rendered from notes/Roofing/data/gold_variable_inventory.md
Gold Variable Inventory
Generated by scripts/roofing/inventory_v3.py against the Gold parquet on disk (data/sandbox/roofing_audit/gold_<FIPS>/). Role rules: see notes/Roofing/steps/01_variable_inventory.md. Spec ratified 2026-05-20 rev2.
Originator = field provenance per the BuildZoom data dictionary (buildzoom_permit_dictionary.md). permit = primary AHJ/owner source text · BuildZoom = BuildZoom-derived classification (a secondary machine guess) · 8020rei-ETL = added by the pipeline. PROJECT_TYPE is BuildZoom-derived, NOT an AHJ field — a signal-tier scheme must not rank it above DESCRIPTION.
Role summary
| Role | Count |
|---|
LABEL_SIGNAL | 7 |
FEATURE | 23 |
METADATA | 22 |
DROP | 2 |
Master role table
| column | dtype | role | originator | null_p50 | null_max | dist_p50 | n_fips |
|---|
BUSINESS_NAME | VARCHAR | LABEL_SIGNAL | permit | 25.58% | 99.96% | 78324 | 31/31 |
DESCRIPTION | VARCHAR | LABEL_SIGNAL | permit | 12.77% | 61.23% | 872488 | 31/31 |
JOB_VALUE | DOUBLE | LABEL_SIGNAL | permit | 49.22% | 100.00% | 58109 | 31/31 |
PROJECT_NAME | VARCHAR | LABEL_SIGNAL | permit | 89.67% | 100.00% | 106608 | 31/31 |
PROJECT_TYPE | VARCHAR[] | LABEL_SIGNAL | BuildZoom | 11.43% | 39.09% | 30228 | 31/31 |
SUBTYPE | VARCHAR | LABEL_SIGNAL | permit | 77.09% | 99.95% | 590 | 31/31 |
TYPE | VARCHAR | LABEL_SIGNAL | permit | 1.40% | 49.85% | 979 | 31/31 |
APPLIED_DATE | DATE | FEATURE | permit | 31.85% | 79.43% | 10819 | 31/31 |
AUX_EFFECTIVE_STATUS_DATE | DATE | FEATURE | BuildZoom | 1.67% | 19.34% | 12524 | 31/31 |
AUX_PERMIT_STATUS | VARCHAR | FEATURE | BuildZoom | 1.24% | 17.17% | 12 | 31/31 |
CANCELLED_DATE | DATE | FEATURE | permit | 90.19% | 100.00% | 8827 | 31/31 |
CBSA_FIPS | VARCHAR | FEATURE | BuildZoom | 1.39% | 7.25% | 28 | 31/31 |
CBSA_NAME | VARCHAR | FEATURE | BuildZoom | 1.39% | 7.25% | 28 | 31/31 |
CITY | VARCHAR | FEATURE | BuildZoom | 0.00% | 0.03% | 212 | 31/31 |
COMPLETED_DATE | DATE | FEATURE | permit | 40.78% | 99.97% | 10028 | 31/31 |
CONTRACTOR_ID | VARCHAR | FEATURE | BuildZoom | 39.80% | 100.00% | 22363 | 31/31 |
FEES | DOUBLE | FEATURE | permit | 33.64% | 99.98% | 14310 | 31/31 |
HOMEOWNER | VARCHAR | FEATURE | permit | 39.68% | 100.00% | 253426 | 31/31 |
INITIAL_STATUS | VARCHAR | FEATURE | permit | 0.84% | 17.16% | 12 | 31/31 |
INITIAL_STATUS_DATE | DATE | FEATURE | permit | 0.18% | 8.24% | 11717 | 31/31 |
ISSUED_DATE | DATE | FEATURE | permit | 19.96% | 60.44% | 10704 | 31/31 |
LATEST_STATUS | VARCHAR | FEATURE | permit | 0.84% | 17.16% | 13 | 31/31 |
LATEST_STATUS_DATE | DATE | FEATURE | permit | 0.18% | 8.24% | 12479 | 31/31 |
LATITUDE | DOUBLE | FEATURE | BuildZoom | 0.00% | 0.00% | 164886 | 31/31 |
LONGITUDE | DOUBLE | FEATURE | BuildZoom | 0.00% | 0.00% | 181759 | 31/31 |
PLACE_NAME | VARCHAR | FEATURE | BuildZoom | 1.59% | 47.13% | 108 | 31/31 |
SQUARE_FEET | INTEGER | FEATURE | permit | 92.93% | 100.00% | 3254 | 31/31 |
STREET | VARCHAR | FEATURE | BuildZoom | 0.00% | 0.00% | 272719 | 31/31 |
SUBDIVISION | VARCHAR | FEATURE | permit | 97.40% | 100.00% | 2289 | 31/31 |
ZIP_CODE | INTEGER | FEATURE | BuildZoom | 1.45% | 98.11% | 142 | 31/31 |
BUILDING_PERMIT_ID | VARCHAR | METADATA | BuildZoom | 0.00% | 0.00% | 1924184 | 31/31 |
COUNTY_FIPS | INTEGER | METADATA | BuildZoom | 0.00% | 0.00% | 1 | 31/31 |
COUNTY_NAME | VARCHAR | METADATA | BuildZoom | 0.00% | 0.00% | 1 | 31/31 |
DateSnapshot | DATE | METADATA | 8020rei-ETL | 0.00% | 0.00% | 9 | 31/31 |
FA_PROPERTYID | INTEGER[] | METADATA | 8020rei-ETL | 0.00% | 0.00% | 219932 | 31/31 |
FIPS | INTEGER | METADATA | 8020rei-ETL | 0.00% | 0.00% | 1 | 31/31 |
ID_PREFIX | VARCHAR | METADATA | 8020rei-ETL | 0.00% | 0.00% | 44 | 31/31 |
PARCEL_NUMBER | VARCHAR | METADATA | permit | 83.97% | 100.00% | 80437 | 31/31 |
PARTITION_YEAR | INTEGER | METADATA | 8020rei-ETL | 0.00% | 0.00% | 39 | 31/31 |
PERMIT_JURISDICTION | VARCHAR | METADATA | BuildZoom | 0.00% | 0.00% | 37 | 31/31 |
PERMIT_NUMBER | VARCHAR | METADATA | permit | 0.00% | 0.02% | 1578637 | 31/31 |
PLACE_FIPS | VARCHAR | METADATA | BuildZoom | 1.59% | 47.13% | 118 | 31/31 |
Partition_FIPS_Salting | VARCHAR | METADATA | 8020rei-ETL | 0.00% | 0.00% | 5 | 31/31 |
PropertyID | VARCHAR | METADATA | BuildZoom | 0.00% | 0.00% | 275792 | 31/31 |
STATE | VARCHAR | METADATA | BuildZoom | 0.00% | 0.00% | 11 | 31/31 |
STREET4JOIN1 | VARCHAR | METADATA | 8020rei-ETL | 0.00% | 0.00% | 272531 | 31/31 |
_hoodie_commit_seqno | VARCHAR | METADATA | 8020rei-ETL | 0.00% | 0.00% | 1924184 | 31/31 |
_hoodie_commit_time | VARCHAR | METADATA | 8020rei-ETL | 0.00% | 0.00% | 1 | 31/31 |
_hoodie_file_name | VARCHAR | METADATA | 8020rei-ETL | 0.00% | 0.00% | 66 | 31/31 |
_hoodie_partition_path | VARCHAR | METADATA | 8020rei-ETL | 0.00% | 0.00% | 1 | 31/31 |
_hoodie_record_key | VARCHAR | METADATA | 8020rei-ETL | 0.00% | 0.00% | 1924184 | 31/31 |
ts | TIMESTAMP WITH TIME ZONE | METADATA | 8020rei-ETL | 0.00% | 0.00% | 1 | 31/31 |
STORIES | INTEGER | DROP | permit | 96.30% | 100.00% | 14 | 31/31 |
UNITS | INTEGER | DROP | permit | 98.98% | 100.00% | 73 | 31/31 |