A Classification of a Wine Dataset with a Decision Tree, improving its accuracy with Principal Component Analysis(PCA) for dimensionality reduction.

Pairplot without PCA:

Pairplot with PCA:

• The Decision Tree Accuracy without PCA is: 0.94
• The Decision Tree Accuracy with PCA is: 0.96

More information on this dataset at: https://archive.ics.uci.edu/ml/datasets/wine

What libraries you need to run:

• Pandas 0.23.4
• Seaborn 0.9
• Matplotlib 3.0.0
• Scikit-learn 0.20.0

Run wine-final.py to see the plots and the accuracy before and after PCA.

• Thiago Vilela - svthiago