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

debugging stoneater alg

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-11-16 16:33:43 +00:00
parent 8f9b8f0886
commit 2158ab2cd5
1 changed files with 7 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
etl/customers/stonewater/Wave 3 Preparation.py
View file

@ -1635,7 +1635,7 @@ def propsed_wave_3_sample():
) )
# TODO: We drop 302 properties that are not priority postcodes - confirm w/ Stonewater # TODO: We drop 302 properties that are not priority postcodes - confirm w/ Stonewater
asset_list = asset_list[asset_list["Archetype ID"] == "NOT PRIORITY POSTCODE"] 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"]
@ -1678,7 +1678,7 @@ def propsed_wave_3_sample():
# #
results = [] results = []
for region in unique_postal_regions: for region in tqdm(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()
archetypes = region_assets["Archetype ID"].unique() archetypes = region_assets["Archetype ID"].unique()
@ -1739,7 +1739,11 @@ def propsed_wave_3_sample():
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 if not missed_addressids:
results.append(region_assets)
continue
# This means that this archetype was never surveyed and so we need to find a sufficiently similar property
final_missed_matches = [] final_missed_matches = []
for a_id in missed_addressids: for a_id in missed_addressids:
property = asset_list[asset_list["Address ID"] == a_id].squeeze() property = asset_list[asset_list["Address ID"] == a_id].squeeze()