# Data sources and sampling-frame rules (WP20). Paths point to read-only copies outside the repository.
sources:
  immoka_db: /Users/simon-pierreboucher/Desktop/Cluster/apps-laptop/toveli/data/src/immoka.db
  vraiprix_db: /Users/simon-pierreboucher/Desktop/Cluster/apps-laptop/toveli/data/src/vraiprix.db
  copy_date: "2026-10-17"           # sqlite3 .backup taken from M3U96a:~/apps/vrai-prix/data/ for the Toveli project
  listings_window: ["2026-08-12", "2026-10-17"]

frame:
  house_property_types: ["Maison", "Détachée", "Jumelé", "Maison de ville"]
  max_match_m: 15                   # metres between listing geocode and roll unit
  min_images: 4
  price_min: 100000
  price_max: 3000000
  excluded_sources: ["kijiji", "fb_marketplace"]   # no broker structured fields, median 6–10 photos
  # Image hosts whose robots.txt disallows automated retrieval for all agents ("User-agent: * / Disallow: /");
  # verified 2026-10-20 (results/raw/robots_check.txt). The Anthropic URL fetcher also refuses them. Excluded on
  # data-rights grounds; the selection effect is reported (results/tables/robots_exclusion_balance.csv).
  robots_disallowed_hosts: ["media.remax-quebec.com"]

sample:
  seed: 20261020
  n_listings: 1200
  max_images_per_listing: 12
  strata: ["cma", "age_band", "price_tier"]        # proportional allocation with a floor of 20 per non-empty stratum
  subsample_opus: 200                              # third extractor tier on a nested random subsample
  holdout_cma_for_geo_oos: "quebec"                # geographic holdout used in the cost-model calibration