feat(analysis): fetch real MP metadata, fix anchor axis for party-level actors

- fetch_mp_metadata: use real OData URL with pagination (1200 records, 5 pages)
  uses Fractie.Afkorting not NaamNL for abbreviation matching
  skips Verwijderd=true records
- upsert_mp_metadata: keep most recent membership (prefer active over ended,
  then higher Van date) so current party affiliations are not overwritten by historical
- compute_anchor_axis: anchor directly on party-level SVD entities (GroenLinks-PvdA etc)
  before falling back to mp_metadata individual MP lookup
- test_fetch_mp_metadata: fix mock for timeout kwarg + pagination + Afkorting field
- Generated anchor axis HTML for 2025-Q2 through 2026-Q1 in outputs/
This commit is contained in:
2026-03-21 23:33:47 +01:00
parent 5ad83ef1be
commit aa2f66ac9f
8 changed files with 152 additions and 63 deletions
+63 -39
View File
@@ -34,61 +34,85 @@ def normalize_mp_name(
return name
_ODATA_BASE = "https://gegevensmagazijn.tweedekamer.nl/OData/v4/2.0"
_PAGE_SIZE = 250
def fetch_mp_metadata(
db_path: str, odata_url: str = "https://odata.example/FractieZetelPersoon"
db_path: str,
odata_url: str = f"{_ODATA_BASE}/FractieZetelPersoon",
) -> int:
"""Fetch MP party membership and tenure from OData and upsert into DB.
Paginates through all records using $skip. Uses Fractie.Afkorting as
the party name so it matches the abbreviations used in mp_votes.
Returns the number of records processed (inserted or updated).
"""
expand = "$expand=FractieZetel($expand=Fractie),Persoon"
session = requests.Session()
try:
resp = session.get(odata_url)
resp.raise_for_status()
data = resp.json()
except Exception as e:
logger.error("Failed to fetch MP metadata: %s", e)
raise
values = data.get("value") if isinstance(data, dict) else None
if values is None:
logger.error("Unexpected OData payload; missing 'value' list")
return 0
db = MotionDatabase(db_path)
processed = 0
skip = 0
for item in values:
while True:
url = f"{odata_url}?{expand}&$top={_PAGE_SIZE}&$skip={skip}"
try:
persoon = item.get("Persoon") or {}
fractiezetel = item.get("FractieZetel") or {}
fractie = fractiezetel.get("Fractie") or {}
resp = session.get(url, timeout=30)
resp.raise_for_status()
data = resp.json()
except Exception as e:
logger.error("Failed to fetch MP metadata (skip=%d): %s", skip, e)
raise
achternaam = persoon.get("Achternaam")
initialen = persoon.get("Initialen")
tussenvoegsel = persoon.get("Tussenvoegsel")
persoon_id = persoon.get("Id")
values = data.get("value") if isinstance(data, dict) else None
if values is None:
logger.error("Unexpected OData payload at skip=%d; missing 'value'", skip)
break
party = fractie.get("NaamNL")
van = item.get("Van")
tot_en_met = item.get("TotEnMet")
if not values:
break # no more pages
if not achternaam:
logger.debug("Skipping record without achternaam: %s", item)
continue
for item in values:
try:
if item.get("Verwijderd"):
continue
mp_name = normalize_mp_name(achternaam, initialen, tussenvoegsel)
persoon = item.get("Persoon") or {}
fractiezetel = item.get("FractieZetel") or {}
fractie = fractiezetel.get("Fractie") or {}
db.upsert_mp_metadata(
mp_name=mp_name,
party=party,
van=van,
tot_en_met=tot_en_met,
persoon_id=persoon_id,
)
processed += 1
except Exception:
logger.exception("Error processing OData item: %s", item)
achternaam = persoon.get("Achternaam")
initialen = persoon.get("Initialen")
tussenvoegsel = persoon.get("Tussenvoegsel")
persoon_id = persoon.get("Id")
# Use Afkorting (e.g. "VVD", "GroenLinks-PvdA") to match mp_votes party column
party = fractie.get("Afkorting") or fractie.get("NaamNL")
van = item.get("Van")
tot_en_met = item.get("TotEnMet")
if not achternaam:
logger.debug("Skipping record without achternaam: %s", item)
continue
mp_name = normalize_mp_name(achternaam, initialen, tussenvoegsel)
db.upsert_mp_metadata(
mp_name=mp_name,
party=party,
van=van,
tot_en_met=tot_en_met,
persoon_id=persoon_id,
)
processed += 1
except Exception:
logger.exception("Error processing OData item: %s", item)
logger.debug("Fetched page skip=%d, got %d records", skip, len(values))
if len(values) < _PAGE_SIZE:
break # last page
skip += _PAGE_SIZE
logger.info("Processed %d MP metadata records", processed)
return processed