Problem with randomtrain

Jake Di Toro karrde at viluppo.net
Fri May 16 22:52:25 CEST 2003


I seem to be having a problem getting randomtrain to work correctly.

I created a directory and word list with a small subset of my
spam/ham, and then ran randomtrain against it.  After a third run it
no longer had to train to "properly classify" the mail.  But when I
ran one of the training mboxes through bogofilter to see what kind of
scores came up, I recieved a mix of ham/unsures and spam/unsures.

some data follows, all commands run in ~/tmp/bogofilter:

>bogofilter -V

bogofilter version 0.10.3.1

>./randomtrain -d . -c ./config -n testgood -s testspam
 spam  reg   good  reg
  260    0     57    0

>cat config | grep -v "^#"
algorithm=fisher
min_dev=0.0
ham_cutoff = 0.10
spam_cutoff = 0.95

>cat testspam | formail -s bogofilter -d . -v -c ./config | head -20
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.947721,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.877095,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=0.998009,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.888167,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.831944,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=0.997927,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=0.993587,version=0.10.3.1
X-Bogosity: Yes, tests=bogofilter, spamicity=1.000000,version=0.10.3.1

>cat testgood | formail -s bogofilter -d . -v -c ./config | head -20
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.500000,version=0.10.3.1
X-Bogosity: No, tests=bogofilter, spamicity=0.000415, version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.490592,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.499901,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.484491,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.472677,version=0.10.3.1
X-Bogosity: No, tests=bogofilter, spamicity=0.000000, version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.500000,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.498308,version=0.10.3.1
X-Bogosity: No, tests=bogofilter, spamicity=0.000000, version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.499999,version=0.10.3.1
X-Bogosity: No, tests=bogofilter, spamicity=0.000000, version=0.10.3.1
X-Bogosity: No, tests=bogofilter, spamicity=0.000000, version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.493587,version=0.10.3.1
X-Bogosity: No, tests=bogofilter, spamicity=0.000000, version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.499999,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.501147,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.489290,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.500000,version=0.10.3.1
X-Bogosity: Unsure, tests=bogofilter, spamicity=0.500000,version=0.10.3.1

-- 
Till Later,
Jake <karrde at viluppo.net>
http://www.viluppo.net/





More information about the Bogofilter mailing list