junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-07-12 13:29:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Extending to HA 7

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-02-27 15:45:33 +00:00
parent d573c4d8a0
commit b26e44b465
1 changed files with 18 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
etl/eligibility/ha_15_32/ha_analysis_batch_3.py
View file

@ -48,6 +48,10 @@ PROPERTY_TYPE_LOOKUP = {
'EXTRACARE SCHEME': "Flat", 'EXTRACARE SCHEME': "Flat",
} }
}, },
"HA7": {
"property_type": {},
"built_form": {}
},
"HA14": { "HA14": {
"property_type": { "property_type": {
"House": "House", "House": "House",
@ -143,6 +147,13 @@ class DataLoader:
asset_list["matching_postcode"] = asset_list[ asset_list["matching_postcode"] = asset_list[
self.COLUMN_CONFIG[ha_name]["postcode"] self.COLUMN_CONFIG[ha_name]["postcode"]
].str.lower().str.strip() ].str.lower().str.strip()
elif ha_name == "HA7":
# Create matching_address by concatenating Address 1, Address 2, Address 3, Address 4, Postcode
asset_list["matching_address"] = asset_list["Address"].str.lower().str.strip() + ", " + \
asset_list["Address2"].str.lower().str.strip() + ", " + \
asset_list["Address3"].str.lower().str.strip() + ", " + \
asset_list["Postcode"].str.lower().str.strip()
asset_list["matching_postcode"] = asset_list["Postcode"].str.lower().str.strip()
elif ha_name == "HA14": elif ha_name == "HA14":
# Create matching_address by concatenating Address 1, Address 2, Address 3, Address 4, Postcode # Create matching_address by concatenating Address 1, Address 2, Address 3, Address 4, Postcode
asset_list["matching_address"] = asset_list["Address 1"].str.lower().str.strip() + ", " + \ asset_list["matching_address"] = asset_list["Address 1"].str.lower().str.strip() + ", " + \
@ -241,6 +252,8 @@ class DataLoader:
def get_asset_sheetname(workbook): def get_asset_sheetname(workbook):
if "Asset List" in workbook.sheetnames: if "Asset List" in workbook.sheetnames:
return "Asset List" return "Asset List"
elif "Asset" in workbook.sheetnames and "Assets" not in workbook.sheetnames:
return "Asset"
else: else:
return "Assets" return "Assets"
@ -311,6 +324,8 @@ class DataLoader:
survey_list = pd.DataFrame(survey_rows, columns=[cell.value for cell in survey_sheet[1]]) survey_list = pd.DataFrame(survey_rows, columns=[cell.value for cell in survey_sheet[1]])
# Remove columns that are None # Remove columns that are None
survey_list = survey_list.loc[:, survey_list.columns.notnull()] survey_list = survey_list.loc[:, survey_list.columns.notnull()]
# Remove rows that are completely empty
survey_list = survey_list.loc[survey_list.loc[:, survey_list.columns].notnull().any(axis=1)]
survey_list["survey_list_row_id"] = [ha_name + "_survey_" + str(i) for i in range(0, len(survey_list))] survey_list["survey_list_row_id"] = [ha_name + "_survey_" + str(i) for i in range(0, len(survey_list))]
# Perform survey list merge # Perform survey list merge
@ -328,6 +343,8 @@ class DataLoader:
ciga_list = pd.DataFrame(ciga_rows, columns=[cell.value for cell in ciga_sheet[1]]) ciga_list = pd.DataFrame(ciga_rows, columns=[cell.value for cell in ciga_sheet[1]])
# Remove columns that are None # Remove columns that are None
ciga_list = ciga_list.loc[:, ciga_list.columns.notnull()] ciga_list = ciga_list.loc[:, ciga_list.columns.notnull()]
# Remove rows that are completely None
ciga_list = ciga_list.loc[ciga_list.loc[:, ciga_list.columns].notnull().any(axis=1)]
# Perform ciga list merge # Perform ciga list merge
if not ciga_list.empty: if not ciga_list.empty:
# Remove rows with missing postcode which happens in a small number of cases # Remove rows with missing postcode which happens in a small number of cases
@ -1880,7 +1897,7 @@ def app():
# Grab the December HA figures filepath # Grab the December HA figures filepath
december_figures_filepath = "local_data/ha_data/HA_December_figures.csv" december_figures_filepath = "local_data/ha_data/HA_December_figures.csv"
priority_has = ["HA1", "HA6", "HA14", "HA39", "HA107"] priority_has = ["HA1", "HA6", "HA7", "HA14", "HA39", "HA107"]
# Filter down the directories to only the priority HAs # Filter down the directories to only the priority HAs
directories = [d for d in directories if d.split("/")[2] in priority_has] directories = [d for d in directories if d.split("/")[2] in priority_has]