1. Theory

1.1 naive Bayes Classification

$x_i$: Feature vector for datum $i$

$x_i\in C$ where $C$ is $$

$$P(\omega_j | x_i) = \frac{P(x_i | \omega_j) . P(\omega_j)}{P(x_i)}$$

$P(x_i)$ plays as a normalization factor, and therefore is the same for al



In [ ]: