13_naive_bayes

# 280 email classification training data email

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: tic models Example 9.2 Probabilistic models for categorical data Table 9.1: Training data for naive Bayes p.280 Email classification: training data Email classification: training data E-mail E-mail #a #b #c Class E-mail a? b? c? e1 e2 e3 e4 e5 e6 e7 e8 0 0 3 2 4 4 3 0 3 3 0 3 3 0 0 0 0 3 0 0 0 3 0 0 + + + + ° ° ° ° e1 e2 e3 e4 e5 e6 e7 e8 0 0 1 1 1 1 1 0 1 1 0 1 1 0 0 0 0 1 0 0 0 1 0 0 + + + + ° ° ° ° August 25, 2012 #c Class E-mail a? b? c? Class 0 0 3 2 4 4 3 0 3 3 0 3 3 0 0 0 0 3 0 0 0 3 0 0 + + + + ° ° ° ° e1 e2 e3 e4 e5 e6 e7 e8 0 0 1 1 1 1 1 0 1 1 0 1 1 0 0 0 0 1 0 0 0 1 0 0 + + + + ° ° ° ° described by bit vectors. Peter Flach (University of Bristol) What are the parameters of the model? Machine Learning: Making Sense of Data |{i : yi = y }| ˆ P (y ) = n August 25, 2012 277 / 349 ˆ P ( xi , y ) |{i : Xij = xi , yi = y }|/n ˆ P ( xi | y ) = = ˆ |{i : yi = y }|/n P (y ) What are the parameters of the model? Machine Learning: Making Sense of Data #b (left) A small e-mail data set described by count vectors. (right) The same data set (left) A small e-mail data set described by count vectors. (right) The same data set Peter Flach (University of Bristol) #a e1 e2 e3 e4 e5 e6 e7 e8 Class described by bit vectors. 273 / 349 277 / 349 19 20 5 10/29/13 9. Probabilistic models Example 9.2 Probabilistic models for categorical data Comments on Naïve Bayes Table 9.1: Training data for naive Bayes p.280 Email classification: training data E-mail #a #b #c Class E-mail a? b? c? e1 e2 e3 e4 e5 e6 e7 e8 0 0 3 2 4 4 3 0 3 3 0 3 3 0 0 0 0 3 0 0 0 3 0 0 + + + + ° ° ° ° e1 e2 e3 e4 e5 e6 e7 e8 0 0 1 1 1 1 1 0 1 1 0 1 1 0 0 0 0 1 0 0 0 1 0 0 Usually features ar...
View Full Document

## This note was uploaded on 02/10/2014 for the course CS 545 taught by Professor Anderson,c during the Fall '08 term at Colorado State.

Ask a homework question - tutors are online