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

testing out the new model - more reasonable behaviour

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-08-09 08:52:34 +01:00
parent 58374e7a6d
commit 935cfb24cf
6 changed files with 51 additions and 107 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
backend/Property.py
View file

@ -384,8 +384,9 @@ class Property:
types = [x["type"] for x in previous_phase_representatives]
if "external_wall_insulation" in types and "internal_wall_insulation" in types:
raise Exception("We shouldn't have this in the representative recommendations")
# We include previous phases + the recommendation itself in the EPC transformations
epc_transformations = [
x["description_simulation"] for x in previous_phase_representatives
x["description_simulation"] for x in previous_phase_representatives + [rec]
]
# It is possible that we could have two simulations applied to the same descriptions
@ -439,8 +440,6 @@ class Property:
sim_epc.update(
{
"heating-cost-current": rec_impact["epc_heating_cost"],
"hot-water-cost-current": rec_impact["epc_hot_water_cost"],
# CO₂ emissions per square metre floor area per year in kg/m². Since CO₂ emissions are in tonnes
# per year, we multiply by 1000 to get kg/m²
"co2-emiss-curr-per-floor-area": round(
@ -450,7 +449,6 @@ class Property:
"current-energy-rating": sap_to_epc(rec_impact["sap"]),
"current-energy-efficiency": int(np.floor(rec_impact["sap"])),
"energy-consumption-current": rec_impact["heat_demand"],
"lighting-cost-current": rec_impact["epc_lighting_cost"],
"id": "+".join([str(self.id), rec_id])
}
)
@ -594,8 +592,7 @@ class Property:
Given the cleaning that has been performed, we'll use this to identify the property
components, from roof to walls to windows, heating and hot water
:param cleaned: This is the dictionary of components found in cleaner.cleaned
:param energy_consumption_client: Contains the heating and hot water kwh models - used to predict current
energy annual consumption in kWh
:param energy_consumption_client: The client that will be used to convert the energy costs to today's costs
:param kwh_predictions: Contains the kwh predictions for heating and hot water
:return:
"""
@ -686,14 +683,6 @@ class Property:
# 2) Predicted KwH
# Today's costs
todays_heating_cost = energy_consumption_client.convert_cost_to_today(
original_cost=float(self.data["heating-cost-current"]),
lodgement_date=pd.Timestamp(self.epc_record.prepared_epc["lodgement_date"]).tz_localize(None)
)
todays_hot_water_cost = energy_consumption_client.convert_cost_to_today(
original_cost=float(self.data["hot-water-cost-current"]),
lodgement_date=pd.Timestamp(self.epc_record.prepared_epc["lodgement_date"]).tz_localize(None)
)
todays_lighting_cost = energy_consumption_client.convert_cost_to_today(
original_cost=float(self.data["lighting-cost-current"]),
lodgement_date=pd.Timestamp(self.epc_record.prepared_epc["lodgement_date"]).tz_localize(None)
@ -702,15 +691,6 @@ class Property:
# If we have the kwh figures, we don't need to predict them
condition_data = self.energy_assessment_condition_data.copy()
# scoring_df = pd.DataFrame([self.epc_record.prepared_epc])
# # Change columns from underscores to hyphens
# scoring_df.columns = [
# x.lower().replace("_", "-") for x in scoring_df.columns
# ]
# for col in ["heating_kwh", "hot_water_kwh"]:
# scoring_df[col] = None
#
# energy_consumption_client.data = None
heating_kwh_predictions = kwh_predictions["heating_kwh_predictions"]
hotwater_kwh_predictions = kwh_predictions["hotwater_kwh_predictions"]

5
backend/app/plan/router.py
View file

@ -588,7 +588,7 @@ async def trigger_plan(body: PlanTriggerRequest):
raise Exception("Missed setting of spatial data for a property")
p.get_components(
cleaned=cleaned,
energy_consumption_client=energy_consumption_client, # TODO: Full remove me
energy_consumption_client=energy_consumption_client,
kwh_predictions=kwh_predictions
)
@ -799,7 +799,6 @@ async def trigger_plan(body: PlanTriggerRequest):
logger.info("Optimising recommendations")
scoring_epcs = [] # For scoring the kwh models
for property_id in recommendations.keys():
property_instance = [p for p in input_properties if p.id == property_id][0]
recommendations_with_impact, impact_summary = (
@ -880,6 +879,8 @@ async def trigger_plan(body: PlanTriggerRequest):
extract_ids=True
)
# TODO: Costing model, which should include today's costs!
# We now insert into the recommendations
for property_id in recommendations.keys():
property_recommendations = recommendations[property_id]

12
backend/ml_models/api.py
View file

@ -12,20 +12,20 @@ class ModelApi:
"sap_change_predictions",
"heat_demand_predictions",
"carbon_change_predictions",
"lighting_cost_predictions",
"heating_cost_predictions",
"hot_water_cost_predictions",
# "lighting_cost_predictions",
# "heating_cost_predictions",
# "hot_water_cost_predictions",
]
MODEL_URLS = {
"sap_change_predictions": "sapmodel",
"heat_demand_predictions": "heatmodel",
"carbon_change_predictions": "carbonmodel",
"lighting_cost_predictions": "lightingmodel",
"heating_cost_predictions": "heatingmodel",
"hot_water_cost_predictions": "hotwatermodel",
"hotwater_kwh_predictions": "hotwaterkwhmodel",
"heating_kwh_predictions": "heatingkwhmodel",
# "lighting_cost_predictions": "lightingmodel",
# "heating_cost_predictions": "heatingmodel",
# "hot_water_cost_predictions": "hotwatermodel",
}
def __init__(

4
etl/bill_savings/data_collection.py
View file

@ -134,8 +134,8 @@ def app():
for i, directory in tqdm(enumerate(epc_directories), total=len(epc_directories)):
# Skip the first 50
# if i < 57:
# continue
if i < 18:
continue
data = pd.read_csv(directory / "certificates.csv", low_memory=False)
# Rename the columns to the same format as the api returns

46
etl/testing_data/bills_model_testing.py
View file

@ -226,16 +226,18 @@ base_prediction = model_api.predict_all(
extract_ids=False
)
cwi_epc = epcs_for_scoring.copy()
cwi_epc["walls-description"] = "Cavity wall, filled cavity"
cwi_epc["walls-energy-eff"] = "Good"
cwi_epc["heating-cost-current"] = 1650
cwi_epc["current-energy-efficiency"] = 72
cwi_epc["current-energy-rating"] = "C"
cwi_epc["co2-emissions-current"] = 3.7
cwi_epc["energy-consumption-current"] = 121
cwi_epc["co2-emiss-curr-per-floor-area"] = 19
cwi_epc["photo-supply"] = 0
cwi_epc = pd.DataFrame([property_scoring_epcs[1].copy()])
cwi_epc = add_features_from_code(cwi_epc)
cwi_epc = add_estimate_annual_kwh(cwi_epc)
# cwi_epc["walls-description"] = "Cavity wall, filled cavity"
# cwi_epc["walls-energy-eff"] = "Good"
# cwi_epc["heating-cost-current"] = 1650
# cwi_epc["current-energy-efficiency"] = 72
# cwi_epc["current-energy-rating"] = "C"
# cwi_epc["co2-emissions-current"] = 3.7
# cwi_epc["energy-consumption-current"] = 121
# cwi_epc["co2-emiss-curr-per-floor-area"] = 19
# cwi_epc["photo-supply"] = 0
# cwi_epc["energy-consumption-current"] =
# cwi_epc["roof-description"] = "Pitched, 300 mm loft insulation"
# cwi_epc["roof-energy-eff"] = "Very Good"
@ -259,7 +261,27 @@ cwi_prediction = model_api.predict_all(
df=cwi_epc,
bucket=get_settings().DATA_BUCKET,
prediction_buckets=get_prediction_buckets(),
model_prefixes=["heating_kwh_predictions"],
model_prefixes=["heating_kwh_predictions", "hotwater_kwh_predictions"],
extract_ids=False
)
2344 - 2060
# 77 perryn
starting_heating = 19837.2
starting_hot_water = 2974.1
ending_heating = 17041.1
ending_hot_water = 2735.3
# 44 lindlings
starting_heating = 13327.1
starting_hot_water = 2349.5
ending_heating = 9672.3
ending_hot_water = 2030.2
ending_heating = 8695.1
ending_hot_water = 2437.0
heating_impact = starting_heating - ending_heating
hot_water_impact = starting_hot_water - ending_hot_water
total_impact = heating_impact + hot_water_impact

65
recommendations/Recommendations.py
View file

@ -379,26 +379,13 @@ class Recommendations:
property_predictions = {
prefix + "_predictions": all_predictions[prefix + "_predictions"][
all_predictions[prefix + "_predictions"]["property_id"] == str(property_instance.id)
].copy() for prefix in [
"sap_change", "heat_demand", "carbon_change", "lighting_cost", "heating_cost", "hot_water_cost"
]
].copy() for prefix in ["sap_change", "heat_demand", "carbon_change"]
}
# We apply adjustments to each of the heating costs
for prefix in ["lighting_cost", "heating_cost", "hot_water_cost"]:
property_predictions[f"{prefix}_predictions"]["adjusted_cost"] = (
property_predictions[f"{prefix}_predictions"]["predictions"].apply(
lambda x: AnnualBillSavings.adjust_energy_to_metered(
x, current_epc_rating=property_instance.data["current-energy-rating"]
)
)
)
property_recommendations = recommendations[property_instance.id].copy()
# TODO: should fabric upgrades have an impact on hot water costs/kwh?
# TODO: Generally, the costing models are just increasing. Maybe they're including something in the model
# that they shouldn't e.g. SAP, carbon, heat demand etc?
increasing_variables = ["sap"]
decreasing_variables = ["carbon", "heat_demand"]
impact_summary = []
for recommendations_by_type in property_recommendations:
@ -414,14 +401,6 @@ class Recommendations:
)]["predictions"].values[0] for prefix in ["sap_change", "heat_demand", "carbon_change"]
}
# For phase costs, we need adusted and unadjusted values
phase_cost = {
prefix: property_predictions[prefix + "_predictions"][
property_predictions[prefix + "_predictions"]["recommendation_id"] ==
str(rec["recommendation_id"])
] for prefix in ["lighting_cost", "heating_cost", "hot_water_cost"]
}
# We structure this so that depending on the phase, we capture the previous phase impacts and
# then just have one piece of code to calculate the difference
if rec["phase"] == 0:
@ -433,9 +412,6 @@ class Recommendations:
"sap": float(property_instance.data["current-energy-efficiency"]),
"carbon": float(property_instance.data["co2-emissions-current"]),
"heat_demand": float(property_instance.data["energy-consumption-current"]),
"epc_heating_cost": float(property_instance.data["heating-cost-current"]),
"epc_hot_water_cost": float(property_instance.data["hot-water-cost-current"]),
"epc_lighting_cost": float(property_instance.data["lighting-cost-current"])
}
else:
@ -463,26 +439,6 @@ class Recommendations:
"heat_demand": phase_energy_efficiency_metrics["heat_demand"],
}
static_cost_variables = (
["epc_heating_cost", "epc_hot_water_cost"] if
rec["type"] == "low_energy_lighting" else ["epc_lighting_cost"]
)
dynamic_cost_variables = [
v for v in ["epc_heating_cost", "epc_hot_water_cost", "epc_lighting_cost"]
if v not in static_cost_variables
]
# Take the static variables from the previous phase
current_phase_costs = {k: v for k, v in previous_phase_values.items() if k in static_cost_variables}
# Insert the dynamic variables from the current phase
for v in dynamic_cost_variables:
current_phase_costs[v] = phase_cost[v.split("epc_")[1]]["adjusted_cost"].values[0]
current_phase_values.update(current_phase_costs)
increasing_variables = ["sap"]
decreasing_variables = [
"carbon", "heat_demand", "epc_heating_cost", "epc_hot_water_cost", "epc_lighting_cost"
]
# For increasing variables, the new value needs to be higher than the previous, otherwise we set it to
# the previous
# For decreasing variables, the new value should be lower than the previous, otherwise we set it to
@ -507,21 +463,6 @@ class Recommendations:
"carbon": previous_phase_values["carbon"] - current_phase_values["carbon"],
# Decreasing
"heat_demand": previous_phase_values["heat_demand"] - current_phase_values["heat_demand"],
# Decreasing
"epc_heating_cost": (
previous_phase_values["epc_heating_cost"] -
current_phase_values["epc_heating_cost"]
),
# Decreasing
"epc_hot_water_cost": (
previous_phase_values["epc_hot_water_cost"] -
current_phase_values["epc_hot_water_cost"]
),
# Decreasing
"epc_lighting_cost": (
previous_phase_values["epc_lighting_cost"] -
current_phase_values["epc_lighting_cost"]
)
}
# Prevent from being negative