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 1

handle HA56 dupes

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-03-10 14:13:20 +00:00
parent 28434f43c8
commit db7b6de87b
1 changed files with 14 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
etl/eligibility/ha_15_32/ha_analysis_batch_3.py
View file

@ -189,6 +189,7 @@ class DataLoader:
"HA25": 154, "HA25": 154,
"HA41": 26, "HA41": 26,
"HA50": 5, "HA50": 5,
"HA56": 320,
"HA63": 0, "HA63": 0,
"HA117": 4 "HA117": 4
} }
@ -693,6 +694,8 @@ class DataLoader:
asset_list["ECO Eligibility"] asset_list["ECO Eligibility"]
) )
return asset_list
@staticmethod @staticmethod
def correct_ha14_asset_list(asset_list): def correct_ha14_asset_list(asset_list):
@ -2040,6 +2043,14 @@ class DataLoader:
"Ls63nl", "LS6 3NL" "Ls63nl", "LS6 3NL"
) )
# Handle a duplicate
eco3_list = eco3_list[
~((eco3_list["Street / Block Name"] == "Mount Pleasant") &
(eco3_list["Post Code"] == "CW1 3JF") &
(eco3_list["NO "] == 5) &
(eco3_list["INSTALL/ CANCELLATION DATE"] == "CANCELLED 20.5.2022"))
]
return eco3_list return eco3_list
def merge_eco3_to_assets(self, asset_list, eco3_list, ha_name): def merge_eco3_to_assets(self, asset_list, eco3_list, ha_name):
@ -2128,15 +2139,16 @@ class DataLoader:
# HA25 contains 119 missed entries. These are actually 24 unique postcodes, and the majority belong to 2 # HA25 contains 119 missed entries. These are actually 24 unique postcodes, and the majority belong to 2
# where many surveys were conducted on house numbers, not in the asset list # where many surveys were conducted on house numbers, not in the asset list
# 154 missed, 2827 matched for HA 25 # 154 missed, 2827 matched for HA 25
# For HA56, the number of missed is high at 320, however a big portion of these are due to the block being
# listed in the asset list, and individual units being in the survey list
if len(missed) != self.UNMATCHED_ECO3[ha_name]: if len(missed) != self.UNMATCHED_ECO3[ha_name]:
raise ValueError( raise ValueError(
f"Unmatched addresses for {ha_name} is not as expected, got {len(missed)} unmatched" f"Unmatched addresses for {ha_name} is not as expected, got {len(missed)} unmatched"
) )
missed_df = eco3_list[eco3_list["eco3_list_row_id"].isin(missed)]
matching_lookup = pd.DataFrame(matching_lookup) matching_lookup = pd.DataFrame(matching_lookup)
# Check dupes as this will cause problems later on # Check dupes as this will cause problems later on
if matching_lookup["asset_list_row_id"].duplicated().any(): if matching_lookup["asset_list_row_id"].duplicated().sum():
raise ValueError("Duplicated asset list row ids") raise ValueError("Duplicated asset list row ids")
# Merge onto eco3 list # Merge onto eco3 list