Added the drop columns for roof

This commit is contained in:
Khalim Conn-Kowlessar 2023-09-19 11:20:54 +01:00
parent 58913a52af
commit 3a864c6c21
2 changed files with 11 additions and 15 deletions

View file

@ -51,6 +51,8 @@ def process_and_prune_desriptions(df, cleaned_lookup):
# TODO: In a future iteration, we can test using the binary features and the insulation thickness
# estimates, we well as estimated U-values
# TODO: If we integrate u values, we can probably remove insulation thickness
cols_to_drop = {
"walls": [
'original_description', 'clean_description', 'thermal_transmittance_unit',
@ -73,20 +75,15 @@ def process_and_prune_desriptions(df, cleaned_lookup):
"is_assumed_ENDING"
],
"roof": [
'original_description', 'thermal_transmittance',
'thermal_transmittance_unit', 'is_pitched', 'is_roof_room', 'is_loft',
'is_flat', 'is_thatched', 'is_at_rafters', 'is_assumed',
'has_dwelling_above', 'is_valid', 'insulation_thickness',
'original_description_ENDING',
'thermal_transmittance_ENDING', 'thermal_transmittance_unit_ENDING',
'is_pitched_ENDING', 'is_roof_room_ENDING', 'is_loft_ENDING',
'is_flat_ENDING', 'is_thatched_ENDING', 'is_at_rafters_ENDING',
'is_assumed_ENDING', 'has_dwelling_above_ENDING', 'is_valid_ENDING',
'insulation_thickness_ENDING',
"original_description", "clean_description", "thermal_transmittance_unit",
"is_assumed", "is_valid", "original_description_ENDING", "clean_description_ENDING",
"thermal_transmittance_unit_ENDING", "is_pitched_ENDING", "is_roof_room_ENDING",
"is_loft_ENDING", "is_flat_ENDING", "is_thatched_ENDING", "is_at_rafters_ENDING",
"has_dwelling_above_ENDING", "is_assumed_ENDING", "is_valid_ENDING"
]
}
for component in ["walls", "floor", "roof"]:
for component in ["walls", "floor", "roof", "hotwater"]:
component_upper = component.upper()
df = df.merge(
@ -120,7 +117,7 @@ def process_and_prune_desriptions(df, cleaned_lookup):
(df["is_to_unheated_space"] == df["is_to_unheated_space_ENDING"]) &
(df["is_to_external_air"] == df["is_to_external_air_ENDING"])
]
else:
elif component == "roof":
df = df[
(df["is_pitched"] == df["is_pitched_ENDING"]) &
(df["is_roof_room"] == df["is_roof_room_ENDING"]) &

View file

@ -1,8 +1,8 @@
from core.Logger import logger
from model_data.simulation_system.core.Logger import logger
import argparse
import pandas as pd
from pathlib import Path
from core.Settings import RANDOM_SEED, TRAIN_AND_VALIDATION_DATA_NAME, TEST_DATA_NAME
from model_data.simulation_system.core.Settings import RANDOM_SEED, TRAIN_AND_VALIDATION_DATA_NAME, TEST_DATA_NAME
def ingest_arguments() -> argparse.Namespace:
@ -96,7 +96,6 @@ def main(
if __name__ == "__main__":
logger.info("--- Generate test data pipeline ---")
args = ingest_arguments()