Bayes Method

Calculation

P(cause|effect 1, .....effect n) = P(cause) * II P(effect/cause)

Example:

A small training set

No	Attributes				Class
	Outlook	Temperature	Humidity	Windy
1	sunny	hot	high	false	N
2	sunny	hot	high	true	N
3	overcast	hot	high	false	P
4	rain	mild	high	false	P
5	rain	cool	normal	false	P
6	rain	cool	normal	true	N
7	overcast	cool	normal	true	P
8	sunny	mild	high	false	N
9	sunny	cool	normal	false	P
10	rain	mild	normal	false	P
11	sunny	mild	normal	true	P
12	overcast	mild	high	true	P
13	overcast	hot	normal	false	P
14	rain	mild	high	true	N

Suppose that N is Not Win and P is Win

1. Find the probability P(not win | sunny, hot, high, false)

2. Find the probability P( win | sunny, hot, high, false)

Solution:

1 Calculation of P(not win| sunny, hot, high, false)

P(sunny| not_win):

P(hot| not_win):

P(high| not_win):

P(false| not_win):

P(not win| sunny, hot, high, false):

The result of the probability calculation P(not win| sunny, hot, high, false) is

2 Calculation of P(win| sunny, hot, high, false)

P(sunny| win):

P(hot| win):

P(high| win):

P(false| win):

P(win| sunny, hot, high, false):

The result of the probability calculation P(win| sunny, hot, high, false) is

Other examples without cause only effect:

Result of outlook=Sunny, temperature=hot:

Result of outlook=Sunny, temperature=cool:

Result of outlook=Sunny, temperature=mild:

Result of outlook=Rain, temperature=hot:

Result of outlook=Rain, temperature=cool:

Result of outlook=Rain, temperature=mild:

Bayes Method