FilesExpand file tree

 master

/

test_learning.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

220 lines (167 loc) · 6.52 KB

 master

/

test_learning.py

Copy path

Top

File metadata and controls

• Code
• Blame

220 lines (167 loc) · 6.52 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

import pytest

import math

import random

from utils import open_data

from learning import *

random.seed("aima-python")

def test_euclidean():

distance = euclidean_distance([1, 2], [3, 4])

assert round(distance, 2) == 2.83

distance = euclidean_distance([1, 2, 3], [4, 5, 6])

assert round(distance, 2) == 5.2

distance = euclidean_distance([0, 0, 0], [0, 0, 0])

assert distance == 0

def test_rms_error():

assert rms_error([2, 2], [2, 2]) == 0

assert rms_error((0, 0), (0, 1)) == math.sqrt(0.5)

assert rms_error((1, 0), (0, 1)) == 1

assert rms_error((0, 0), (0, -1)) == math.sqrt(0.5)

assert rms_error((0, 0.5), (0, -0.5)) == math.sqrt(0.5)

def test_manhattan_distance():

assert manhattan_distance([2, 2], [2, 2]) == 0

assert manhattan_distance([0, 0], [0, 1]) == 1

assert manhattan_distance([1, 0], [0, 1]) == 2

assert manhattan_distance([0, 0], [0, -1]) == 1

assert manhattan_distance([0, 0.5], [0, -0.5]) == 1

def test_mean_boolean_error():

assert mean_boolean_error([1, 1], [0, 0]) == 1

assert mean_boolean_error([0, 1], [1, 0]) == 1

assert mean_boolean_error([1, 1], [0, 1]) == 0.5

assert mean_boolean_error([0, 0], [0, 0]) == 0

assert mean_boolean_error([1, 1], [1, 1]) == 0

def test_mean_error():

assert mean_error([2, 2], [2, 2]) == 0

assert mean_error([0, 0], [0, 1]) == 0.5

assert mean_error([1, 0], [0, 1]) == 1

assert mean_error([0, 0], [0, -1]) == 0.5

assert mean_error([0, 0.5], [0, -0.5]) == 0.5

def test_exclude():

iris = DataSet(name='iris', exclude=[3])

assert iris.inputs == [0, 1, 2]

def test_parse_csv():

Iris = open_data('iris.csv').read()

assert parse_csv(Iris)[0] == [5.1, 3.5, 1.4, 0.2, 'setosa']

def test_weighted_mode():

assert weighted_mode('abbaa', [1, 2, 3, 1, 2]) == 'b'

def test_weighted_replicate():

assert weighted_replicate('ABC', [1, 2, 1], 4) == ['A', 'B', 'B', 'C']

def test_means_and_deviation():

iris = DataSet(name="iris")

means, deviations = iris.find_means_and_deviations()

assert round(means["setosa"][0], 3) == 5.006

assert round(means["versicolor"][0], 3) == 5.936

assert round(means["virginica"][0], 3) == 6.588

assert round(deviations["setosa"][0], 3) == 0.352

assert round(deviations["versicolor"][0], 3) == 0.516

assert round(deviations["virginica"][0], 3) == 0.636

def test_plurality_learner():

zoo = DataSet(name="zoo")

pL = PluralityLearner(zoo)

assert pL([1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 4, 1, 0, 1]) == "mammal"

def test_naive_bayes():

iris = DataSet(name="iris")

# Discrete

nBD = NaiveBayesLearner(iris, continuous=False)

assert nBD([5, 3, 1, 0.1]) == "setosa"

assert nBD([6, 3, 4, 1.1]) == "versicolor"

assert nBD([7.7, 3, 6, 2]) == "virginica"

# Continuous

nBC = NaiveBayesLearner(iris, continuous=True)

assert nBC([5, 3, 1, 0.1]) == "setosa"

assert nBC([6, 5, 3, 1.5]) == "versicolor"

assert nBC([7, 3, 6.5, 2]) == "virginica"

# Simple

data1 = 'a'*50 + 'b'*30 + 'c'*15

dist1 = CountingProbDist(data1)

data2 = 'a'*30 + 'b'*45 + 'c'*20

dist2 = CountingProbDist(data2)

data3 = 'a'*20 + 'b'*20 + 'c'*35

dist3 = CountingProbDist(data3)

dist = {('First', 0.5): dist1, ('Second', 0.3): dist2, ('Third', 0.2): dist3}

nBS = NaiveBayesLearner(dist, simple=True)

assert nBS('aab') == 'First'

assert nBS(['b', 'b']) == 'Second'

assert nBS('ccbcc') == 'Third'

def test_k_nearest_neighbors():

iris = DataSet(name="iris")

kNN = NearestNeighborLearner(iris, k=3)

assert kNN([5, 3, 1, 0.1]) == "setosa"

assert kNN([5, 3, 1, 0.1]) == "setosa"

assert kNN([6, 5, 3, 1.5]) == "versicolor"

assert kNN([7.5, 4, 6, 2]) == "virginica"

def test_truncated_svd():

test_mat = [[17, 0],

[0, 11]]

_, _, eival = truncated_svd(test_mat)

assert isclose(abs(eival[0]), 17)

assert isclose(abs(eival[1]), 11)

test_mat = [[17, 0],

[0, -34]]

_, _, eival = truncated_svd(test_mat)

assert isclose(abs(eival[0]), 34)

assert isclose(abs(eival[1]), 17)

test_mat = [[1, 0, 0, 0, 2],

[0, 0, 3, 0, 0],

[0, 0, 0, 0, 0],

[0, 2, 0, 0, 0]]

_, _, eival = truncated_svd(test_mat)

assert isclose(abs(eival[0]), 3)

assert isclose(abs(eival[1]), 5**0.5)

test_mat = [[3, 2, 2],

[2, 3, -2]]

_, _, eival = truncated_svd(test_mat)

assert isclose(abs(eival[0]), 5)

assert isclose(abs(eival[1]), 3)

def test_decision_tree_learner():

iris = DataSet(name="iris")

dTL = DecisionTreeLearner(iris)

assert dTL([5, 3, 1, 0.1]) == "setosa"

assert dTL([6, 5, 3, 1.5]) == "versicolor"

assert dTL([7.5, 4, 6, 2]) == "virginica"

def test_random_forest():

iris = DataSet(name="iris")

rF = RandomForest(iris)

tests = [([5.0, 3.0, 1.0, 0.1], "setosa"),

([5.1, 3.3, 1.1, 0.1], "setosa"),

([6.0, 5.0, 3.0, 1.0], "versicolor"),

([6.1, 2.2, 3.5, 1.0], "versicolor"),

([7.5, 4.1, 6.2, 2.3], "virginica"),

([7.3, 3.7, 6.1, 2.5], "virginica")]

assert grade_learner(rF, tests) >= 1/3

def test_neural_network_learner():

iris = DataSet(name="iris")

classes = ["setosa", "versicolor", "virginica"]

iris.classes_to_numbers(classes)

nNL = NeuralNetLearner(iris, [5], 0.15, 75)

tests = [([5.0, 3.1, 0.9, 0.1], 0),

([5.1, 3.5, 1.0, 0.0], 0),

([4.9, 3.3, 1.1, 0.1], 0),

([6.0, 3.0, 4.0, 1.1], 1),

([6.1, 2.2, 3.5, 1.0], 1),

([5.9, 2.5, 3.3, 1.1], 1),

([7.5, 4.1, 6.2, 2.3], 2),

([7.3, 4.0, 6.1, 2.4], 2),

([7.0, 3.3, 6.1, 2.5], 2)]

assert grade_learner(nNL, tests) >= 1/3

assert err_ratio(nNL, iris) < 0.2

def test_perceptron():

iris = DataSet(name="iris")

iris.classes_to_numbers()

classes_number = len(iris.values[iris.target])

perceptron = PerceptronLearner(iris)

tests = [([5, 3, 1, 0.1], 0),

([5, 3.5, 1, 0], 0),

([6, 3, 4, 1.1], 1),

([6, 2, 3.5, 1], 1),

([7.5, 4, 6, 2], 2),

([7, 3, 6, 2.5], 2)]

assert grade_learner(perceptron, tests) > 1/2

assert err_ratio(perceptron, iris) < 0.4

def test_random_weights():

min_value = -0.5

max_value = 0.5

num_weights = 10

test_weights = random_weights(min_value, max_value, num_weights)

assert len(test_weights) == num_weights

for weight in test_weights:

assert weight >= min_value and weight <= max_value