Model/sfr/principal_pitch/2_export_data.py
2025-06-25 14:08:22 +01:00

224 lines
7.8 KiB
Python

"""
This script prepares the data for the financial model
"""
import pandas as pd
from backend.app.utils import sap_to_epc
from sqlalchemy.orm import sessionmaker
from backend.app.db.connection import db_engine
from backend.app.db.models.recommendations import Recommendation, Plan, PlanRecommendations
from backend.app.db.models.portfolio import PropertyModel, PropertyDetailsEpcModel
PORTFOLIO_ID = 206
SCENARIOS = [389]
def get_data(portfolio_id, scenario_ids):
session = sessionmaker(bind=db_engine)()
session.begin()
# Get properties and their details for a specific portfolio
properties_query = session.query(
PropertyModel,
PropertyDetailsEpcModel
).join(
PropertyDetailsEpcModel, PropertyModel.id == PropertyDetailsEpcModel.property_id
).filter(
PropertyModel.portfolio_id == portfolio_id # Filter by portfolio ID
).all()
# Transform properties data to include all fields dynamically
properties_data = [
{**{col.name: getattr(prop.PropertyModel, col.name) for col in PropertyModel.__table__.columns},
**{col.name: getattr(prop.PropertyDetailsEpcModel, col.name) for col in
PropertyDetailsEpcModel.__table__.columns}}
for prop in properties_query
]
# Get property IDs from fetched properties
# Get plans linked to the fetched properties
plans_query = session.query(Plan).filter(Plan.scenario_id.in_(scenario_ids)).all()
# Transform plans data to include all fields dynamically
plans_data = [
{col.name: getattr(plan, col.name) for col in Plan.__table__.columns}
for plan in plans_query
]
# Extract plan IDs for filtering recommendations through PlanRecommendations
plan_ids = [plan['id'] for plan in plans_data]
# Get recommendations through PlanRecommendations for those plans and that are default
recommendations_query = session.query(
Recommendation,
Plan.scenario_id
).join(
PlanRecommendations, Recommendation.id == PlanRecommendations.recommendation_id
).join(
Plan, Plan.id == PlanRecommendations.plan_id # Join with Plan to access scenario_id
).filter(
PlanRecommendations.plan_id.in_(plan_ids),
Recommendation.default == True # Filtering for default recommendations
).all()
# Transform recommendations data to include all fields dynamically and include scenario_id
recommendations_data = [
{**{col.name: getattr(rec.Recommendation, col.name) if hasattr(rec, 'Recommendation') else getattr(rec,
col.name) for
col in Recommendation.__table__.columns},
"Scenario ID": rec.scenario_id}
for rec in recommendations_query
]
session.close()
return properties_data, plans_data, recommendations_data
properties_data, plans_data, recommendations_data = get_data(portfolio_id=PORTFOLIO_ID, scenario_ids=SCENARIOS)
properties_df = pd.DataFrame(properties_data)
plans_df = pd.DataFrame(plans_data)
recommendations_df = pd.DataFrame(recommendations_data)
recommended_measures_df = recommendations_df[
["property_id", "measure_type", "estimated_cost", "default"]
]
recommended_measures_df = recommended_measures_df[recommended_measures_df["default"]]
recommended_measures_df = recommended_measures_df.drop(columns=["default"])
post_install_sap = recommendations_df[["property_id", "default", "sap_points"]]
post_install_sap = post_install_sap[post_install_sap["default"]]
# Sum up the sap points by property id
post_install_sap = post_install_sap.groupby("property_id")[["sap_points"]].sum().reset_index()
recommendations_measures_pivot = recommended_measures_df.pivot(
index='property_id',
columns='measure_type',
values='estimated_cost'
)
recommendations_measures_pivot = recommendations_measures_pivot.reset_index()
# Total cost is the row sum, excluding the property_id column
recommendations_measures_pivot["total_retrofit_cost"] = recommendations_measures_pivot.drop(
columns=["property_id"]
).sum(axis=1)
df = properties_df[
[
"property_id", "uprn", "address", "postcode", "property_type", "walls", "roof", "heating", "windows",
"current_epc_rating",
"current_sap_points", "total_floor_area", "number_of_rooms",
]
].merge(
recommendations_measures_pivot, how="left", on="property_id"
).merge(
post_install_sap, how="left", on="property_id"
)
df = df.drop(columns=["property_id"])
df["sap_points"] = df["sap_points"].fillna(0)
df["predicted_post_works_sap"] = df["current_sap_points"] + df["sap_points"]
df["predicted_post_works_sap"] = df["predicted_post_works_sap"].round()
df["predicted_post_works_epc"] = df["predicted_post_works_sap"].apply(lambda x: sap_to_epc(x))
# We merge this back to the main dataframe, which will contain the bathrooms
from utils.s3 import read_csv_from_s3
asset_list = read_csv_from_s3(bucket_name="retrofit-plan-inputs-dev", filepath='8/206/asset_list.csv')
asset_list = pd.DataFrame(asset_list)
df["uprn"] = df["uprn"].astype(str)
asset_list = asset_list.merge(
df.drop(columns=["address", "postcode", "property_type", "total_floor_area"]),
how="left",
on="uprn"
)
condition_costs = pd.read_excel(
"/Users/khalimconn-kowlessar/Documents/hestia/sfr/Spring JV/Condition costs.xlsx",
sheet_name="Prices - Khalim",
header=35
)
# Remove unnamed columns and reset index
condition_costs = condition_costs.loc[:, ~condition_costs.columns.str.contains('^Unnamed')]
condition_costs = condition_costs.reset_index(drop=True)
# We now estimate condition cost
def simulate_condition(asset_list, condition_costs):
"""
This function is for testing, and will simulate condition cost from 1-10 for each property to see what the
costing array looks like.
:param df:
:return:
"""
condition_df = []
for _, row in asset_list.iterrows():
n_bathrooms = row["bathrooms"]
conditions = {}
for condition in reversed(range(1, 11)):
condition_cost = condition_costs[
condition_costs["Condition"] == condition
].drop(columns=["Condition"]).iloc[0]
# Each cost is scaled by floor area
condition_cost = condition_cost * row["total_floor_area"]
condition_cost["Bathroom"] = condition_cost["Bathroom"] * n_bathrooms
total_condition_cost = condition_cost.sum()
conditions["Condition " + str(condition)] = (total_condition_cost)
condition_df.append(
{
"uprn": row["uprn"],
**conditions
}
)
condition_df = pd.DataFrame(condition_df)
asset_list = asset_list.merge(
condition_df,
how="left",
on="uprn"
)
return asset_list
# asset_list = simulate_condition(asset_list, condition_costs)
# We calculate the condition cost based on the condition
for _, row in asset_list.iterrows():
condition = row["condition_score"]
if condition in [None, ""]:
continue
condition = int(float(condition))
condition_cost = condition_costs[
condition_costs["Condition"] == condition
].drop(columns=["Condition"]).iloc[0]
# Each cost is scaled by floor area
condition_cost = condition_cost * float(row["total_floor_area"])
n_bathrooms = row["n_bathrooms"]
condition_cost["Bathroom"] = condition_cost["Bathroom"] * float(n_bathrooms)
total_condition_cost = condition_cost.sum()
asset_list.loc[asset_list["uprn"] == row["uprn"], "domna_condition_cost"] = total_condition_cost
# Store output
asset_list.to_excel(
"/Users/khalimconn-kowlessar/Documents/hestia/sfr/Spring JV/20250624_portfolio_retrofit_packages.xlsx",
index=False
)
condition_cost_comparison = asset_list[
["condition_score", "decoration_sum_min ", "decoration_sum_max", "domna_condition_cost"]
]