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

Added data load for HA25

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-03-02 12:34:22 +00:00
parent cbd4a0052e
commit fc022b8a22
1 changed files with 25 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
etl/eligibility/ha_15_32/ha_analysis_batch_3.py
View file

@ -155,6 +155,10 @@ class DataLoader:
"HA24": { "HA24": {
"address": "Address", "address": "Address",
"postcode": "Postcode" "postcode": "Postcode"
},
"HA25": {
"address": "T1_Address",
"postcode": "matching_postcode"
} }
} }
@ -178,7 +182,7 @@ class DataLoader:
def create_asset_list_matching_address(self, ha_name, asset_list): def create_asset_list_matching_address(self, ha_name, asset_list):
if ha_name in ["HA1", "HA6", "HA16", "HA24"]: if ha_name in ["HA1", "HA6", "HA16", "HA24", "HA25"]:
asset_list["matching_address"] = asset_list[ asset_list["matching_address"] = asset_list[
self.COLUMN_CONFIG[ha_name]["address"] self.COLUMN_CONFIG[ha_name]["address"]
].astype(str).str.lower().str.strip() ].astype(str).str.lower().str.strip()
@ -374,13 +378,23 @@ class DataLoader:
asset_sheetname = self.get_asset_sheetname(workbook) asset_sheetname = self.get_asset_sheetname(workbook)
asset_sheet = workbook[asset_sheetname] asset_sheet = workbook[asset_sheetname]
asset_sheet_colnames = [cell.value for cell in asset_sheet[1]] asset_sheet_colnames = [cell.value for cell in asset_sheet[1]]
if ha_name == "HA25":
asset_sheet_colnames[11] = "matching_postcode"
values_only = not ha_name != "HA25"
rows_data = [] rows_data = []
for row in asset_sheet.iter_rows(min_row=2, values_only=False): if not values_only:
row_data = [cell.value for cell in row] # This will get you the cell values for row in asset_sheet.iter_rows(min_row=2, values_only=values_only):
rows_data.append(row_data) row_data = [cell.value for cell in row] # This will get you the cell values
rows_data.append(row_data)
else:
for row in asset_sheet.iter_rows(min_row=2, values_only=values_only): # use values_only=True to get values
row_data = list(row) # No need for comprehension, values_only=True returns a tuple of values
rows_data.append(row_data)
asset_list = pd.DataFrame(rows_data, columns=asset_sheet_colnames) asset_list = pd.DataFrame(rows_data, columns=asset_sheet_colnames)
asset_list = asset_list.loc[:, asset_list.columns.notnull()] asset_list = asset_list.loc[:, asset_list.columns.notnull()]
# Remove entirely empty rows - consider all rows apart from row_color # Remove entirely empty rows - consider all rows apart from row_color
@ -403,9 +417,10 @@ class DataLoader:
asset_list_correction_function = getattr(self, f"correct_{ha_name.lower()}_asset_list") asset_list_correction_function = getattr(self, f"correct_{ha_name.lower()}_asset_list")
asset_list = asset_list_correction_function(asset_list) asset_list = asset_list_correction_function(asset_list)
# For HA1, there is an exception in the structure of the data. We don't have any survey or ciga lists, and so # For HA1 and HA25, there is an exception in the structure of the data. We don't have any survey or ciga
# lists, and so
# we can return the asset list now # we can return the asset list now
if ha_name == "HA1": if ha_name in ["HA1", "HA25"]:
return asset_list, pd.DataFrame(), pd.DataFrame() return asset_list, pd.DataFrame(), pd.DataFrame()
# We check if there is a survey list # We check if there is a survey list
@ -1149,7 +1164,8 @@ class DataLoader:
"ECO4": "ECO4", "ECO4": "ECO4",
"AFFORDABLE WARMTH": "ECO4", "AFFORDABLE WARMTH": "ECO4",
"ECO4 A/W": "ECO4", "ECO4 A/W": "ECO4",
"ECO4 GBIS (ECO+)": "GBIS" "ECO4 GBIS (ECO+)": "GBIS",
"ECO4 GBIS (ECO+) JJC UNDER 73m²": "GBIS"
} }
eco_eligibility_map = { eco_eligibility_map = {
@ -3305,6 +3321,8 @@ def app():
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", "HA7", "HA14", "HA16", "HA24", "HA25", "HA39", "HA107"] priority_has = ["HA1", "HA6", "HA7", "HA14", "HA16", "HA24", "HA25", "HA39", "HA107"]
# Next HAs to do: 15, 32, 33,
# Then: 28, 41, 38, 10, 14, 20, 48
# 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]