Model/etl/customers/plus dane/prepare_asset_list.py
Khalim Conn-Kowlessar 20e4b28e07 major bulk update
2025-07-14 10:38:15 +01:00

48 lines
1.7 KiB
Python

"""
July 2025, this script prepares the asset list for Plus Dane
"""
import pandas as pd
oldest_asset_list = pd.read_excel(
"/Users/khalimconn-kowlessar/Documents/hestia/Customers/Plus Dane/New Programme July 2025/PLUS DANE Asset List.xlsx"
)
solar_asset_list = pd.read_excel(
"/Users/khalimconn-kowlessar/Documents/hestia/Customers/Plus Dane/New Programme July 2025/Plus Dane - potential "
"PV List 04.03.2025.xlsx"
)
newest_asset_list = pd.read_excel(
"/Users/khalimconn-kowlessar/Documents/hestia/Customers/Plus Dane/New Programme July 2025/Sava Intelligent Energy "
"- Property List - March 2025.xlsx"
)
old_missed = oldest_asset_list[~oldest_asset_list["UPRN"].isin(newest_asset_list["UPRN"])]
solar_missed = solar_asset_list[~solar_asset_list["UPRN"].isin(newest_asset_list["UPRN"])] # Empty
# Build new asset list
# NEWEST
# 'UPRN', 'Address', 'Postcode', 'Town', 'EPC SAP Band', 'SAP Rating',
# 'CO₂ Emissions', 'EPC EI Band', 'Data Quality Indicator',
# 'Results Calculated', 'Property Age', 'Property Type', 'Built Form',
# 'Wall Construction', 'Wall Insulation', 'Roof Construction',
# 'Joist Insulation', 'Space Heating System', 'Space Heating Fuel'
#
# SOlAR
df = newest_asset_list.merge(
solar_asset_list, how="left", on="UPRN", suffixes=("", "_solar"),
).merge(
oldest_asset_list, how="left", on="UPRN", suffixes=("", "_old")
)
df["asset_list_versiion"] = "July 2025"
old_missed["asset_list_versiion"] = "Historic"
# Append on the old missed?
df = pd.concat(
[df, old_missed], ignore_index=True, sort=False
)
# Store excel
df.to_excel(
"/Users/khalimconn-kowlessar/Documents/hestia/Customers/Plus Dane/New Programme July 2025/Plus Dane Asset List "
"July 2025.xlsx",
index=False,
)