diff --git a/create-dataset.py b/create-dataset.py
new file mode 100644
index 0000000..34955f4
--- /dev/null
+++ b/create-dataset.py
@@ -0,0 +1,17 @@
+import pandas as pd
+import os
+import numpy as np
+
+
+cutoff = int(os.environ['CUTOFF'])
+
+data = pd.read_csv('./ium_z444510/barcelona_weekends.csv')
+data = data.sample(cutoff)
+data = data.iloc[:, 1:]
+
+train_set, dev_set, test_set = np.split(data.sample(frac=1, random_state=42),
+                                        [int(.6 * len(data)), int(.8 * len(data))])
+
+train_set.to_csv('train.csv', index=False)
+dev_set.to_csv('dev.csv', index=False)
+test_set.to_csv('test.csv', index=False)