diff --git a/create_dataset.py b/create_dataset.py index 22d9dbf..068a6e4 100644 --- a/create_dataset.py +++ b/create_dataset.py @@ -49,5 +49,14 @@ water_test, water_dev = train_test_split(water_test, train_size=0.66, random_sta #water["is_safe"].value_counts().plot(kind="bar") -waterNorm.to_csv('waterQuality.csv', index=False) + + +directory ='dane' +if not os.path.exists(directory): + os.makedirs('dane') + +waterNorm.to_csv('waterQuality.csv', index=False) +water_train.to_csv('dane/diamonds_train.csv', index=False) +water_test.to_csv('dane/diamonds_test.csv', index=False) +water_dev.to_csv('dane/diamonds_dev.csv', index=False)