HA117 data load

This commit is contained in:
Khalim Conn-Kowlessar 2024-03-08 18:52:32 +00:00
parent 76ef60d06c
commit e3f36fc881

View file

@ -188,7 +188,8 @@ class DataLoader:
"HA25": 154,
"HA41": 26,
"HA50": 5,
"HA63": 0
"HA63": 0,
"HA117": 4
}
def __init__(self, directories, december_figures_filepath, use_cache, rebuild):
@ -308,6 +309,11 @@ class DataLoader:
asset_list["District"].astype(str).str.lower().str.strip() + ", " + \
asset_list["Postcode"].astype(str).str.lower().str.strip()
asset_list["matching_postcode"] = asset_list["Postcode"].astype(str).str.lower().str.strip()
elif ha_name == "HA117":
asset_list["matching_address"] = asset_list["Address1"].astype(str).str.lower().str.strip() + ", " + \
asset_list["Address2"].astype(str).str.lower().str.strip() + ", " + \
asset_list["PostCode"].astype(str).str.lower().str.strip()
asset_list["matching_postcode"] = asset_list["PostCode"].astype(str).str.lower().str.strip()
else:
raise NotImplementedError("implement me")
@ -1800,6 +1806,17 @@ class DataLoader:
return eco3_list
@staticmethod
def correct_ha117_eco3_list(eco3_list):
# Delete rows where postcode is null - there are some placeholder rows where this happens
eco3_list = eco3_list[~pd.isnull(eco3_list["Post Code"])]
eco3_list["Street / Block Name"] = eco3_list["Street / Block Name"].str.replace(
"TARRING ROAD", "155 TARRING ROAD"
)
return eco3_list
def merge_eco3_to_assets(self, asset_list, eco3_list, ha_name):
eco3_list_correction_function = getattr(self, f"correct_{ha_name.lower()}_eco3_list")
@ -4505,13 +4522,13 @@ def app():
# Add in:
priority_has = [
"HA1", "HA2", "HA6", "HA7", "HA12", "HA14", "HA15", "HA16", "HA24", "HA25", "HA28", "HA32", "HA39", "HA41",
"HA48", "HA50", "HA63", "HA107",
"HA48", "HA50", "HA63", "HA107", "HA117"
]
# Next HAs to do: 14 [DONE], 15[DONE], 32 [DONE], 33 [Input format is 4 parts and no eco4 jobs identified - come
# back on this], 28 [DONE], 41 [DONE], 50 [DONE], 48 [DONE], 2 [DONE], 63 [DONE], 12 [DONE]
#
# Consider for ECO4: 13, 136, 117
# COnsider for GBIS: 56, 35, 34
# 117 [WIP]
# Consider for ECO4: 13
# Consider for GBIS: 56, 35, 34
# Ignore for now:
# 38 [problematic, but no ECO4], 10 problematic (no eligibility), 20 has barely any in
# Filter down the directories to only the priority HAs