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

Merge branch 'main' of https://github.com/Hestia-Homes/Model into eon

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-05-28 17:22:49 +01:00
commit 52fb07099e
1 changed files with 13 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
etl/epc/Dataset.py
View file

@ -203,11 +203,11 @@ class TrainingDataset(BaseDataset):
common_cols = [[col + "_starting", col + "_ending"] for col in common_cols]
self.df = self.df.loc[
:,
no_suffix_cols
+ only_ending_cols
+ [col for cols in common_cols for col in cols],
]
:,
no_suffix_cols
+ only_ending_cols
+ [col for cols in common_cols for col in cols],
]
def _remove_abnormal_change_in_floor_area(self):
"""
@ -509,7 +509,7 @@ class TrainingDataset(BaseDataset):
expanded_df["is_sandstone_or_limestone"]
== expanded_df["is_sandstone_or_limestone_ending"]
)
]
]
elif component == "floor":
expanded_df = expanded_df[
(expanded_df["is_suspended"] == expanded_df["is_suspended_ending"])
@ -526,7 +526,7 @@ class TrainingDataset(BaseDataset):
expanded_df["is_to_external_air"]
== expanded_df["is_to_external_air_ending"]
)
]
]
elif component == "roof":
expanded_df = expanded_df[
(expanded_df["is_pitched"] == expanded_df["is_pitched_ending"])
@ -539,7 +539,7 @@ class TrainingDataset(BaseDataset):
expanded_df["has_dwelling_above"]
== expanded_df["has_dwelling_above_ending"]
)
]
]
return expanded_df
@ -567,13 +567,12 @@ class TrainingDataset(BaseDataset):
"is_system_built_ending",
"is_timber_frame_ending",
"is_granite_or_whinstone_ending",
"is_as_built_ending",
# "is_as_built_ending",
"is_cob_ending",
"is_assumed_ending",
"is_sandstone_or_limestone_ending",
# Re remove the is_assumed columns
"is_assumed",
"is_assumed_ending",
# "is_assumed",
# "is_assumed_ending",
],
"floor": [
"original_description",
@ -698,6 +697,8 @@ class TrainingDataset(BaseDataset):
# Rename columns to component specific names, if they have not been dropped
expanded_df = expanded_df.rename(
columns={
"is_assumed": f"{component}_is_assumed",
"is_assumed_ending": f"{component}_is_assumed_ending",
"insulation_thickness": f"{component}_insulation_thickness",
"insulation_thickness_ending": f"{component}_insulation_thickness_ending",
"thermal_transmittance": f"{component}_thermal_transmittance",