V1          V2          V3             V4
1                            |        SPAM      E-MAIL       DATABASE
2                            |
3                            |          48  continuous           real
4                            |           =  percentage             of
5                            |        i.e.         100              *
6                            |       total      number             of
7                            |      string          of   alphanumeric
8                            |  characters          or end-of-string.
9                            |
10                           |           6  continuous           real
11                           |           =  percentage             of
12                           |        i.e.         100              *
13                           |
14                           |           1  continuous           real
15                           |           =     average         length
16                           |
17                           |           1  continuous        integer
18                           |           =      length             of
19                           |
20                           |           1  continuous        integer
21                           |           =         sum             of
22                           |           =       total         number
23                           |
24                           |           1     nominal          {0,1}
25                           |           =     denotes        whether
26                           |        i.e. unsolicited     commercial
27                           |
28                           |         For        more   information,
29                           |         UCI     Machine       Learning
30                          1,          0.           |          spam,
31             word_freq_make: continuous.
32          word_freq_address: continuous.
33              word_freq_all: continuous.
34               word_freq_3d: continuous.
35              word_freq_our: continuous.
36             word_freq_over: continuous.
37           word_freq_remove: continuous.
38         word_freq_internet: continuous.
39            word_freq_order: continuous.
40             word_freq_mail: continuous.
41          word_freq_receive: continuous.
42             word_freq_will: continuous.
43           word_freq_people: continuous.
44           word_freq_report: continuous.
45        word_freq_addresses: continuous.
46             word_freq_free: continuous.
47         word_freq_business: continuous.
48            word_freq_email: continuous.
49              word_freq_you: continuous.
50           word_freq_credit: continuous.
51             word_freq_your: continuous.
52             word_freq_font: continuous.
53              word_freq_000: continuous.
54            word_freq_money: continuous.
55               word_freq_hp: continuous.
56              word_freq_hpl: continuous.
57           word_freq_george: continuous.
58              word_freq_650: continuous.
59              word_freq_lab: continuous.
60             word_freq_labs: continuous.
61           word_freq_telnet: continuous.
62              word_freq_857: continuous.
63             word_freq_data: continuous.
64              word_freq_415: continuous.
65               word_freq_85: continuous.
66       word_freq_technology: continuous.
67             word_freq_1999: continuous.
68            word_freq_parts: continuous.
69               word_freq_pm: continuous.
70           word_freq_direct: continuous.
71               word_freq_cs: continuous.
72          word_freq_meeting: continuous.
73         word_freq_original: continuous.
74          word_freq_project: continuous.
75               word_freq_re: continuous.
76              word_freq_edu: continuous.
77            word_freq_table: continuous.
78       word_freq_conference: continuous.
79                char_freq_;: continuous.
80                char_freq_(: continuous.
81                char_freq_[: continuous.
82                char_freq_!: continuous.
83                char_freq_$: continuous.
84                  char_freq_
85 capital_run_length_average: continuous.
86 capital_run_length_longest: continuous.
87   capital_run_length_total: continuous.
            V5                                               V6
1   ATTRIBUTES                                              (in
2
3      [0,100]                                       attributes
4        words                                               in
5      (number                                               of
6        words                                               in
7   characters                                          bounded
8
9
10     [0,100]                                       attributes
11  characters                                               in
12     (number                                               of
13
14     [1,...]                                        attribute
15          of                                    uninterrupted
16
17     [1,...]                                        attribute
18     longest                                    uninterrupted
19
20     [1,...]                                        attribute
21      length                                               of
22          of                                          capital
23
24       class                                        attribute
25         the                                           e-mail
26     e-mail.
27
28         see                                             file
29 Repository: http://www.ics.uci.edu/~mlearn/MLRepository.html
30    non-spam                                          classes
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
                       V7               V8                         V9     V10
1                  .names          format)
2
3                      of             type             word_freq_WORD
4                     the           e-mail                       that   match
5                   times              the                       WORD appears
6                 e-mail.                A                       word      in
7                      by non-alphanumeric
8
9
10                     of             type             char_freq_CHAR
11                    the           e-mail                       that   match
12                   CHAR      occurences)                          /   total
13
14                     of             type capital_run_length_average
15              sequences               of                    capital letters
16
17                     of             type capital_run_length_longest
18               sequence               of                    capital letters
19
20                     of             type   capital_run_length_total
21          uninterrupted        sequences                         of capital
22                letters               in                        the  e-mail
23
24                     of             type                       spam
25                    was       considered                       spam     (1)
26
27
28 spambase.DOCUMENTATION               at                        the
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
          V11  V12     V13 V14
1
2
3
4       WORD,
5          in  the e-mail)   /
6        this case      is any
7
8
9
10
11      CHAR,
12 characters   in  e-mail
13
14
15
16
17
18
19
20
21    letters
22
23
24
25         or  not    (0),
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87