Exercise

Training and testing the "fake news" model with TfidfVectorizer

Now that you have evaluated the model using the CountVectorizer, you'll do the same using the TfidfVectorizer with a Naive Bayes model.

The training and test sets have been created, and tfidf_vectorizer, tfidf_train, and tfidf_test have been computed. Additionally, MultinomialNB and metrics have been imported from, respectively, sklearn.naive_bayes and sklearn.

Instructions

100 XP
  • Instantiate a MultinomialNB classifier called nb_classifier.
  • Fit the classifier to the training data.
  • Compute the predicted tags for the test data.
  • Calculate and print the accuracy score of the classifier.
  • Compute the confusion matrix. As in the previous exercise, specify the keyword argument labels=['FAKE', 'REAL'] so that the resulting confusion matrix is easier to read.