[cvs] SF.net SVN: bogofilter:[6781] trunk/bogofilter/src/tests
Fast Bayesian spam filter along lines suggested by Paul Graham
Brought to you by:
m-a
From: <re...@us...> - 2009-02-01 14:10:35
|
Revision: 6781 http://bogofilter.svn.sourceforge.net/bogofilter/?rev=6781&view=rev Author: relson Date: 2009-02-01 14:10:32 +0000 (Sun, 01 Feb 2009) Log Message: ----------- Expand test. Modified Paths: -------------- trunk/bogofilter/src/tests/outputs/token.count.ref trunk/bogofilter/src/tests/t.token.count Modified: trunk/bogofilter/src/tests/outputs/token.count.ref =================================================================== --- trunk/bogofilter/src/tests/outputs/token.count.ref 2009-02-01 13:45:32 UTC (rev 6780) +++ trunk/bogofilter/src/tests/outputs/token.count.ref 2009-02-01 14:10:32 UTC (rev 6781) @@ -58,6 +58,36 @@ "agree" 3 0.000000 0.142857 0.997169 + N_P_Q_S_s_x_md 4 0.000085 0.065746 0.532831 0.017800 0.520000 0.491605 +#### --min-dev=0.496 --token-count-max=8 #### +X-Bogosity: Unsure, tests=bogofilter, spamicity=0.493025 + n pgood pbad fw U + "there" 14 0.291667 0.000000 0.000660 + + "its" 12 0.229167 0.047619 0.172558 - + "all" 21 0.395833 0.095238 0.194216 - + "web" 10 0.187500 0.047619 0.203096 - + "too" 9 0.166667 0.047619 0.222810 - + "more" 15 0.270833 0.095238 0.260471 - + "file" 6 0.104167 0.047619 0.314336 - + "also" 11 0.187500 0.095238 0.337138 - + "about" 16 0.270833 0.142857 0.345518 - + "little" 5 0.083333 0.047619 0.364191 - + "any" 20 0.312500 0.238095 0.432510 - + "would" 15 0.229167 0.190476 0.453979 - + "visit" 3 0.041667 0.047619 0.533255 - + "does" 9 0.125000 0.142857 0.533307 - + "for" 49 0.666667 0.809524 0.548377 - + "how" 14 0.187500 0.238095 0.559390 - + "name" 8 0.104167 0.142857 0.578184 - + "new" 12 0.145833 0.238095 0.620007 - + "this" 45 0.541667 0.904762 0.625473 - + "home" 9 0.104167 0.190476 0.646215 - + "over" 10 0.104167 0.238095 0.695340 - + "way" 11 0.104167 0.285714 0.732481 - + "visiting" 1 0.000000 0.047619 0.991605 - + "dealer" 2 0.000000 0.095238 0.995766 - + "agree" 3 0.000000 0.142857 0.997169 + + N_P_Q_S_s_x_md 2 0.019431 0.005482 0.493025 + 0.017800 0.520000 0.496000 #### --min-dev=0.100 #### X-Bogosity: Unsure, tests=bogofilter, spamicity=0.559839 n pgood pbad fw U @@ -88,6 +118,36 @@ "agree" 3 0.000000 0.142857 0.997169 + N_P_Q_S_s_x_md 18 0.073858 0.193537 0.559839 0.017800 0.520000 0.100000 +#### --min-dev=0.100 --token-count-min=4 #### +X-Bogosity: Unsure, tests=bogofilter, spamicity=0.559839 + n pgood pbad fw U + "there" 14 0.291667 0.000000 0.000660 + + "its" 12 0.229167 0.047619 0.172558 + + "all" 21 0.395833 0.095238 0.194216 + + "web" 10 0.187500 0.047619 0.203096 + + "too" 9 0.166667 0.047619 0.222810 + + "more" 15 0.270833 0.095238 0.260471 + + "file" 6 0.104167 0.047619 0.314336 + + "also" 11 0.187500 0.095238 0.337138 + + "about" 16 0.270833 0.142857 0.345518 + + "little" 5 0.083333 0.047619 0.364191 + + "any" 20 0.312500 0.238095 0.432510 - + "would" 15 0.229167 0.190476 0.453979 - + "visit" 3 0.041667 0.047619 0.533255 - + "does" 9 0.125000 0.142857 0.533307 - + "for" 49 0.666667 0.809524 0.548377 - + "how" 14 0.187500 0.238095 0.559390 - + "name" 8 0.104167 0.142857 0.578184 - + "new" 12 0.145833 0.238095 0.620007 + + "this" 45 0.541667 0.904762 0.625473 + + "home" 9 0.104167 0.190476 0.646215 + + "over" 10 0.104167 0.238095 0.695340 + + "way" 11 0.104167 0.285714 0.732481 + + "visiting" 1 0.000000 0.047619 0.991605 + + "dealer" 2 0.000000 0.095238 0.995766 + + "agree" 3 0.000000 0.142857 0.997169 + + N_P_Q_S_s_x_md 18 0.073858 0.193537 0.559839 + 0.017800 0.520000 0.100000 #### --min-dev=0.100 --token-count-max=8 #### X-Bogosity: Unsure, tests=bogofilter, spamicity=0.514634 n pgood pbad fw U @@ -150,6 +210,8 @@ 0.017800 0.520000 0.067490 #### U 0.493025 --min-dev=0.496 #### U 0.532831 --min-dev=0.496 --token-count-min=4 +#### U 0.493025 --min-dev=0.496 --token-count-max=8 #### U 0.559839 --min-dev=0.100 +#### U 0.559839 --min-dev=0.100 --token-count-min=4 #### U 0.514634 --min-dev=0.100 --token-count-max=8 #### U 0.570641 --min-dev=0.100 --token-count=20 Modified: trunk/bogofilter/src/tests/t.token.count =================================================================== --- trunk/bogofilter/src/tests/t.token.count 2009-02-01 13:45:32 UTC (rev 6780) +++ trunk/bogofilter/src/tests/t.token.count 2009-02-01 14:10:32 UTC (rev 6781) @@ -56,25 +56,30 @@ header_format = %h: %c, tests=bogofilter, spamicity=%p EOF -# 2 tokens scored, increased to 4 by --token-count-min -MIN1="--min-dev=0.496" -MIN2="--min-dev=0.496 --token-count-min=4" +# 2 tokens scored +TST1="--min-dev=0.496" +# min 4 -- score more +MIN1="--min-dev=0.496 --token-count-min=4" +# max 8 -- OK - 2 less than 8 +MAX1="--min-dev=0.496 --token-count-max=8" -# 18 tokens scored, decreased to 8 by --token-count-max -MAX1="--min-dev=0.100" +# 18 tokens scored +TST2="--min-dev=0.100" +# min 4 -- OK - 4 less than 18 +MIN2="--min-dev=0.100 --token-count-min=4" +# max 8 -- score fewer MAX2="--min-dev=0.100 --token-count-max=8" +# fix 20 -- score more +FIX2="--min-dev=0.100 --token-count=20" -# 18 tokens scored, increased to 20 by --token-count -CNT2="--min-dev=0.100 --token-count=20" - cat /dev/null > $OUT -for OPT in "$MIN1" "$MIN2" "$MAX1" "$MAX2" "$CNT2" ; do +for OPT in "$TST1" "$MIN1" "$MAX1" "$TST2" "$MIN2" "$MAX2" "$FIX2" ; do echo "#### $OPT ####" >> $OUT map_rc $BOGOFILTER $OPT -c $CFG -vvv -H -I $INP >> $OUT done -for OPT in "$MIN1" "$MIN2" "$MAX1" "$MAX2" "$CNT2" ; do +for OPT in "$TST1" "$MIN1" "$MAX1" "$TST2" "$MIN2" "$MAX2" "$FIX2" ; do SCORE=$( map_rc $BOGOFILTER $OPT -c $CFG -v -tt -H -I $INP ) echo "#### $SCORE $OPT " >> $OUT done This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site. |