diff --git a/etl/bill_savings/EnergyConsumptionModel.py b/etl/bill_savings/EnergyConsumptionModel.py
index ca221175..51972a36 100644
--- a/etl/bill_savings/EnergyConsumptionModel.py
+++ b/etl/bill_savings/EnergyConsumptionModel.py
@@ -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",
diff --git a/etl/bill_savings/data_collection.py b/etl/bill_savings/data_collection.py
index 79afa936..24b10d7f 100644
--- a/etl/bill_savings/data_collection.py
+++ b/etl/bill_savings/data_collection.py
@@ -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)