The data is downloaded from the following link: http://www3.dsi.uminho.pt/pcortez/wine/. The Portuguese white wine has 11 features (density, sugar, chlorides etc.). Its quality is determined by the wine connoisseurs and marked from three to nine. The task is to predict quality of wine based on its chemical features using four different algorithms. As the dataset is biased the results are shown in confusion matrix. The support vector regression outperformed other algorithms reaching accuracy of 99.4% on testing dataset.
-
Notifications
You must be signed in to change notification settings - Fork 0
kekastepanovic/Predicting-Quality-of-Wine-Based-on-Chemical-Features
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Predicting quality of white wine using chemical attributes
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published