source: orange/orange/doc/datasets/crx.htm @ 1760:9d4bb141fb0e

Revision 1760:9d4bb141fb0e, 1.6 KB checked in by blaz <blaz.zupan@…>, 9 years ago (diff)

data info file

Line 
1<html>
2<head>
3<title>Credit Approval Data Base</title>
4</head>
5<body>
6<h1>Info on Credit Approval Data Base</h1>
7<pre>
81. Title: Credit Approval
9
102. Sources:
11    (confidential)
12    Submitted by quinlan@cs.su.oz.au
13
143.  Past Usage:
15
16    See Quinlan,
17    * "Simplifying decision trees", Int J Man-Machine Studies 27,
18      Dec 1987, pp. 221-234.
19    * "C4.5: Programs for Machine Learning", Morgan Kaufmann, Oct 1992
20 
214.  Relevant Information:
22
23    This file concerns credit card applications.  All attribute names
24    and values have been changed to meaningless symbols to protect
25    confidentiality of the data.
26 
27    This dataset is interesting because there is a good mix of
28    attributes -- continuous, nominal with small numbers of
29    values, and nominal with larger numbers of values.  There
30    are also a few missing values.
31 
325.  Number of Instances: 690
33
346.  Number of Attributes: 15 + class attribute
35
367.  Attribute Information:
37
38    A1: b, a.
39    A2: continuous.
40    A3: continuous.
41    A4: u, y, l, t.
42    A5: g, p, gg.
43    A6: c, d, cc, i, j, k, m, r, q, w, x, e, aa, ff.
44    A7: v, h, bb, j, n, z, dd, ff, o.
45    A8: continuous.
46    A9: t, f.
47    A10:    t, f.
48    A11:    continuous.
49    A12:    t, f.
50    A13:    g, p, s.
51    A14:    continuous.
52    A15:    continuous.
53    A16: +,-         (class attribute)
54
558.  Missing Attribute Values:
56    37 cases (5%) have one or more missing values.  The missing
57    values from particular attributes are:
58
59    A1:  12
60    A2:  12
61    A4:   6
62    A5:   6
63    A6:   9
64    A7:   9
65    A14: 13
66
679.  Class Distribution
68 
69    +: 307 (44.5%)
70    -: 383 (55.5%)
71<pre>
72</body>
73</html>
Note: See TracBrowser for help on using the repository browser.