Description
The wine dataset is a multi-class classification dataset which contains three different wine categories and continuous-valued
features, for a total of observations.
The goal is to classify an unlabeled wine according to its characteristic features.
13
178
In [2]:
1. Perform a train-test split on the data using sklearn train_test_split with test_size=0.3 . Name your variables
X_train , X_test , y_train , y_test . Make sure that your training set contains samples from all the categories.
2. Fit sklearn LogisticRegression model to the training data X_train , y_train , predict the classification labels on the
test data X_test and use sklearn classification_report to evaluate your model against the actual labels y_test .
3. Repeat step 2. using sklearn Naive Bayes classifier GaussianNB .
