STATISTICS REPORT FOR SPAMASSASSIN RULESET
Classification success on test corpora, at default threshold:
# SUMMARY for threshold 5.0:
# Correctly non-spam: 67508 99.94%
# Correctly spam: 117303 98.51%
# False positives: 42 0.06%
# False negatives: 1780 1.49%
# TCR(l=50): 30.691495 SpamRecall: 98.505% SpamPrec: 99.964%
Results on test corpora at various alternative thresholds:
# SUMMARY for threshold -4.0:
# Correctly non-spam: 723 1.07%
# Correctly spam: 119083 100.00%
# False positives: 66827 98.93%
# False negatives: 0 0.00%
# TCR(l=50): 0.035639 SpamRecall: 100.000% SpamPrec: 64.054%
# SUMMARY for threshold -3.0:
# Correctly non-spam: 816 1.21%
# Correctly spam: 119082 100.00%
# False positives: 66734 98.79%
# False negatives: 1 0.00%
# TCR(l=50): 0.035689 SpamRecall: 99.999% SpamPrec: 64.086%
# SUMMARY for threshold -2.0:
# Correctly non-spam: 49401 73.13%
# Correctly spam: 119081 100.00%
# False positives: 18149 26.87%
# False negatives: 2 0.00%
# TCR(l=50): 0.131228 SpamRecall: 99.998% SpamPrec: 86.775%
# SUMMARY for threshold -1.0:
# Correctly non-spam: 55728 82.50%
# Correctly spam: 119079 100.00%
# False positives: 11822 17.50%
# False negatives: 4 0.00%
# TCR(l=50): 0.201459 SpamRecall: 99.997% SpamPrec: 90.969%
# SUMMARY for threshold 0.0:
# Correctly non-spam: 61994 91.77%
# Correctly spam: 119065 99.98%
# False positives: 5556 8.23%
# False negatives: 18 0.02%
# TCR(l=50): 0.428637 SpamRecall: 99.985% SpamPrec: 95.542%
# SUMMARY for threshold 1.0:
# Correctly non-spam: 65688 97.24%
# Correctly spam: 119012 99.94%
# False positives: 1862 2.76%
# False negatives: 71 0.06%
# TCR(l=50): 1.278112 SpamRecall: 99.940% SpamPrec: 98.460%
# SUMMARY for threshold 2.0:
# Correctly non-spam: 66745 98.81%
# Correctly spam: 118903 99.85%
# False positives: 805 1.19%
# False negatives: 180 0.15%
# TCR(l=50): 2.945412 SpamRecall: 99.849% SpamPrec: 99.328%
# SUMMARY for threshold 3.0:
# Correctly non-spam: 67260 99.57%
# Correctly spam: 118770 99.74%
# False positives: 290 0.43%
# False negatives: 313 0.26%
# TCR(l=50): 8.039087 SpamRecall: 99.737% SpamPrec: 99.756%
# SUMMARY for threshold 4.0:
# Correctly non-spam: 67446 99.85%
# Correctly spam: 117999 99.09%
# False positives: 104 0.15%
# False negatives: 1084 0.91%
# TCR(l=50): 18.950191 SpamRecall: 99.090% SpamPrec: 99.912%
# SUMMARY for threshold 4.5:
# Correctly non-spam: 67482 99.90%
# Correctly spam: 117738 98.87%
# False positives: 68 0.10%
# False negatives: 1345 1.13%
# TCR(l=50): 25.096523 SpamRecall: 98.871% SpamPrec: 99.942%
# SUMMARY for threshold 5.5:
# Correctly non-spam: 67522 99.96%
# Correctly spam: 116618 97.93%
# False positives: 28 0.04%
# False negatives: 2465 2.07%
# TCR(l=50): 30.810608 SpamRecall: 97.930% SpamPrec: 99.976%
# SUMMARY for threshold 6.0:
# Correctly non-spam: 67531 99.97%
# Correctly spam: 115906 97.33%
# False positives: 19 0.03%
# False negatives: 3177 2.67%
# TCR(l=50): 28.854616 SpamRecall: 97.332% SpamPrec: 99.984%
# SUMMARY for threshold 6.5:
# Correctly non-spam: 67543 99.99%
# Correctly spam: 115120 96.67%
# False positives: 7 0.01%
# False negatives: 3963 3.33%
# TCR(l=50): 27.610248 SpamRecall: 96.672% SpamPrec: 99.994%
# SUMMARY for threshold 7.0:
# Correctly non-spam: 67545 99.99%
# Correctly spam: 114100 95.82%
# False positives: 5 0.01%
# False negatives: 4983 4.18%
# TCR(l=50): 22.756163 SpamRecall: 95.816% SpamPrec: 99.996%
# SUMMARY for threshold 8.0:
# Correctly non-spam: 67548 100.00%
# Correctly spam: 111736 93.83%
# False positives: 2 0.00%
# False negatives: 7347 6.17%
# TCR(l=50): 15.990735 SpamRecall: 93.830% SpamPrec: 99.998%
# SUMMARY for threshold 9.0:
# Correctly non-spam: 67550 100.00%
# Correctly spam: 108958 91.50%
# False positives: 0 0.00%
# False negatives: 10125 8.50%
# TCR(l=50): 11.761284 SpamRecall: 91.498% SpamPrec: 100.000%
# SUMMARY for threshold 10.0:
# Correctly non-spam: 67550 100.00%
# Correctly spam: 105529 88.62%
# False positives: 0 0.00%
# False negatives: 13554 11.38%
# TCR(l=50): 8.785820 SpamRecall: 88.618% SpamPrec: 100.000%
# SUMMARY for threshold 12.0:
# Correctly non-spam: 67550 100.00%
# Correctly spam: 97669 82.02%
# False positives: 0 0.00%
# False negatives: 21414 17.98%
# TCR(l=50): 5.560988 SpamRecall: 82.018% SpamPrec: 100.000%
# SUMMARY for threshold 15.0:
# Correctly non-spam: 67550 100.00%
# Correctly spam: 84760 71.18%
# False positives: 0 0.00%
# False negatives: 34323 28.82%
# TCR(l=50): 3.469481 SpamRecall: 71.177% SpamPrec: 100.000%
# SUMMARY for threshold 17.0:
# Correctly non-spam: 67550 100.00%
# Correctly spam: 75737 63.60%
# False positives: 0 0.00%
# False negatives: 43346 36.40%
# TCR(l=50): 2.747266 SpamRecall: 63.600% SpamPrec: 100.000%
# SUMMARY for threshold 20.0:
# Correctly non-spam: 67550 100.00%
# Correctly spam: 62558 52.53%
# False positives: 0 0.00%
# False negatives: 56525 47.47%
# TCR(l=50): 2.106732 SpamRecall: 52.533% SpamPrec: 100.000%
Test hit frequencies, for spam and ham corpora:
(note: S/O indicates ratio of spam hits to overall hits for
each test, where 0.0 = hits only non-spam and 1.0 = hits only spam,
and the 'score' field should be ignored.)
OVERALL SPAM% HAM% S/O RANK SCORE NAME
0 953545 540903 0.638 0.00 0.00 (all messages)
0.00000 63.8058 36.1942 0.638 0.00 0.00 (all messages as %)
9.376 14.6938 0.0000 1.000 1.00 2.52 RCVD_FORGED_WROTE
9.348 14.6504 0.0000 1.000 1.00 4.33 RCVD_FORGED_WROTE2
7.589 11.8932 0.0000 1.000 1.00 3.39 FH_MSGID_XXBLAH
9.647 15.1196 0.0007 1.000 1.00 4.50 L_SPAM_TOOL_13
6.458 10.1207 0.0004 1.000 0.99 3.94 HELO_LOCALHOST
3.682 5.7707 0.0000 1.000 0.98 3.19 HDR_ORDER_FTSDMCXX_BAT
8.141 12.7583 0.0024 1.000 0.98 0.00 HDR_ORDER_FTSDMCXX_001C
3.075 4.8195 0.0000 1.000 0.97 4.39 HELO_DYNAMIC_IPADDR2
5.597 8.7700 0.0022 1.000 0.97 2.43 HELO_DYNAMIC_IPADDR
2.497 3.9135 0.0000 1.000 0.97 3.24 FH_MSGID_000000
2.494 3.9091 0.0000 1.000 0.97 2.03 AXB_XMID_OEGOESNULL
2.434 3.8150 0.0000 1.000 0.96 3.02 AXB_XMID_1510
2.404 3.7669 0.0002 1.000 0.96 4.00 FM_DOESNT_SAY_STOCK
2.388 3.7427 0.0002 1.000 0.96 3.51 FB_SOFTTABS
2.136 3.3479 0.0000 1.000 0.95 3.57 TVD_QUAL_MEDS
2.183 3.4208 0.0002 1.000 0.95 0.00 LONG_TERM_PRICE
2.308 3.6177 0.0006 1.000 0.95 1.63 CTYPE_8SPACE_GIF
6.309 9.8851 0.0043 1.000 0.95 0.91 STOCK_IMG_CTYPE
2.228 3.4916 0.0006 1.000 0.95 0.68 SHORT_TERM_PRICE
6.387 10.0080 0.0044 1.000 0.95 0.00 STOCK_IMG_HDR_FROM
6.117 9.5847 0.0043 1.000 0.95 0.00 STOCK_IMG_HTML
1.988 3.1150 0.0002 1.000 0.95 0.00 STOCK_PRICES
1.839 2.8821 0.0000 1.000 0.95 4.29 HELO_DYNAMIC_HCC
1.711 2.6816 0.0000 1.000 0.95 3.70 MID_DEGREES
1.691 2.6496 0.0000 1.000 0.94 1.56 DRUG_ED_GENERIC
3.368 5.2767 0.0035 0.999 0.94 1.59 CURR_PRICE
4.705 7.3705 0.0052 0.999 0.94 2.27 DC_GIF_UNO_LARGO
1.395 2.1867 0.0000 1.000 0.94 3.49 HELO_DYNAMIC_SPLIT_IP
26.339 41.2748 0.0096 1.000 0.94 1.50 URIBL_JP_SURBL
1.502 2.3533 0.0004 1.000 0.94 1.50 FM_LIKE_STOCKS
1.841 2.8845 0.0013 1.000 0.94 1.93 TVD_RCVD_IP
1.645 2.5773 0.0007 1.000 0.94