This shows you the differences between two versions of the page.
Next revision | Previous revision | ||
faq:bayesandlogs [2009/04/06 09:52] – created xuesheng | faq:bayesandlogs [2009/04/07 13:54] (current) – external edit 127.0.0.1 | ||
---|---|---|---|
Line 3: | Line 3: | ||
POPFile makes use of Bayes Theorem in the form: | POPFile makes use of Bayes Theorem in the form: | ||
- | | + | P(E|Bi) x P(Bi) |
P(Bi|E) = --------------- | P(Bi|E) = --------------- | ||
P(E) | P(E) | ||
Line 27: | Line 27: | ||
POPFile ignores the term P(E) since it is the same for each calculation and calculates: | POPFile ignores the term P(E) since it is the same for each calculation and calculates: | ||
- | (1) P(Bi|E) = P(E1|Bi) x P(E2|Bi) x ... x P(Eo|Bi) x P(Bi) | + | |
And picks the largest to determine which bucket the email belongs in. But equation (1) works well in theory and badly in practice. | And picks the largest to determine which bucket the email belongs in. But equation (1) works well in theory and badly in practice. | ||
Line 37: | Line 37: | ||
POPFile calculates the following: | POPFile calculates the following: | ||
- | (2) log P(Bi|E) = log P(E1|Bi) + log P(E2|Bi) + ... + P(Eo|Bi) + log P(Bi) | + | |
and then chooses the largest value of log P(Bi|E) in determining the bucket. | and then chooses the largest value of log P(Bi|E) in determining the bucket. |
Should you find anything in the documentation that is incomplete, unclear, outdated or just plain wrong, please let us know and leave a note in the Documentation Forum.