spb/qwhpi Public
QHPI — Quebec Housing Price Index: quality-adjusted, hierarchically pooled housing price indexes.
Python 63.9%
TypeScript 25.4%
CSS 5.5%
TeX 3.5%
SQL 0.8%
Makefile 0.5%
Dockerfile 0.5%
1<!--2=============================================================================3QWHPI — Quebec Weekly Housing Price Index4Author : Simon-Pierre Boucher5Contact : contact@spboucher.ai6File : outputs/reports/cleaning_report.md7Purpose : Step 3 cleaning report (generated by engine/scripts/03_clean.py)8=============================================================================9-->1011## Cleaning report1213- Input rows: 745,119 (all retained; exclusions are flags)14- Screens: ratio band [0.2, 5.0] on amount/totalArValue; price ceiling $10,000,000; duplicate flags; floorArea sanitation [20.0, 2000.0] m².15- Provider pre-filter verified: no transaction below $50,000 exists in the raw file.1617### Exclusion table (outputs/tables/exclusions.csv)18- assessment_ratio_outside_band: 24,976 (3.352%)19- exact_duplicate: 665 (0.089%)20- addr_date_amount_duplicate: 107 (0.014%)21- price_above_10m: 46 (0.006%)22- TOTAL_EXCLUDED: 25,794 (3.462%)23- RETAINED_IN_RESEARCH_SAMPLE: 719,325 (96.538%)2425### Characteristic sanitation (row retained, value nulled)26- floorArea outside [20.0, 2000.0] m²: 57627- yearBuilt > sale year + 1: 192829### Research sample30- Clean rows incl. indéterminé: 719,32531- Headline sample (3 determined types): 626,127 (84.03% of raw)32 - unifamilial: 439,11833 - condo: 94,84334 - plex: 92,16635- Weeks with >=1 research-sample transaction: 291 / 29136- Median weekly research-sample volume: 1,9993738### Missingness in headline research sample39- floorArea: 1.85%40- yearBuilt: 5.4%41- buildingType: 27.61%42- ownerType: 23.7%43