Q: Given Email B with its feature vector. Compute the probability of email B being “spam” and “ham” using Naïve bayes algorithm and then finally assign class label (spam or ham).
P(spam) = 0.65
Email B = < 0, 1, 1, 1 >, = < count(meeting), count(enron), count(dating), count(hi) >
P (meeting | spam) = 0.6, P (meeting | ham) = 0.02
P (enron | spam) = 0.4, P (enron | ham) = 0.001
P (dating | spam) = 0.7, P (dating | ham) = 0.005
P (hi | spam) = 0.3, P (hi | ham) = 0.09
Comments
Leave a comment