Model/etl/customers/lincs_rural/get_missed.py
Khalim Conn-Kowlessar 395ab0e083 minor debugging
2025-12-13 22:13:09 +08:00

47 lines
2 KiB
Python

# After going back to Lincs rural, they gave us some additional data that we can use to try to fetch missed UPRNs again
import pandas as pd
# missed = pd.read_excel(
# "/Users/khalimconn-kowlessar/Downloads/lincs_rural_missed_nov_2025.xlsx",
# sheet_name="Missed Properties"
# )
# missed = missed[~pd.isnull(missed["rrn"])]
prepared = pd.read_excel(
"/Users/khalimconn-kowlessar/Downloads/lincs_rural_standardised_ara_nov_2025.xlsx",
sheet_name="Standardised Asset List"
)
updated_data = pd.read_excel(
"/Users/khalimconn-kowlessar/Downloads/MASTER LIST EPCS UPDATED November 2025 Domna Homes - Copy.xlsx",
sheet_name="PROPERTY EPC RATINGS"
)
updated_data = updated_data[~pd.isnull(updated_data["Property Ref."])]
missed = updated_data[~updated_data["Property Ref."].isin(prepared["landlord_property_id"].values.tolist())].copy()
# missed.to_csv("/Users/khalimconn-kowlessar/Downloads/lincs_rural_missed_uprn.csv")
# We'll grab the UPRNs manually and then pull them in, and prepare for ARA
missing_uprns = pd.read_csv("/Users/khalimconn-kowlessar/Downloads/lincs_rural_missed_uprn.csv")
missing_uprns["landlord_property_id"] = missing_uprns["Property Ref."].copy()
missing_uprns["domna_property_id"] = missing_uprns["Property Ref."].copy()
missing_uprns["domna_address_1"] = missing_uprns['Unnamed: 1'].str.split(",").str[0].str.strip()
missing_uprns["postcode"] = missing_uprns['Unnamed: 1'].str.split(",").str[-1].str.strip()
missing_uprns["landlord_property_type"] = "unknown"
missing_uprns["landlord_built_form"] = "unknown"
missing_uprns["domna_full_address"] = missing_uprns['Unnamed: 1'].copy()
missed_standardised_for_ara = missing_uprns[
['landlord_property_id', 'domna_address_1', 'landlord_property_type', 'landlord_built_form', 'postcode',
'domna_property_id', 'UPRN']
].rename(
columns={"UPRN": "epc_os_uprn"}
)
# Store
missed_standardised_for_ara.to_excel(
"/Users/khalimconn-kowlessar/Downloads/lincs_rural_missed_standardised_ara_nov_2025.xlsx",
index=False,
sheet_name="Standardised Asset List"
)