Wine is an alcoholic beverage made from fermented grapes. It is a seemingly simple beverage that becomes more complex the more you study it. The good thing is, it does not matter how much you know, nearly everyone can appreciate wine.
In this project we analyzed the physicochemical attributes of wine and tried to understand their relationships and significance with wine quality and types classifications. The goal was to follow standard machine learning and data mining workflow to try to predict the quality of a wine (low, medium, high) and its type (red, white) from the physicochemical attributes.
Two datasets (one for red and one for white wine varieties of the Portuguese “Vlnho Verde” wine ) from UCI Machine Learning Repository were used as a data source.
The complete code can be found in the Wine Classification notebook and detailed description of the project in the slide deck.
- Tools/techniques used: Python, Jupyter Notebook, Scikit-learn
- Algorithms used: Logistic Regression, SVM, Decision Tree, Random Forest
GitHub Repository for this project.