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

implemented xgboost which performs really well

Browse source
This commit is contained in:
Khalim Conn-Kowlessar 2024-07-02 17:48:06 +01:00
parent 39a4c2e975
commit 0a1f728f37
2 changed files with 3 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
etl/bill_savings/EnergyConsumptionModel.py
View file

@ -2,7 +2,6 @@ import pandas as pd
from xgboost import XGBRegressor
from datetime import datetime
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_percentage_error
from sklearn.feature_selection import RFECV
from utils.s3 import save_pickle_to_s3, read_pickle_from_s3, read_dataframe_from_s3_parquet
@ -16,8 +15,8 @@ class EnergyConsumptionModel:
FEATURES = {
"heating_kwh": [
"lodgement-year", "lodgement-month", "current-energy-efficiency", "energy-consumption-current",
"heating-cost-current", "main-fuel", "total-floor-area", "number-heated-rooms", "number-habitable-rooms",
"mainheat-energy-eff"
"heating-cost-current", "total-floor-area", "number-heated-rooms", "number-habitable-rooms",
# "mainheat-energy-eff", "mainheat-description", "main-fuel",
],
"hot_water_kwh": [
"lodgement-year", "lodgement-month", "current-energy-efficiency", "energy-consumption-current",

2
etl/bill_savings/data_collection.py
View file

@ -133,7 +133,7 @@ def app():
energy_consumption_data = []
for i, directory in tqdm(enumerate(epc_directories), total=len(epc_directories)):
# Skip the first 50
if i < 50:
if i < 90:
continue
data = pd.read_csv(directory / "certificates.csv", low_memory=False)