You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spamassassin.apache.org by do...@apache.org on 2007/04/18 06:07:00 UTC
svn commit: r529851 - in
/spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen: scores
scores-set0 scores-set1 stats-set0 stats-set1
Author: dos
Date: Tue Apr 17 21:06:59 2007
New Revision: 529851
URL: http://svn.apache.org/viewvc?view=rev&rev=529851
Log:
generated scores for new rules for scoresets 0 and 1; holy crap, checkout the stats for scoreset 0
Modified:
spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores
spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores-set0
spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores-set1
spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/stats-set0
spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/stats-set1
Modified: spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores
URL: http://svn.apache.org/viewvc/spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores?view=diff&rev=529851&r1=529850&r2=529851
==============================================================================
--- spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores (original)
+++ spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores Tue Apr 17 21:06:59 2007
@@ -0,0 +1,54 @@
+score AXB_MIME_IMG830 0.000 3.599 0.000 0.000
+score AXB_XTIDX_CHAIN 1.201 3.769 0.000 0.000
+score CTYPE_1SPACE_GIF 0.000 3.636 0.000 0.000
+score DOS_PROVISION4 1.000 1.877 0.000 0.000
+score DOS_REPORT_FIN_INC 0.449 2.310 0.000 0.000
+score DOS_STOCK_CDYV_GENERIC 4.299 4.199 0.000 0.000
+score DOS_STOCK_INCOME_STATEMENT 1.000 1.757 0.000 0.000
+score FB_CASINO 0.690 0.000 0.000 0.000
+score FB_GREAT_BEST_SEX 0.154 0.000 0.000 0.000
+score FB_MED1CAT 1.000 1.070 0.000 0.000
+score FB_MEDS_PERCENT 0.976 2.293 0.000 0.000
+score FB_PIPENEWSLETTER 0.000 0.000 0.000 0.000
+score FB_REFI 0.000 0.000 0.000 0.000
+score FB_SMALL_PEN 0.833 0.000 0.000 0.000
+score FB_WHILECONNECTED 0.000 0.000 0.000 0.000
+score FB_WORD1_END_DOLLAR 0.000 2.688 0.000 0.000
+score FH_XMAIL_RND_833 0.000 1.835 0.000 0.000
+score FM_LOTTO_MONEY 0.000 0.000 0.000 0.000
+score FM_LOTTO_YOU_WON 0.107 0.000 0.000 0.000
+score FM_MORTGAGE3PLUS 0.000 0.000 0.000 0.000
+score FM_MORTGAGE4PLUS 0.000 1.000 0.000 0.000
+score FRT_ADULT2 0.311 0.000 0.000 0.000
+score FRT_APPROV 1.000 0.000 0.000 0.000
+score FRT_COCK 0.000 0.000 0.000 0.000
+score FRT_ERECTION 0.188 0.000 0.000 0.000
+score FRT_FREE 0.159 0.000 0.000 0.000
+score FRT_OPPORTUN1 1.218 1.000 0.000 0.000
+score FRT_STOCK1 0.535 0.000 0.000 0.000
+score FRT_STOCK2 0.278 0.000 0.000 0.000
+score FR_TITLE_NUMS 1.000 0.000 0.000 0.000
+score FS_COSTARICA 1.722 0.000 0.000 0.000
+score FS_LOWER_YOUR 0.650 2.198 0.000 0.000
+score FS_NUDE 1.000 2.302 0.000 0.000
+score FS_SPERMAX 0.000 0.000 0.000 0.000
+score FS_WEIGHT_LOSS 0.916 1.318 0.000 0.000
+score FUZZY_SPRM 1.000 0.000 0.000 0.000
+score FUZZY_STOCK 0.575 0.000 0.000 0.000
+score HELO_ADMIN 1.000 0.000 0.000 0.000
+score HS_EXTRA 1.000 0.000 0.000 0.000
+score HS_NO_FLOWERS 0.000 0.000 0.000 0.000
+score KAM_STOCKTIP16 1.000 0.000 0.000 0.000
+score OEBOUND 2.494 0.000 0.000 0.000
+score STOX_RCVD_N_NN_N 4.264 4.099 0.000 0.000
+score TEMPLATE_203_RCVD 1.000 0.000 0.000 0.000
+score TVD_APP_LOAN 1.580 0.000 0.000 0.000
+score TVD_DOLLARS_US 2.715 0.000 0.000 0.000
+score TVD_FW_GRAPHIC_ID1 0.000 1.000 0.000 0.000
+score TVD_FW_GRAPHIC_ID2 0.000 1.322 0.000 0.000
+score TVD_GET_STOCK 1.000 0.000 0.000 0.000
+score TVD_HEAD_EDITION 0.000 0.000 0.000 0.000
+score TVD_HEAD_USR 0.000 0.000 0.000 0.000
+score TVD_PH_BODY_META 2.228 0.000 0.000 0.000
+score TVD_PH_SUBJ_META 1.000 0.000 0.000 0.000
+score VERTICAL_DRUGS_1 0.000 0.000 0.000 0.000
Modified: spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores-set0
URL: http://svn.apache.org/viewvc/spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores-set0?view=diff&rev=529851&r1=529850&r2=529851
==============================================================================
--- spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores-set0 (original)
+++ spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores-set0 Tue Apr 17 21:06:59 2007
@@ -0,0 +1,49 @@
+score AXB_XTIDX_CHAIN 1.201
+score DOS_PROVISION4 1.000
+score DOS_REPORT_FIN_INC 0.449
+score DOS_STOCK_CDYV_GENERIC 4.299
+score DOS_STOCK_INCOME_STATEMENT 1.000
+score FB_CASINO 0.690
+score FB_GREAT_BEST_SEX 0.154
+score FB_MED1CAT 1.000
+score FB_MEDS_PERCENT 0.976
+score FB_REFI 0.043
+score FB_SMALL_PEN 0.833
+score FB_WORD1_END_DOLLAR 0.001
+score FM_LOTTO_MONEY 0.001
+score FM_LOTTO_YOU_WON 0.107
+score FM_MORTGAGE3PLUS 0.001
+score FRT_ADULT2 0.311
+score FRT_APPROV 1.000
+score FRT_COCK 0.001
+score FRT_ERECTION 0.188
+score FRT_FREE 0.159
+score FRT_OPPORTUN1 1.218
+score FRT_STOCK1 0.535
+score FRT_STOCK2 0.278
+score FR_TITLE_NUMS 1.000
+score FS_COSTARICA 1.722
+score FS_LOWER_YOUR 0.650
+score FS_NUDE 1.000
+score FS_WEIGHT_LOSS 0.916
+score FUZZY_SPRM 1.000
+score FUZZY_STOCK 0.575
+score HELO_ADMIN 1.000
+score HS_EXTRA 1.000
+score KAM_STOCKTIP16 1.000
+score OEBOUND 2.494
+score STOX_RCVD_N_NN_N 4.264
+score TEMPLATE_203_RCVD 1.000
+score TVD_APP_LOAN 1.580
+score TVD_DOLLARS_US 2.715
+score TVD_GET_STOCK 1.000
+score TVD_PH_BODY_META 2.228
+score TVD_PH_SUBJ_META 1.000
+# in active.list but have no hits in recent corpus
+score FB_PIPENEWSLETTER 0.000
+score FB_WHILECONNECTED 0.000
+score FS_SPERMAX 0.000
+score HS_NO_FLOWERS 0.000
+score TVD_HEAD_EDITION 0.000
+score TVD_HEAD_USR 0.000
+score VERTICAL_DRUGS_1 0.000
Modified: spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores-set1
URL: http://svn.apache.org/viewvc/spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores-set1?view=diff&rev=529851&r1=529850&r2=529851
==============================================================================
--- spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores-set1 (original)
+++ spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/scores-set1 Tue Apr 17 21:06:59 2007
@@ -0,0 +1,19 @@
+score AXB_MIME_IMG830 3.599
+score AXB_XTIDX_CHAIN 3.769
+score CTYPE_1SPACE_GIF 3.636
+score DOS_PROVISION4 1.877
+score DOS_REPORT_FIN_INC 2.310
+score DOS_STOCK_CDYV_GENERIC 4.199
+score DOS_STOCK_INCOME_STATEMENT 1.757
+score FB_MED1CAT 1.070
+score FB_MEDS_PERCENT 2.293
+score FB_WORD1_END_DOLLAR 2.688
+score FH_XMAIL_RND_833 1.835
+score FM_MORTGAGE4PLUS 1.000
+score FRT_OPPORTUN1 1.000
+score FS_LOWER_YOUR 2.198
+score FS_NUDE 2.302
+score FS_WEIGHT_LOSS 1.318
+score STOX_RCVD_N_NN_N 4.099
+score TVD_FW_GRAPHIC_ID1 1.000
+score TVD_FW_GRAPHIC_ID2 1.322
Modified: spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/stats-set0
URL: http://svn.apache.org/viewvc/spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/stats-set0?view=diff&rev=529851&r1=529850&r2=529851
==============================================================================
--- spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/stats-set0 (original)
+++ spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/stats-set0 Tue Apr 17 21:06:59 2007
@@ -0,0 +1,40 @@
+##### WITH NEW RULES AND SCORES #####
+
+# SUMMARY for threshold 5.0:
+# Correctly non-spam: 97753 17.925% (97.167% of non-spam corpus)
+# Correctly spam: 418895 76.813% (94.188% of spam corpus)
+# False positives: 2850 0.523% (2.833% of nonspam, 155678 weighted)
+# False negatives: 25848 4.740% (5.812% of spam, 74890 weighted)
+# Average score for spam: 16.7 nonspam: 1.0
+# Average for false-pos: 6.2 false-neg: 2.9
+# TOTAL: 545346 100.00%
+
+Reading scores from "tmprules"...
+Reading per-message hit stat logs and scores...
+
+# SUMMARY for threshold 5.0:
+# Correctly non-spam: 12380 97.35%
+# Correctly spam: 52193 94.15%
+# False positives: 337 2.65%
+# False negatives: 3243 5.85%
+# TCR(l=50): 2.758971 SpamRecall: 94.150% SpamPrec: 99.358%
+
+##### WITHOUT NEW RULES AND SCORES #####
+Reading scores from "../rules-base"...
+Reading per-message hit stat logs and scores...
+
+# SUMMARY for threshold 5.0:
+# Correctly non-spam: 98045 97.46%
+# Correctly spam: 235192 52.88%
+# False positives: 2558 2.54%
+# False negatives: 209551 47.12%
+# TCR(l=50): 1.317948 SpamRecall: 52.883% SpamPrec: 98.924%
+Reading scores from "../rules-base"...
+Reading per-message hit stat logs and scores...
+
+# SUMMARY for threshold 5.0:
+# Correctly non-spam: 12404 97.54%
+# Correctly spam: 29584 53.37%
+# False positives: 313 2.46%
+# False negatives: 25852 46.63%
+# TCR(l=50): 1.335743 SpamRecall: 53.366% SpamPrec: 98.953%
Modified: spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/stats-set1
URL: http://svn.apache.org/viewvc/spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/stats-set1?view=diff&rev=529851&r1=529850&r2=529851
==============================================================================
--- spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/stats-set1 (original)
+++ spamassassin/rules/trunk/sandbox/dos/new-rule-score-gen/stats-set1 Tue Apr 17 21:06:59 2007
@@ -0,0 +1,40 @@
+##### WITH NEW RULES AND SCORES #####
+
+# SUMMARY for threshold 5.0:
+# Correctly non-spam: 52067 27.036% (99.077% of non-spam corpus)
+# Correctly spam: 137506 71.402% (98.198% of spam corpus)
+# False positives: 485 0.252% (0.923% of nonspam, 39184 weighted)
+# False negatives: 2523 1.310% (1.802% of spam, 8528 weighted)
+# Average score for spam: 25.8 nonspam: 0.0
+# Average for false-pos: 6.1 false-neg: 3.4
+# TOTAL: 192581 100.00%
+
+Reading scores from "tmprules"...
+Reading per-message hit stat logs and scores...
+
+# SUMMARY for threshold 5.0:
+# Correctly non-spam: 6569 98.87%
+# Correctly spam: 17263 98.34%
+# False positives: 75 1.13%
+# False negatives: 291 1.66%
+# TCR(l=50): 4.343974 SpamRecall: 98.342% SpamPrec: 99.567%
+
+##### WITHOUT NEW RULES AND SCORES #####
+Reading scores from "../rules-base"...
+Reading per-message hit stat logs and scores...
+
+# SUMMARY for threshold 5.0:
+# Correctly non-spam: 52056 99.06%
+# Correctly spam: 126615 90.42%
+# False positives: 496 0.94%
+# False negatives: 13414 9.58%
+# TCR(l=50): 3.664338 SpamRecall: 90.421% SpamPrec: 99.610%
+Reading scores from "../rules-base"...
+Reading per-message hit stat logs and scores...
+
+# SUMMARY for threshold 5.0:
+# Correctly non-spam: 6572 98.92%
+# Correctly spam: 15862 90.36%
+# False positives: 72 1.08%
+# False negatives: 1692 9.64%
+# TCR(l=50): 3.317082 SpamRecall: 90.361% SpamPrec: 99.548%