ML_Algorithm_Scratch_Implementation/sample_data_logistic_reg.py at main · sonakshigupta29/ML_Algorithm_Scratch_Implementation · 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
import numpy as np


def load_sample_data():
    """
    Features:
    ---------
    X[:,0] → hours studied
    X[:,1] → number of practice tests taken

    Label:
    ------
    y = 1 → Pass
    y = 0 → Fail
    added some noisiness in data
    """

    X = np.array([
        [1, 1],
        [1, 2],
        [2, 1],
        [2, 2],
        [2, 3],
        [3, 2],
        [3, 3],
        [3, 4],   # borderline
        [4, 3],
        [4, 4],
        [4, 5],
        [5, 4],   # noise (failed despite effort)
        [5, 5],
        [6, 5],
        [6, 6],
        [7, 6],
        [7, 7],
        [8, 7],
        [8, 8]
    ], dtype=float)

    y = np.array([
        0,  # 1,1
        0,  # 1,2
        0,  # 2,1
        0,  # 2,2
        0,  # 2,3
        0,  # 3,2
        0,  # 3,3
        1,  # 3,4
        1,  # 4,3
        1,  # 4,4
        1,  # 4,5
        0,  # 5,4  <-- noise
        1,  # 5,5
        1,  # 6,5
        1,  # 6,6
        1,  # 7,6
        1,  # 7,7
        1,  # 8,7
        1   # 8,8
    ], dtype=int)

    return X, y