junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-08 11:17:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

reducing cleaning code

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2026-03-11 19:28:03 +00:00
parent ec146cba77
commit 034a5de104
1 changed files with 19 additions and 30 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

49
etl/epc/Record.py
View file

@ -102,11 +102,26 @@ CLEANING_RULES: dict[str, CleaningRule] = {
"anomaly_to": None,
},
"number-open-fireplaces": {
"cast": int,
"default": 0
},
"extension-count": {
"cast": int,
"default": 0
},
"flat-storey-count": {
"cast": int,
"anomaly_to": None
},
"number-habitable-rooms": {
"cast": int,
"anomaly_to": None
},
# -----------------------------
# TO NONE
# -----------------------------
@ -410,7 +425,10 @@ class EPCRecord:
if "cast" in rule and value is not None:
try:
self._prepared_epc[field] = rule["cast"](value)
if rule["cast"] is int:
self._prepared_epc[field] = int(float(value))
else:
self._prepared_epc[field] = rule["cast"](value)
except Exception as e:
logger.warning(
f"Failed casting field '{field}' value '{value}': {e}"
@ -581,7 +599,6 @@ class EPCRecord:
self._clean_built_form()
self._clean_solar_hot_water()
self._clean_count_variables()
self._clean_heat_loss_corridor()
self._clean_age_band()
self._clean_year_built()
@ -867,34 +884,6 @@ class EPCRecord:
self._prepared_epc["heat-loss-corridor"]
]
def _clean_count_variables(self) -> None:
"""
This method will clean the count variables, if empty or invalid
"""
if not self._prepared_epc:
raise ValueError("EPC Recrod doesn not contain epc data")
_fields = [
"number-open-fireplaces",
"extension-count",
"flat-storey-count",
"number-habitable-rooms",
]
null_attributes = ["flat-storey-count", "number-habitable-rooms"]
for attribute in _fields:
value = self._prepared_epc[attribute]
if value in DATA_ANOMALY_MATCHES or pd.isnull(value):
if attribute in null_attributes:
value = None
else:
value = 0
else:
value = int(float(value))
self._prepared_epc[attribute] = value
def _clean_solar_hot_water(self) -> None:
"""
This method will clean the solar hot water, if empty or invalid