junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-08 11:17:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

completing full rename

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2025-02-20 07:57:47 +00:00
parent fe6de36782
commit 63dbda005d
1 changed files with 49 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

51
asset_list/AssetList.py
View file

@ -218,8 +218,9 @@ class AssetList:
STANDARD_ADDRESS_1 = "domna_address_1"
STANDARD_POSTCODE = "domna_postcode"
STANDARD_FULL_ADDRESS = "domna_full_address"
STANDARD_YEAR_BUILT = "domna_year_built"
STANDARD_YEAR_BUILT = "landlord_year_built"
STANDARD_UPRN = "ordnance_survey_uprn"
STANDARD_LANDLORD_PROPERTY_ID = "landlord_property_id"
STANDARD_PROPERTY_TYPE = "landlord_property_type"
STANDARD_WALL_CONSTRUCTION = "landlord_wall_construction"
STANDARD_HEATING_SYSTEM = "landlord_heating_system"
@ -293,6 +294,8 @@ class AssetList:
self.variable_mappings = {}
self.rename_map = {}
def _extract_address1(self, asset_list, full_address_col, postcode_col, method="first_two_words"):
if method not in self.ADDRESS_1_CLEANING_METHODS:
@ -359,6 +362,25 @@ class AssetList:
# We look for string in the form (x-y)
return bool(cls.MULTI_UNIT_REGEX.search(address1_section))
@staticmethod
def _convert_uprn(x):
"""
Used to convert UPRNS to integer strings
:param x: uprn to convert
:return: converted uprn
"""
if pd.isnull(x):
return x
# check if numeric
if np.isreal(x):
return str(int(x))
if str(x).isdigit():
return str(int(x))
return x
def init_standardise(self):
"""
This function is used to standardise the asset list
@ -411,6 +433,12 @@ class AssetList:
# We create the domna property id
self.create_property_id()
# Clean up the UPRN column, if the landlord has provided them
if self.landlord_uprn is not None:
self.standardised_asset_list[self.landlord_uprn] = (
self.standardised_asset_list[self.landlord_uprn].apply(self._convert_uprn)
)
# We keep just the columns we care about and will work through the various columns and standardise
variables = [
self.landlord_property_id,
@ -425,7 +453,21 @@ class AssetList:
self.landlord_heating_system,
self.landlord_existing_pv
]
rename = {}
# Keep just non-null variables (e.g landlord may not provide uprn
variables = [v for v in variables if v is not None]
rename = {
self.landlord_property_id: self.STANDARD_LANDLORD_PROPERTY_ID,
self.address1_colname: self.STANDARD_ADDRESS_1,
self.postcode_colname: self.STANDARD_POSTCODE,
self.full_address_colname: self.STANDARD_FULL_ADDRESS,
self.landlord_uprn: self.STANDARD_UPRN,
self.landlord_property_type: self.STANDARD_PROPERTY_TYPE,
self.landlord_year_built: self.STANDARD_YEAR_BUILT,
self.landlord_wall_construction: self.STANDARD_WALL_CONSTRUCTION,
self.landlord_heating_system: self.STANDARD_HEATING_SYSTEM,
self.landlord_existing_pv: self.STANDARD_EXISTING_PV
}
rename = {k: v for k, v in rename.items() if k is not None}
if self.non_intrusives_present:
variables += self.NON_INTRUSIVES_COLNAMES
@ -538,5 +580,10 @@ class AssetList:
~self.standardised_asset_list[self.DOMNA_PROPERTY_ID].duplicated()
]
# Apply renames to our standard names
self.standardised_asset_list = self.standardised_asset_list.rename(
columns=self.rename_map
)
def create_lookup_mappings(self):
pass