Dataminingstuff/assignment3 at master · mkhalil77/Dataminingstuff · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
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
88

This is a temporary script file.
"""
sep = ','
params = []

def read_in_data(file_name,separator):
    file_ = open(file_name, "r")#just for reading

    data = []
    for line in file_:
        line = line.strip('\n')
        split_up =  line.split(separator)
        if len(params) == 0:
            params.append((split_up))
        else:
            data.append(split_up)

    return data


"""
#print read_in_data( 'spectTrain.txt', sep)
#print params
def quality_f(hypo, F):
    g = len(group)
    if F == 1:
        q = (g**.5) *abs(p - p_0)
    elif F == 2:
        q = (g/(1 - g))*(p - p_0)**2
    else:
        q = g * (2 * p-1) + 1 - p_0
    return q

#m rows, n cols, n+1 label
def ref_op(data, m, n):
    hypo = [] #index of attribute for the hypotheses


    return
"""


def pseudo_midos(file_name):
    D = read_in_data(file_name , sep)
    m = int(float(params[0][0]))
    n = int(float(params[0][1]))
    k = int(float(params[0][2]))
    F = int(float(params[0][3]))


    max_level = []
    sum_line  = 0


    #------------------#maximum numberof levels--------------------------------
    for a_i in range(m):
        sum_line  = 0
        for i in range(n):
            sum_line = sum_line + float(D[a_i][i])

        max_level.append(sum_line)

    n_levels = int(max(max_level))
    #--------------------------------------------------------------------------


    #-----------------#add configuration according to levels-------------------
    levels = [[] for i in range(n_levels)]
    for a_i in range(m):
        sum_line  = 0
        for i in range(n):
            sum_line = sum_line + float(D[a_i][i])
            #print sum_line
        if sum_line>0:
            levels[int(sum_line)-1].append(D[a_i])

    #--------------------------------------------------------------------------


    return len(levels[2][3])