diff --git a/Dockerfile b/Dockerfile
index 2d11201..49de659 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -3,7 +3,7 @@ FROM ubuntu:latest
 RUN apt-get update && \
     apt-get install -y python3-pip
 
-RUN pip3 install --user kaggle pandas
+RUN pip3 install --user kaggle pandas sklearn
 
 ENV PATH="/root/.local/bin:${PATH}"
 
diff --git a/data_processing.py b/data_processing.py
index 9f43108..adb9b42 100644
--- a/data_processing.py
+++ b/data_processing.py
@@ -4,7 +4,7 @@ from sklearn.model_selection import train_test_split
 import pandas as pd
 import subprocess
 
-# subprocess.run(["kaggle", "datasets", "download", "muhammadbinimran/housing-price-prediction-data", "--unzip"])
+subprocess.run(["kaggle", "datasets", "download", "muhammadbinimran/housing-price-prediction-data", "--unzip"])
 housing_price_dataset = pd.read_csv('housing_price_dataset.csv')
 
 hp_train_test, hp_dev = sklearn.model_selection.train_test_split(housing_price_dataset, test_size=0.1)