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

updated wall description to filled cavity

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2023-12-22 17:14:15 +00:00
parent 612922df6a
commit 9c140dc055
3 changed files with 150 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

147
etl/eligibility/ha_15_32/ha4_app.py
View file

@ -64,6 +64,7 @@ def get_ha_4_data(data, cleaned, cleaning_data, created_at):
postcode=property_meta["Post Code"],
size=1000
)
searcher.search()
if searcher.data is None:
@ -108,7 +109,7 @@ def get_ha_4_data(data, cleaned, cleaning_data, created_at):
].to_dict("records")
scoring_dictionary = prepare_model_data_row(
property_id=property_meta["row_id"],
property_id=eligibility.epc["uprn"],
modelling_epc=eligibility.epc,
cleaned=cleaned,
cleaning_data=cleaning_data,
@ -120,7 +121,7 @@ def get_ha_4_data(data, cleaned, cleaning_data, created_at):
results.append(
{
"row_id": property_meta["row_id"],
"uprn": epc["uprn"],
"Location Name": property_meta["Location Name"],
"Post Code": property_meta["Post Code"],
"gbis_eligible": eligibility.gbis_warmfront,
@ -140,6 +141,131 @@ def get_ha_4_data(data, cleaned, cleaning_data, created_at):
}
)
scoring_df = pd.DataFrame(scoring_data)
# Perform the same cleaning as in the model - first clean number of room variables though
scoring_df = DataProcessor.apply_averages_cleaning(
data_to_clean=scoring_df,
cleaning_data=cleaning_data,
cols_to_merge_on=['PROPERTY_TYPE', 'BUILT_FORM', 'CONSTRUCTION_AGE_BAND', 'LOCAL_AUTHORITY'],
colnames=["NUMBER_HABITABLE_ROOMS", "NUMBER_HEATED_ROOMS"],
)
scoring_df = DataProcessor.apply_averages_cleaning(
data_to_clean=scoring_df,
cleaning_data=cleaning_data,
cols_to_merge_on=COLUMNS_TO_MERGE_ON + ["LOCAL_AUTHORITY"],
).drop(columns=["LOCAL_AUTHORITY"])
scoring_df = DataProcessor.clean_missings_after_description_process(
scoring_df,
ignore_cols=[c for c in scoring_df.columns if ("thermal_transmittance" in c) or (
"insulation_thickness" in c) or ("ENERGY_EFF" in c)]
)
scoring_df = DataProcessor.clean_efficiency_variables(scoring_df)
model_api = ModelApi(portfolio_id="ha33-eligibility", timestamp=created_at)
all_predictions = model_api.predict_all(
df=scoring_df,
bucket="retrofit-data-dev",
prediction_buckets={
"sap_change_predictions": "retrofit-sap-predictions-dev",
"heat_demand_predictions": "retrofit-heat-predictions-dev",
"carbon_change_predictions": "retrofit-carbon-predictions-dev"
}
)
predictions = all_predictions["sap_change_predictions"].copy()
results_df = pd.DataFrame(results)
predictions = predictions.rename(columns={"property_id": "uprn"}).merge(
results_df[["uprn", "sap"]], how="left", on="uprn"
)
predictions["sap_uplift"] = predictions["predictions"] - predictions["sap"]
predictions = predictions.groupby("uprn")["sap_uplift"].sum().reset_index()
results_df = results_df.merge(
predictions[["sap_uplift", "uprn"]],
how="left",
on="uprn"
)
results_df["post_install_sap"] = results_df["sap"] + results_df["sap_uplift"]
results_df = results_df[~pd.isnull(results_df["uprn"])]
eligibility_assessment = []
for _, row in results_df[results_df["eco4_eligible"] == True].iterrows():
# The upgrade requirements are dependent on the current SAP
# If the property is an F or G, it only needs to upgrade to an %
if row["sap"] <= 38:
if row["post_install_sap"] >= 57:
eligibility_classification = "highest confidence"
elif row["post_install_sap"] >= 55:
eligibility_classification = "high confidence"
elif row["post_install_sap"] >= 53:
eligibility_classification = "medium confidence"
else:
eligibility_classification = "unlikely"
else:
if row["post_install_sap"] >= 71:
eligibility_classification = "highest confidence"
elif row["post_install_sap"] >= 69:
eligibility_classification = "high confidence"
elif row["post_install_sap"] >= 67:
eligibility_classification = "medium confidence"
else:
eligibility_classification = "unlikely"
eligibility_assessment.append(
{
"uprn": row["uprn"],
"eligibility_classification": eligibility_classification
}
)
eligibility_assessment = pd.DataFrame(eligibility_assessment)
results_df = results_df.merge(
eligibility_assessment, how="left", on="uprn"
)
# We have some properties that are duplicated so we take just one instance
results_df = results_df.drop_duplicates(subset=["uprn"])
return results_df, scoring_data, nodata
def analyse_ha_4(results_df, data):
results_df_social = results_df[results_df["tenure"] == "Rented (social)"]
results_df_social["tenure"].value_counts()
n_identified = (results_df_social["gbis_eligible"] | results_df_social["eco4_eligible"]).sum()
n_eco4 = results_df_social["eco4_eligible"].sum()
n_gbis = results_df_social[~results_df_social["eco4_eligible"]]["gbis_eligible"].sum()
eco_eligibile = results_df_social[results_df_social["eco4_eligible"]]
eco_eligibile["walls"].value_counts()
eco_eligibile["roof"].value_counts()
eco_eligibile[eco_eligibile["walls"] == "Cavity wall, as built, insulated"]
results_df_social[results_df_social["gbis_eligible"] | results_df_social["eco4_eligible"]]["tenure"].value_counts()
results_df_social["eligibility_classification"].value_counts()
future_possibilities_eco = results_df[
(results_df["eco4_eligible_future"] == True) & (~(results_df["gbis_eligible"] | results_df["eco4_eligible"]))
].copy()
future_possibilities_gbis = results_df[
(results_df["gbis_eligible_future"] == True) & (results_df["eco4_eligible_future"] == False) & (
~(results_df["gbis_eligible"] | results_df["eco4_eligible"]))
].copy()
def app():
data = load_ha_4()
@ -159,3 +285,20 @@ def app():
)
created_at = datetime.now().isoformat()
results_df, scoring_data, nodata = get_ha_4_data(
data=data,
cleaned=cleaned,
cleaning_data=cleaning_data,
created_at=created_at
)
# Store the data locally as a pickle
# import pickle
# with open("ha_4.pickle", "wb") as f:
# pickle.dump(
# {
# "results_df": results_df,
# "scoring_data": scoring_data,
# "nodata": nodata
# }, f)

3
etl/epc_clean/epc_attributes/WallAttributes.py
View file

@ -152,4 +152,7 @@ class WallAttributes(Definitions):
else:
result["insulation_thickness"] = "average"
if result["is_cavity_wall"] & result["is_as_built"] & (result["insulation_thickness"] == "average"):
result["is_filled_cavity"] = True
return result

4
etl/epc_clean/tests/test_data/test_wall_attributes_cases.py
View file

@ -550,7 +550,7 @@ wall_cases = [
'is_as_built': False, 'is_cob': False, 'is_assumed': False, 'is_sandstone_or_limestone': False,
'insulation_thickness': None, 'external_insulation': False, 'internal_insulation': False},
{'original_description': 'Cavity wall, as built, insulated (assumed)', 'thermal_transmittance': None,
'thermal_transmittance_unit': None, 'is_cavity_wall': True, 'is_filled_cavity': False, 'is_solid_brick': False,
'thermal_transmittance_unit': None, 'is_cavity_wall': True, 'is_filled_cavity': True, 'is_solid_brick': False,
'is_system_built': False, 'is_timber_frame': False, 'is_granite_or_whinstone': False, 'is_as_built': True,
'is_cob': False, 'is_assumed': True, 'is_sandstone_or_limestone': False, 'insulation_thickness': 'average',
'external_insulation': False, 'internal_insulation': False},
@ -727,7 +727,7 @@ wall_cases = [
'external_insulation': False, 'internal_insulation': False},
{'original_description': 'Waliau ceudod, fel yGÇÖu hadeiladwyd, wediGÇÖu hinswleiddio (rhagdybiaeth)',
'thermal_transmittance': None,
'thermal_transmittance_unit': None, 'is_cavity_wall': True, 'is_filled_cavity': False, 'is_solid_brick': False,
'thermal_transmittance_unit': None, 'is_cavity_wall': True, 'is_filled_cavity': True, 'is_solid_brick': False,
'is_system_built': False, 'is_timber_frame': False, 'is_granite_or_whinstone': False, 'is_as_built': True,
'is_cob': False, 'is_assumed': True, 'is_sandstone_or_limestone': False, 'insulation_thickness': 'average',
'external_insulation': False, 'internal_insulation': False},