1 | TYA 0.7 (for J116) loaded. Copyright (c) 1997,98 The TYA Team
|
---|
2 | Building classifier and saving it...
|
---|
3 | Loading data...
|
---|
4 | Counting positive examples...
|
---|
5 | Looking for missed keyphrases in the dataset...
|
---|
6 | Found 130 documents in the dataset.
|
---|
7 | Total number of examples missing: 211
|
---|
8 | Total number of positive examples: 668
|
---|
9 | Deleting columns...
|
---|
10 | Discretizing columns...
|
---|
11 | Building classifier...
|
---|
12 |
|
---|
13 | Naive Bayes
|
---|
14 |
|
---|
15 | Class yes: P(C) = 0.00481649
|
---|
16 |
|
---|
17 | Attribute keyword_freq
|
---|
18 | '(-inf-0]' '(0-17]' '(17-18]' '(18-inf)'
|
---|
19 | 0.39479393 0.52711497 0.01952278 0.05856833
|
---|
20 |
|
---|
21 | Attribute tfidf
|
---|
22 | '(-inf-0.000347]' '(0.000347-0.00237]' '(0.00237-0.00512]' '(0.00512-0.0126]' '(0.0126-0.0474]' '(0.0474-inf)'
|
---|
23 | 0.00647948 0.1663067 0.22678186 0.28293737 0.24406048 0.07343413
|
---|
24 |
|
---|
25 | Attribute first_occurrence
|
---|
26 | '(-inf-0.00207]' '(0.00207-0.0103]' '(0.0103-0.0343]' '(0.0343-0.142]' '(0.142-inf)'
|
---|
27 | 0.21861472 0.20995671 0.24242424 0.19264069 0.13636364
|
---|
28 |
|
---|
29 |
|
---|
30 |
|
---|
31 | Class no: P(C) = 0.99518351
|
---|
32 |
|
---|
33 | Attribute keyword_freq
|
---|
34 | '(-inf-0]' '(0-17]' '(17-18]' '(18-inf)'
|
---|
35 | 0.86182702 0.13687325 0.00001057 0.00128916
|
---|
36 |
|
---|
37 | Attribute tfidf
|
---|
38 | '(-inf-0.000347]' '(0.000347-0.00237]' '(0.00237-0.00512]' '(0.00512-0.0126]' '(0.0126-0.0474]' '(0.0474-inf)'
|
---|
39 | 0.22192166 0.52464681 0.16605556 0.06533385 0.02027748 0.00176464
|
---|
40 |
|
---|
41 | Attribute first_occurrence
|
---|
42 | '(-inf-0.00207]' '(0.00207-0.0103]' '(0.0103-0.0343]' '(0.0343-0.142]' '(0.142-inf)'
|
---|
43 | 0.01623061 0.04124223 0.10043747 0.2244706 0.61761909
|
---|
44 |
|
---|
45 |
|
---|
46 | Finding most probable keyphrases...
|
---|
47 | Finding best cutoffs...
|
---|
48 | Best rank cutoff: 8 Best prob cutoff: 0.25999999999999934 F-Measure: 0.22979397781299524
|
---|
49 | Classifying phrases...
|
---|
50 | Preparing data...
|
---|
51 | Counting positive examples...
|
---|
52 | Looking for missed keyphrases in the dataset...
|
---|
53 | Found 500 documents in the dataset.
|
---|
54 | Total number of examples missing: 809
|
---|
55 | Total number of positive examples: 2709
|
---|
56 | Deleting columns...
|
---|
57 | Finding most probable keyphrases...
|
---|
58 | Computing statistics...
|
---|
59 | Rank cutoff: 8
|
---|
60 | Probability cutoff: 0.25999999999999934
|
---|
61 | F-Measure: 0.22598870056497175
|
---|
62 | Rank Prec. Conf.
|
---|
63 | 1 0.308 0.0406 &&&
|
---|
64 | 2 0.287 0.0291 &&&
|
---|
65 | 3 0.26 0.0237 &&&
|
---|
66 | 4 0.2395 0.0196 &&&
|
---|
67 | 5 0.2288 0.0174 &&&
|
---|
68 | 6 0.2177 0.0159 &&&
|
---|
69 | 7 0.2071 0.0143 &&&
|
---|
70 | 8 0.1913 0.013 &&&
|
---|
71 | 9 0.1791 0.0117 &&&
|
---|
72 | 10 0.1696 0.011 &&&
|
---|
73 | 11 0.1622 0.0102 &&&
|
---|
74 | 12 0.1567 0.0097 &&&
|
---|
75 | 13 0.1486 0.0091 &&&
|
---|
76 | 14 0.1436 0.0086 &&&
|
---|
77 | 15 0.1377 0.0081 &&&
|
---|
78 | 16 0.1325 0.0077 &&&
|
---|
79 | 17 0.128 0.0073 &&&
|
---|
80 | 18 0.1236 0.0071 &&&
|
---|
81 | 19 0.1195 0.0068 &&&
|
---|
82 | 20 0.1146 0.0065 &&&
|
---|