-
Notifications
You must be signed in to change notification settings - Fork 0
/
test.py
319 lines (268 loc) · 11 KB
/
test.py
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
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
# -*- coding: utf-8 -*-
import unittest
import math
from data import Vector
from word import Cleaner
from search import TFIDF
from data import Loader
class TestVectorFunctions(unittest.TestCase):
def setUp(self):
self.v0 = [0, 0, 0, 0]
self.v1 = [1, 2, 3, 4]
self.v2 = [5, 6, 7, 8]
def test_length(self):
actual = Vector.length(self.v0)
expected = 0.0
self.assertAlmostEqual(actual, expected)
actual = Vector.length(self.v1)
expected = 5.477225575
self.assertAlmostEqual(actual, expected)
actual = Vector.length(self.v2)
expected = 13.190905958
self.assertAlmostEqual(actual, expected)
def test_dot_product(self):
actual = Vector.dot_product(self.v1, self.v2)
expected = 5 + 12 + 21 + 32
self.assertAlmostEqual(actual, expected)
def test_similarity(self):
actual = Vector.similarity(self.v0, self.v1)
expected = 0.0
self.assertAlmostEqual(actual, expected)
actual = Vector.similarity(self.v1, self.v2)
expected = 70.0 / (5.477225575 * 13.190905958)
self.assertAlmostEqual(actual, expected)
class TestCleaner(unittest.TestCase):
def setUp(self):
stopwords = "stop halt basta".split()
self.c = Cleaner(stopwords)
def test_clean_word(self):
word = "STop"
actual = self.c.clean_word(word)
self.assertIsNone(actual)
word = "co.mp%&*uTEr"
actual = self.c.clean_word(word)
self.assertEqual(actual, "comput")
def test_clean_wordlist(self):
words = "stop coMputer #$%&*".split()
actual = self.c.clean_wordlist(words)
expected = ["comput"]
self.assertEqual(actual, expected)
words = "stop computer halt 12-10-2010 morning".split()
actual = self.c.clean_wordlist(words)
expected = ["comput", "12", "10", "2010", "morn"]
self.assertEqual(actual, expected)
class TestTFIDF(unittest.TestCase):
def setUp(self):
stopwords = "stop".split()
keywords = "aaa bbb ccc ddd eee fff".split()
documents = [
('document 1 ccc', "aaa aaa aaa ccc"),
('document 2 stop', "stop aaa bbb ccc"),
('document 3 stop', "aaa"),
('document 4 ddd', "aaa bbb ccc ddd eee")
]
self.s = TFIDF(keywords, documents, Cleaner(stopwords))
def test_keyword_setup(self):
actual = self.s.keywords.items()
expected = [("aaa", 0), ("bbb", 1), ("ccc", 2),
("ddd", 3), ("eee", 4), ("fff", 5)]
self.assertEqual(actual, expected)
def test_documents_setup(self):
actual = self.s.document_vectors
expected = {
0: [3, 0, 2, 0, 0, 0],
1: [1, 1, 1, 0, 0, 0],
2: [1, 0, 0, 0, 0, 0],
3: [1, 1, 1, 2, 1, 0]
}
self.assertEqual(actual, expected)
def test_search_with_no_results(self):
actual = self.s.search("fff")
expected = []
self.assertEqual(actual, expected)
def test_search_with_only_popular_terms(self):
actual = self.s.search("aaa")
expected = [] # because idf=0
self.assertEqual(actual, expected)
def test_tf(self):
document = self.s.document_vectors[0]
actual = self.s.tf(document, 'ccc')
expected = 0.6666666666
self.assertAlmostEqual(actual, expected)
document = self.s.document_vectors[0]
actual = self.s.tf(document, 'aaa')
expected = 1.0
self.assertAlmostEqual(actual, expected)
document = self.s.document_vectors[1]
actual = self.s.tf(document, 'aaa')
expected = 1.0
self.assertAlmostEqual(actual, expected)
document = self.s.document_vectors[2]
actual = self.s.tf(document, 'aaa')
expected = 1.0
self.assertAlmostEqual(actual, expected)
document = self.s.document_vectors[3]
actual = self.s.tf(document, 'aaa')
expected = 0.5
self.assertAlmostEqual(actual, expected)
def test_idf(self):
expected_results = [("aaa", math.log(1.0, 10)),
("bbb", math.log(2.0, 10)),
("ccc", math.log(1.3333333333333, 10)),
("ddd", math.log(4.0, 10)),
("eee", math.log(4.0, 10)),
("fff", 0.0)]
for term, expected in expected_results:
actual = self.s.idf(term)
self.assertAlmostEqual(actual, expected)
class TestTFIDF_flies(unittest.TestCase):
def setUp(self):
stopwords = "stop".split()
keywords = "bee wasp fly fruit like".split()
documents = [
("D1",
"Time fly like an arrow but fruit fly like a banana."),
("D2",
"It's strange that bees and wasps don't like each other."),
("D3",
"The fly attendant sprayed the cabin with a strange fruit "
"aerosol."),
("D4",
"Try not to carry a light, as wasps and bees may fly "
"toward it."),
("D5",
"Fruit fly fly around in swarms. When fly they flap their "
"wings 220 times a second.")
]
self.s = TFIDF(keywords, documents, Cleaner(stopwords))
def test_keyword_setup(self):
actual = self.s.keywords.items()
expected = [("bee", 0),
("fly", 1),
("fruit", 2),
("like", 3),
("wasp", 4)]
self.assertEqual(actual, expected)
def test_documents_setup(self):
actual = self.s.document_vectors
expected = {
0: [0, 2, 1, 2, 0],
1: [1, 0, 0, 1, 1],
2: [0, 1, 1, 0, 0],
3: [1, 1, 0, 0, 1],
4: [0, 3, 1, 0, 0]
}
self.assertEqual(actual, expected)
def test_tf(self):
expected_results = [
(0, [0, 1, 0.5, 1, 0]),
(1, [1, 0, 0, 1, 1]),
(2, [0, 1, 1, 0, 0]),
(3, [1, 1, 0, 0, 1]),
(4, [0, 1, 0.333333333333333333, 0, 0])
]
for index, expected_vector in expected_results:
document = self.s.document_vectors[index]
for word, i in self.s.keywords.items():
actual = self.s.tf(document, word)
expected = expected_vector[i]
self.assertEqual(actual, expected)
def test_idf(self):
expected_results = [
("bee", 0.397940009),
("fly", 0.096910013),
("fruit", 0.22184875),
("like", 0.397940009),
("wasp", 0.397940009)
]
for term, expected in expected_results:
actual = self.s.idf(term)
self.assertAlmostEqual(actual, expected, places=6)
def test_tfidf(self):
expected_results = [
(0, [0, 0.096910013, 0.110924375, 0.397940009, 0]),
(1, [0.397940009, 0, 0, 0.397940009, 0.397940009]),
(2, [0, 0.096910013, 0.22184875, 0, 0]),
(3, [0.397940009, 0.096910013, 0, 0, 0.397940009]),
(4, [0, 0.096910013, 0.073949583, 0, 0])
]
for title, expected_vector in expected_results:
document = self.s.document_vectors[title]
actual_vector = self.s.tfidf(document)
for actual, expected in zip(actual_vector, expected_vector):
self.assertAlmostEqual(actual, expected, places=6)
class TestTFIDF_InfoRetrieval(unittest.TestCase):
def setUp(self):
stopwords = "stop".split()
keywords = "information agency retrieval".split()
# documents = [
# ("Document 1", "information retrieval information retrieval"),
# ("Document 2", "retrieval retrieval retrieval retrieval"),
# ("Document 3", "agency information retrieval agency"),
# ("Document 4", "retrieval agency retrieval agency"),
# ]
documents = Loader.load_documents("data/documents-lab1.txt")
self.s = TFIDF(keywords, documents, Cleaner(stopwords))
def test_keyword_setup(self):
actual = self.s.keywords.items()
expected = [("agenc", 0), ("inform", 1), ("retriev", 2)]
self.assertEqual(actual, expected)
def test_documents_setup(self):
actual = self.s.document_vectors
expected = {
0: [0, 2, 2],
1: [0, 0, 4],
2: [2, 1, 1],
3: [2, 0, 2]
}
self.assertEqual(actual, expected)
def test_tf(self):
expected_results = [
(0, [0, 1, 1]),
(1, [0, 0, 1]),
(2, [1, 0.5, 0.5]),
(3, [1, 0, 1])
]
for index, expected_vector in expected_results:
document = self.s.document_vectors[index]
for word, i in self.s.keywords.items():
actual = self.s.tf(document, word)
expected = expected_vector[i]
self.assertEqual(actual, expected)
def test_idf(self):
expected_results = [
("inform", math.log(2, 10)),
("retriev", 0.0),
("agenc", math.log(2, 10))
]
for term, expected in expected_results:
actual = self.s.idf(term)
self.assertAlmostEqual(actual, expected, places=6)
def test_tfidf(self):
expected_results = [
(0, [0, math.log(2, 10), 0]),
(1, [0, 0, 0]),
(2, [math.log(2, 10), 0.5 * math.log(2, 10), 0]),
(3, [math.log(2, 10), 0, 0])
]
for index, expected_vector in expected_results:
document = self.s.document_vectors[index]
actual_vector = self.s.tfidf(document)
for actual, expected in zip(actual_vector, expected_vector):
self.assertAlmostEqual(actual, expected, places=6)
def test_similarity(self):
expected_results = [(0, 1), (1, 0), (2, math.sqrt(0.2)), (3, 0)]
question_vector = self.s.phrase_to_vector("information retrieval")
question_tfidfs = self.s.tfidf(question_vector)
for index, expected in expected_results:
actual = self.s.doc_question_similarity(index, question_tfidfs)
self.assertEqual(actual, expected)
def test_search(self):
expected = [
("Document 1", 1.0, 0),
("Document 3", math.sqrt(0.2), 2),
]
actual = self.s.search("information retrieval")
self.assertEqual(actual, expected)
if __name__ == '__main__':
unittest.main()