diff --git a/createDataset/createDataset.py b/createDataset/createDataset.py
index 3963850..4c53f65 100644
--- a/createDataset/createDataset.py
+++ b/createDataset/createDataset.py
@@ -4,8 +4,8 @@ from sklearn.model_selection import train_test_split
 home_loan_train = pd.read_csv('loan_sanction_train.csv')
 home_loan_test = pd.read_csv('loan_sanction_test.csv')
 
-home_loan_val_final, home_loan_test_final = train_test_split(home_loan_test, test_size=0.5, random_state=1)
-home_loan_train_final = home_loan_train
+home_loan_train_final, home_loan_test = train_test_split(home_loan_train, test_size=0.2, random_state=1)
+home_loan_test_final, home_loan_val_final = train_test_split(home_loan_test, test_size=0.5, random_state=1)
 
 numeric_cols_train = home_loan_train_final.select_dtypes(include='number').columns
 numeric_cols_test = home_loan_test_final.select_dtypes(include='number').columns