Hugging Face's logo

ModelForge
/
spam-classifier

Text Classification
Scikit-learn
Joblib
English
spam
binary-classification
scikit-learn
english
Model card Files Community
spam-classifier
File size: 3,114 Bytes 
7885a28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
 
import numpy as np
from numpy.testing import assert_equal, assert_almost_equal, assert_allclose
from scipy.special import boxcox, boxcox1p, inv_boxcox, inv_boxcox1p
import pytest


# There are more tests of boxcox and boxcox1p in test_mpmath.py.

def test_boxcox_basic():
    x = np.array([0.5, 1, 2, 4])

    # lambda = 0  =>  y = log(x)
    y = boxcox(x, 0)
    assert_almost_equal(y, np.log(x))

    # lambda = 1  =>  y = x - 1
    y = boxcox(x, 1)
    assert_almost_equal(y, x - 1)

    # lambda = 2  =>  y = 0.5*(x**2 - 1)
    y = boxcox(x, 2)
    assert_almost_equal(y, 0.5*(x**2 - 1))

    # x = 0 and lambda > 0  =>  y = -1 / lambda
    lam = np.array([0.5, 1, 2])
    y = boxcox(0, lam)
    assert_almost_equal(y, -1.0 / lam)

def test_boxcox_underflow():
    x = 1 + 1e-15
    lmbda = 1e-306
    y = boxcox(x, lmbda)
    assert_allclose(y, np.log(x), rtol=1e-14)


def test_boxcox_nonfinite():
    # x < 0  =>  y = nan
    x = np.array([-1, -1, -0.5])
    y = boxcox(x, [0.5, 2.0, -1.5])
    assert_equal(y, np.array([np.nan, np.nan, np.nan]))

    # x = 0 and lambda <= 0  =>  y = -inf
    x = 0
    y = boxcox(x, [-2.5, 0])
    assert_equal(y, np.array([-np.inf, -np.inf]))


def test_boxcox1p_basic():
    x = np.array([-0.25, -1e-20, 0, 1e-20, 0.25, 1, 3])

    # lambda = 0  =>  y = log(1+x)
    y = boxcox1p(x, 0)
    assert_almost_equal(y, np.log1p(x))

    # lambda = 1  =>  y = x
    y = boxcox1p(x, 1)
    assert_almost_equal(y, x)

    # lambda = 2  =>  y = 0.5*((1+x)**2 - 1) = 0.5*x*(2 + x)
    y = boxcox1p(x, 2)
    assert_almost_equal(y, 0.5*x*(2 + x))

    # x = -1 and lambda > 0  =>  y = -1 / lambda
    lam = np.array([0.5, 1, 2])
    y = boxcox1p(-1, lam)
    assert_almost_equal(y, -1.0 / lam)


def test_boxcox1p_underflow():
    x = np.array([1e-15, 1e-306])
    lmbda = np.array([1e-306, 1e-18])
    y = boxcox1p(x, lmbda)
    assert_allclose(y, np.log1p(x), rtol=1e-14)


def test_boxcox1p_nonfinite():
    # x < -1  =>  y = nan
    x = np.array([-2, -2, -1.5])
    y = boxcox1p(x, [0.5, 2.0, -1.5])
    assert_equal(y, np.array([np.nan, np.nan, np.nan]))

    # x = -1 and lambda <= 0  =>  y = -inf
    x = -1
    y = boxcox1p(x, [-2.5, 0])
    assert_equal(y, np.array([-np.inf, -np.inf]))


def test_inv_boxcox():
    x = np.array([0., 1., 2.])
    lam = np.array([0., 1., 2.])
    y = boxcox(x, lam)
    x2 = inv_boxcox(y, lam)
    assert_almost_equal(x, x2)

    x = np.array([0., 1., 2.])
    lam = np.array([0., 1., 2.])
    y = boxcox1p(x, lam)
    x2 = inv_boxcox1p(y, lam)
    assert_almost_equal(x, x2)


def test_inv_boxcox1p_underflow():
    x = 1e-15
    lam = 1e-306
    y = inv_boxcox1p(x, lam)
    assert_allclose(y, x, rtol=1e-14)


@pytest.mark.parametrize(
    "x, lmb",
    [[100, 155],
     [0.01, -155]]
)
def test_boxcox_premature_overflow(x, lmb):
    # test boxcox & inv_boxcox
    y = boxcox(x, lmb)
    assert np.isfinite(y)
    x_inv = inv_boxcox(y, lmb)
    assert_allclose(x, x_inv)

    # test boxcox1p & inv_boxcox1p
    y1p = boxcox1p(x-1, lmb)
    assert np.isfinite(y1p)
    x1p_inv = inv_boxcox1p(y1p, lmb)
    assert_allclose(x-1, x1p_inv)