mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-07-12 13:29:04 +00:00
8b8cc96d43
Audits identity pass-through fields (dims, counts, thicknesses) raw cert vs EpcPropertyData across all 1000 certs. All apparent mismatches are legitimate mapper behavior the first-pass audit didn't model: window_wall_type=4 windows correctly split to sap_roof_windows (not dropped); empty placeholder building parts correctly discarded; 'measured' insulation-thickness sentinel resolved to the wall_insulation_thickness_measured value. Remaining per-BP diffs were an index-misalignment artifact (raw BP[i] vs epc BP[i] after empty BP0 dropped). Conclusion: mapper is faithful; divergences are Playwright-entry or calc-side. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
56 lines
3.3 KiB
Python
56 lines
3.3 KiB
Python
"""Mapper faithfulness audit: for identity pass-through fields (dims, counts,
|
|
thicknesses) compare the RAW cert value to what EpcPropertyDataMapper produced.
|
|
Any mismatch is a mapper bug silently feeding the SAP engine wrong inputs."""
|
|
from __future__ import annotations
|
|
import json
|
|
from collections import defaultdict
|
|
from datatypes.epc.domain.mapper import EpcPropertyDataMapper
|
|
CORPUS="backend/epc_api/json_samples/RdSAP-Schema-21.0.1/corpus.jsonl"
|
|
def gv(x): return x.get('value') if isinstance(x,dict) else x
|
|
def num(x):
|
|
x=gv(x)
|
|
if x is None: return None
|
|
s=str(x).lower().replace('mm','').replace('m2','').strip()
|
|
try: return float(s)
|
|
except: return s # keep strings like 'measured'/'NI' for equality
|
|
mism=defaultdict(list)
|
|
n=0
|
|
for line in open(CORPUS):
|
|
d=json.loads(line)
|
|
try: epc=EpcPropertyDataMapper.from_api_response(d)
|
|
except Exception: continue
|
|
n+=1; u=d.get('uprn')
|
|
# top-level counts
|
|
checks=[('door_count', d.get('door_count'), epc.door_count),
|
|
('habitable', d.get('habitable_room_count'), getattr(epc,'habitable_room_count',None)),
|
|
('led', d.get('led_fixed_lighting_bulbs_count'), epc.led_fixed_lighting_bulbs_count),
|
|
('cfl', d.get('cfl_fixed_lighting_bulbs_count'), epc.cfl_fixed_lighting_bulbs_count),
|
|
('incand', d.get('incandescent_fixed_lighting_bulbs_count'), epc.incandescent_fixed_lighting_bulbs_count)]
|
|
for name,rv,ev in checks:
|
|
if rv is not None and ev is not None and num(rv)!=num(ev):
|
|
mism[name].append((u,rv,ev))
|
|
# per-building-part fabric
|
|
rbps=d.get('sap_building_parts') or []; ebps=epc.sap_building_parts or []
|
|
for i,rbp in enumerate(rbps):
|
|
if i>=len(ebps):
|
|
mism['DROPPED_building_part'].append((u,len(rbps),len(ebps))); break
|
|
ebp=ebps[i]
|
|
for name,rv,ev in [('wall_thick',rbp.get('wall_thickness'),getattr(ebp,'wall_thickness_mm',None)),
|
|
('wall_ins_thick',rbp.get('wall_insulation_thickness'),getattr(ebp,'wall_insulation_thickness',None)),
|
|
('roof_ins_thick',rbp.get('roof_insulation_thickness'),getattr(ebp,'roof_insulation_thickness',None)),
|
|
('wall_con',rbp.get('wall_construction'),getattr(ebp,'wall_construction',None)),
|
|
('wall_ins_type',rbp.get('wall_insulation_type'),getattr(ebp,'wall_insulation_type',None))]:
|
|
if rv is not None and ev is not None and num(rv)!=num(ev):
|
|
mism[name].append((u,rv,ev))
|
|
# windows: count + total area
|
|
rw=d.get('sap_windows') or []; ew=epc.sap_windows or []
|
|
if len(rw)!=len(ew): mism['window_count'].append((u,len(rw),len(ew)))
|
|
ra=sum((gv(w.get('window_width')) or 0)*(gv(w.get('window_height')) or 0) for w in rw)
|
|
ea=sum((float(w.window_width) if w.window_width else 0)*(float(w.window_height) if w.window_height else 0) for w in ew)
|
|
if abs(ra-ea)>0.02: mism['window_area'].append((u,round(ra,2),round(ea,2)))
|
|
print(f"audited {n} certs")
|
|
print("=== field mismatches (raw cert vs EpcPropertyData) ===")
|
|
for k,v in sorted(mism.items(), key=lambda x:-len(x[1])):
|
|
print(f"\n[{len(v):4d}] {k}")
|
|
for u,rv,ev in v[:5]: print(f" {u}: raw={rv} epc={ev}")
|
|
if not mism: print(" (no mismatches — mapper is identity-faithful on all checked fields)")
|