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

removing redundant funcs

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2026-03-06 13:25:39 +00:00
parent a9cb25de23
commit fb2a69faff
1 changed files with 0 additions and 54 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

54
etl/epc/Record.py
View file

@ -277,22 +277,6 @@ class EPCRecord:
return
def _drop_features(self):
"""
Drop features that are not needed for modelling
"""
self.df = self.df.drop(
columns=["lodgement_date_starting", "lodgement_date_ending"]
)
def _feature_generation(self):
"""
Generate features for modelling
"""
self.df["days_to_lodgement_date"] = self._calculate_days_to(
self.prepared_epc["lodgement_date"]
)
@staticmethod
def _calculate_days_to(lodgement_date):
if isinstance(lodgement_date, str):
@ -387,44 +371,6 @@ class EPCRecord:
same_index = df.apply(pd.Series.duplicated).any()
self.prepared_epc_delta_metadata = df[same_index[~same_index].index]
def _expand_description_to_features(self):
pass
def _expand_description_to_uvalues(self):
# TODO: can be loop over all the descriptions, or done in one
pass
# def _process_and_prune(self, cleaned_lookup: dict):
# """
# This method will merge on the cleaned lookup table and ensure that the building fabric in the
# starting and ending EPC is consistent, so ensure that we are performing our modelling on the cleanest
# possible dataset.
# """
# for component in ["walls", "floor", "roof", "hotwater", "mainheat", "mainheatcont", "windows", "main-fuel"]:
# if component == "main-fuel":
# component = component.replace("-", "_")
# cleaned_key = "main-fuel" if component == "main-fuel" else f"{component}-description"
# left_on_starting = (
# f"{component}_starting" if component == "main-fuel" else f"{component}_description_starting"
# )
# left_on_ending = (
# f"{component}_ending" if component == "main-fuel" else f"{component}_description_ending"
# )
# self.df2 = self.df.merge(
# pd.DataFrame(cleaned_lookup[cleaned_key]),
# how="left",
# left_on=left_on_starting,
# right_on="original_description",
# ).merge(
# pd.DataFrame(cleaned_lookup[cleaned_key]),
# how="left",
# left_on=left_on_ending,
# right_on="original_description",
# suffixes=("", "_ending")
# )
def _clean_records_using_epc_records(self):
"""
This method will clean the records