junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-30 13:10:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

working on algorithm

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-11-16 16:30:23 +00:00
parent c13c84b98c
commit 8f9b8f0886
1 changed files with 14 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
etl/customers/stonewater/Wave 3 Preparation.py
View file

@ -1633,6 +1633,9 @@ def propsed_wave_3_sample():
"- Archetyped V3.1.xlsx", "- Archetyped V3.1.xlsx",
header=4 header=4
) )
# TODO: We drop 302 properties that are not priority postcodes - confirm w/ Stonewater
asset_list = asset_list[asset_list["Archetype ID"] == "NOT PRIORITY POSTCODE"]
# Clean address ids # Clean address ids
asset_list = asset_list[~pd.isnull(asset_list["Address ID"])] asset_list = asset_list[~pd.isnull(asset_list["Address ID"])]
asset_list = asset_list[asset_list["Address ID"] != "Address ID"] asset_list = asset_list[asset_list["Address ID"] != "Address ID"]
@ -1674,6 +1677,7 @@ def propsed_wave_3_sample():
# Tier 2: We have a property in the same archetype that was surveyed and is below EPC D # Tier 2: We have a property in the same archetype that was surveyed and is below EPC D
# #
results = []
for region in unique_postal_regions: for region in unique_postal_regions:
# Take all of the properties in that region # Take all of the properties in that region
region_assets = asset_list[asset_list["Postal Region"] == region].copy() region_assets = asset_list[asset_list["Postal Region"] == region].copy()
@ -1722,10 +1726,17 @@ def propsed_wave_3_sample():
) )
region_assets["Current EPC Band"] = region_assets["Current EPC Band"].fillna( region_assets["Current EPC Band"] = region_assets["Current EPC Band"].fillna(
region_assets["Current EPC Band_method2"]) region_assets["Current EPC Band_method2"].astype(str),
)
region_assets = region_assets.drop(columns=["Current EPC Band_method2"]) region_assets = region_assets.drop(columns=["Current EPC Band_method2"])
# We label EPC C properties
region_assets["Confidence Tier"] = np.where(
region_assets["Current EPC Band"].isin(["C", "B", "A"]),
"6 - EPC C or above", region_assets["Confidence Tier"]
)
missed_addressids = region_assets[pd.isnull(region_assets["Confidence Tier"])]["Address ID"].unique().tolist() missed_addressids = region_assets[pd.isnull(region_assets["Confidence Tier"])]["Address ID"].unique().tolist()
# This means that this archetype was never surveyed and so we need to find a sufficiently similar property # This means that this archetype was never surveyed and so we need to find a sufficiently similar property
@ -1785,5 +1796,7 @@ def propsed_wave_3_sample():
if pd.isnull(region_assets["Current EPC Band"]).sum(): if pd.isnull(region_assets["Current EPC Band"]).sum():
raise Exception("Something went wrong") raise Exception("Something went wrong")
results.append(region_assets)
# if __name__ == "__main__": # if __name__ == "__main__":
# main() # main()