql: SPARQLWrapper, institution_types: list[str]) -> dict[str, dict[str, Any]]:
|
|
"""
|
|
Query Wikidata for Dutch heritage institutions.
|
|
|
|
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:Q55 . # country: Netherlands
|
|
|
|
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 "nl,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
|
|
museum_keywords = ['museum', 'museo', 'museu']
|
|
archive_keywords = ['archief', 'archive', 'archivo']
|
|
library_keywords = ['bibliotheek', 'library', 'biblioteca']
|
|
|
|
# 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_dutch_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 Dutch 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 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
|
|
if "Wikidata" not in existing_schemes:
|
|
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 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_dutch_enriched.yaml"
|
|
|
|
print("="*80)
|
|
print("🇳🇱 DUTCH 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\n")
|
|
|
|
# Filter Dutch institutions
|
|
dutch_institutions_idx = [
|
|
idx for idx, inst in enumerate(institutions)
|
|
if inst.get('locations', [{}])[0].get('country') == 'NL'
|
|
]
|
|
|
|
print(f"🇳🇱 Found {len(dutch_institutions_idx):,} Dutch institutions\n")
|
|
|
|
# Count those without Wikidata
|
|
dutch_without_wikidata = [
|
|
idx for idx in dutch_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", [])
|
|
)
|
|
]
|
|
|
|
print(f"❓ Dutch institutions without Wikidata: {len(dutch_without_wikidata):,}\n")
|
|
|
|
# Setup SPARQL
|
|
sparql = SPARQLWrapper("https://query.wikidata.org/sparql")
|
|
sparql.setReturnFormat(SPARQL_JSON)
|
|
sparql.setMethod('POST')
|
|
sparql.addCustomHttpHeader("User-Agent", "GLAM-Extractor/0.2")
|
|
|
|
# Query Wikidata for Dutch institutions
|
|
print("🔍 Querying Wikidata for Dutch museums, libraries, and archives...")
|
|
print(" (This may take 30-60 seconds)\n")
|
|
|
|
institution_types = ["Q33506", "Q7075", "Q166118"] # museum, library, archive
|
|
wikidata_results = query_dutch_institutions(sparql, institution_types)
|
|
|
|
print(f"✅ Found {len(wikidata_results):,} Dutch institutions in Wikidata\n")
|
|
|
|
# Fuzzy match
|
|
print("🔗 Fuzzy matching names (threshold: 0.85)...\n")
|
|
|
|
dutch_insts = [institutions[idx] for idx in dutch_without_wikidata]
|
|
matches = fuzzy_match_dutch_institutions(dutch_insts, wikidata_results, threshold=0.85)
|
|
|
|
print(f"✨ Found {len(matches):,} high-confidence matches\n")
|
|
|
|
# Show sample matches for verification
|
|
if matches:
|
|
print("="*80)
|
|
print("📋 SAMPLE MATCHES (Top 10)")
|
|
print("="*80)
|
|
for i, (local_idx, qid, score, wd_data) in enumerate(matches[:10]):
|
|
inst = dutch_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("\n" + "="*80)
|
|
print("\n⚠️ AUTOMATIC APPLICATION")
|
|
print("="*80)
|
|
print("\nApplying all high-confidence matches (>0.85 similarity)...")
|
|
|
|
choice = "1" # Auto-apply
|
|
|
|
if choice == "1":
|
|
# Apply all matches
|
|
print("\n✅ Applying all matches...\n")
|
|
enriched_count = 0
|
|
|
|
for local_idx, qid, score, wd_data in matches:
|
|
global_idx = dutch_without_wikidata[local_idx]
|
|
if enrich_institution(institutions[global_idx], wd_data):
|
|
enriched_count += 1
|
|
|
|
print(f"✨ Enriched {enriched_count:,} institutions\n")
|
|
|
|
# Write output
|
|
print("💾 Writing enriched dataset...")
|
|
|
|
header = f"""---
|
|
# Global Heritage Institutions - Dutch Fuzzy Match Enriched
|
|
# Generated: {datetime.now(timezone.utc).isoformat()}
|
|
#
|
|
# Total institutions: {len(institutions):,}
|
|
# Dutch institutions: {len(dutch_institutions_idx):,}
|
|
# New Dutch matches: {enriched_count:,}
|
|
|
|
"""
|
|
|
|
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("📊 ENRICHMENT REPORT")
|
|
print("="*80)
|
|
print(f"\n✨ Results:")
|
|
print(f" Dutch institutions enriched: {enriched_count:,}")
|
|
print(f" New Dutch Wikidata coverage: {(49 + enriched_count) / len(dutch_institutions_idx) * 100:.1f}%")
|
|
print(f" (was 4.8%, now {(49 + enriched_count) / len(dutch_institutions_idx) * 100:.1f}%)")
|
|
print(f"\n⏱️ Processing time: {(time.time()-start_time)/60:.1f} minutes")
|
|
print("="*80 + "\n")
|
|
|
|
elif choice == "2":
|
|
print("\n⚠️ Interactive review not yet implemented")
|
|
print(" Please review matches manually and run with choice 1 if approved\n")
|
|
else:
|
|
print("\n❌ Cancelled\n")
|
|
else:
|
|
print("❌ No matches found. Try lowering threshold.\n")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|