1# Sample flow (attrition) — WP3823Snapshot 2026-11-01T17:38:30Z. Nothing is deleted; every step is a flag in `data/interim/listings_clean.parquet`.45| step | listings |6|---|---:|7| DB product rows (all statuses all stores) | 465 388 |8| active = 1 and listing_status = 'published' | 390 108 |9| … of an enabled store with >= 1 published listing | 390 108 |10| … excluding store_kind = hors_mission | 390 074 |11| … keeping one representative per (store normalised title) and non-empty title | 370 828 |12| … excluding mirror domains of the same business (sibling stores non-representative) [ASSORTMENT SAMPLE] | 370 054 |13| … and CAD-priced store/listing | 369 325 |14| … and a positive listed price <= 50 000 CAD not on request [PRICE SAMPLE] | 359 612 |1516## Assortment sample diagnostics17```18{19 "listings": 370054,20 "stores": 1557,21 "categories": 20,22 "dup_in_store_listings_removed": 19245,23 "share_autre": 0.1113,24 "available_0_share": 0.1307,25 "on_sale_share": 0.087,26 "has_variants_share": 0.2782,27 "sku_share": 0.7667,28 "vendor_share": 0.755829}30```31## Price-sample exclusions (from the assortment sample)32```33{34 "non_cad_listing_or_store": 729,35 "price_missing_or_on_request": 9635,36 "price_zero": 0,37 "price_gt_cap": 7838}39```40## Price quantiles in the price sample (CAD)41```42{43 "0.001": 0.26,44 "0.01": 1.5,45 "0.1": 5.99,46 "0.5": 24.99,47 "0.9": 274.56,48 "0.99": 3700.0,49 "0.999": 18500.050}51```52Top-10 stores hold 37.1% of the assortment sample.