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
127
128
129
130
|
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
# coding=utf-8
"""Tests for NaiveBayes module."""
import copy
import unittest
import warnings
from Bio import BiopythonDeprecationWarning
with warnings.catch_warnings():
warnings.simplefilter("ignore", category=BiopythonDeprecationWarning)
from Bio import NaiveBayes
# Importing NaiveBayes will itself raise MissingPythonDependencyError
# if NumPy is unavailable.
import numpy as np
try:
hash(np.float64(123.456))
except TypeError:
# Due to a bug in np 1.12.1, this is unhashable under
# PyPy3.5 v5.7 beta - it has been fixed in np
from Bio import MissingPythonDependencyError
raise MissingPythonDependencyError(
"Please update NumPy if you want to use Bio.NaiveBayes "
"(under this version np.float64 is unhashable)."
) from None
del np
class CarTest(unittest.TestCase):
def test_car_data(self):
"""Simple example using car data."""
# Car data from example 'Naive Bayes Classifier example'
# by Eric Meisner November 22, 2003
# http://www.inf.u-szeged.hu/~ormandi/teaching/mi2/02-naiveBayes-example.pdf
xcar = [
["Red", "Sports", "Domestic"],
["Red", "Sports", "Domestic"],
["Red", "Sports", "Domestic"],
["Yellow", "Sports", "Domestic"],
["Yellow", "Sports", "Imported"],
["Yellow", "SUV", "Imported"],
["Yellow", "SUV", "Imported"],
["Yellow", "SUV", "Domestic"],
["Red", "SUV", "Imported"],
["Red", "Sports", "Imported"],
]
ycar = ["Yes", "No", "Yes", "No", "Yes", "No", "Yes", "No", "No", "Yes"]
carmodel = NaiveBayes.train(xcar, ycar)
self.assertEqual(
"Yes", NaiveBayes.classify(carmodel, ["Red", "Sports", "Domestic"])
)
self.assertEqual(
"No", NaiveBayes.classify(carmodel, ["Red", "SUV", "Domestic"])
)
class NaiveBayesTest(unittest.TestCase):
def setUp(self):
# Using example from https://en.wikipedia.org/wiki/Naive_Bayes_classifier
# height (feet), weight (lbs), foot size (inches)
self.xs = [
[6, 180, 12],
[5.92, 190, 11],
[5.58, 170, 12],
[5.92, 165, 10],
[5, 100, 6],
[5.5, 150, 8],
[5.42, 130, 7],
[5.75, 150, 9],
]
self.ys = [
"male",
"male",
"male",
"male",
"female",
"female",
"female",
"female",
]
self.model = NaiveBayes.train(self.xs, self.ys)
self.test = [6, 130, 8]
def test_train_function_no_training_set(self):
self.assertRaises(ValueError, NaiveBayes.train, [], self.ys)
def test_train_function_input_lengths(self):
ys = copy.copy(self.ys)
ys.pop()
self.assertRaises(ValueError, NaiveBayes.train, self.xs, ys)
def test_train_function_uneven_dimension_of_training_set(self):
xs = copy.copy(self.xs)
xs[0] = [1]
self.assertRaises(ValueError, NaiveBayes.train, xs, self.ys)
def test_train_function_with_priors(self):
model = NaiveBayes.train(self.xs, self.ys, priors={"male": 0.1, "female": 0.9})
result = NaiveBayes.calculate(model, self.test, scale=True)
expected = -692.0
self.assertEqual(expected, round(result["male"]))
def test_classify_function(self):
expected = "female"
result = NaiveBayes.classify(self.model, self.test)
self.assertEqual(expected, result)
def test_calculate_function_wrong_dimensionality(self):
xs = self.xs[0]
xs.append(100)
self.assertRaises(ValueError, NaiveBayes.calculate, self.model, xs)
def test_calculate_function_with_scale(self):
result = NaiveBayes.calculate(self.model, self.test, scale=True)
expected = -689.0
self.assertEqual(expected, round(result["male"]))
if __name__ == "__main__":
runner = unittest.TextTestRunner(verbosity=2)
unittest.main(testRunner=runner)
|
