test_representations.py
5.74 KB
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
import copy
import pytest
import numpy as np
import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
@pytest.mark.parametrize(
"model",
[
("kmeans_pca_topic_model"),
("base_topic_model"),
("custom_topic_model"),
("merged_topic_model"),
("reduced_topic_model"),
],
)
def test_update_topics(model, documents, request):
topic_model = copy.deepcopy(request.getfixturevalue(model))
old_ctfidf = topic_model.c_tf_idf_
old_topics = topic_model.topics_
topic_model.update_topics(documents, n_gram_range=(1, 3))
assert old_ctfidf.shape[1] < topic_model.c_tf_idf_.shape[1]
assert old_topics == topic_model.topics_
updated_topics = [topic if topic != 1 else 0 for topic in old_topics]
topic_model.update_topics(documents, topics=updated_topics, n_gram_range=(1, 3))
assert len(set(old_topics)) - 1 == len(set(topic_model.topics_))
old_topics = topic_model.topics_
updated_topics = [topic if topic != 2 else 0 for topic in old_topics]
topic_model.update_topics(documents, topics=updated_topics, n_gram_range=(1, 3))
assert len(set(old_topics)) - 1 == len(set(topic_model.topics_))
@pytest.mark.parametrize(
"model",
[
("kmeans_pca_topic_model"),
("base_topic_model"),
("custom_topic_model"),
("merged_topic_model"),
("reduced_topic_model"),
("online_topic_model"),
],
)
def test_extract_topics(model, documents, request):
topic_model = copy.deepcopy(request.getfixturevalue(model))
nr_topics = 5
documents = pd.DataFrame(
{
"Document": documents,
"ID": range(len(documents)),
"Topic": np.random.randint(-1, nr_topics - 1, len(documents)),
}
)
topic_model._update_topic_size(documents)
topic_model._extract_topics(documents)
freq = topic_model.get_topic_freq()
assert topic_model.c_tf_idf_.shape[0] == 5
assert topic_model.c_tf_idf_.shape[1] > 100
assert isinstance(freq, pd.DataFrame)
assert nr_topics == len(freq.Topic.unique())
assert freq.Count.sum() == len(documents)
assert len(freq.Topic.unique()) == len(freq)
@pytest.mark.parametrize(
"model",
[
("kmeans_pca_topic_model"),
("base_topic_model"),
("custom_topic_model"),
("merged_topic_model"),
("reduced_topic_model"),
("online_topic_model"),
],
)
def test_extract_topics_custom_cv(model, documents, request):
topic_model = copy.deepcopy(request.getfixturevalue(model))
nr_topics = 5
documents = pd.DataFrame(
{
"Document": documents,
"ID": range(len(documents)),
"Topic": np.random.randint(-1, nr_topics - 1, len(documents)),
}
)
cv = CountVectorizer(ngram_range=(1, 2))
topic_model.vectorizer_model = cv
topic_model._update_topic_size(documents)
topic_model._extract_topics(documents)
freq = topic_model.get_topic_freq()
assert topic_model.c_tf_idf_.shape[0] == 5
assert topic_model.c_tf_idf_.shape[1] > 100
assert isinstance(freq, pd.DataFrame)
assert nr_topics == len(freq.Topic.unique())
assert freq.Count.sum() == len(documents)
assert len(freq.Topic.unique()) == len(freq)
@pytest.mark.parametrize(
"model",
[
("kmeans_pca_topic_model"),
("base_topic_model"),
("custom_topic_model"),
("merged_topic_model"),
("reduced_topic_model"),
("online_topic_model"),
],
)
@pytest.mark.parametrize("reduced_topics", [2, 4, 10])
def test_topic_reduction(model, reduced_topics, documents, request):
topic_model = copy.deepcopy(request.getfixturevalue(model))
old_topics = copy.deepcopy(topic_model.topics_)
old_freq = topic_model.get_topic_freq()
topic_model.reduce_topics(documents, nr_topics=reduced_topics)
new_freq = topic_model.get_topic_freq()
if model != "online_topic_model":
assert old_freq.Count.sum() == new_freq.Count.sum()
assert len(old_freq.Topic.unique()) == len(old_freq)
assert len(new_freq.Topic.unique()) == len(new_freq)
assert len(topic_model.topics_) == len(old_topics)
assert topic_model.topics_ != old_topics
@pytest.mark.parametrize(
"model",
[
("kmeans_pca_topic_model"),
("base_topic_model"),
("custom_topic_model"),
("merged_topic_model"),
("reduced_topic_model"),
("online_topic_model"),
],
)
def test_topic_reduction_edge_cases(model, documents, request):
topic_model = copy.deepcopy(request.getfixturevalue(model))
topic_model.nr_topics = 100
nr_topics = 5
topics = np.random.randint(-1, nr_topics - 1, len(documents))
old_documents = pd.DataFrame({"Document": documents, "ID": range(len(documents)), "Topic": topics})
topic_model._update_topic_size(old_documents)
old_documents = topic_model._sort_mappings_by_frequency(old_documents)
topic_model._extract_topics(old_documents)
old_freq = topic_model.get_topic_freq()
new_documents = topic_model._reduce_topics(old_documents)
new_freq = topic_model.get_topic_freq()
assert not set(old_documents.Topic).difference(set(new_documents.Topic))
pd.testing.assert_frame_equal(old_documents, new_documents)
pd.testing.assert_frame_equal(old_freq, new_freq)
@pytest.mark.parametrize(
"model",
[
("kmeans_pca_topic_model"),
("base_topic_model"),
("custom_topic_model"),
("merged_topic_model"),
("reduced_topic_model"),
("online_topic_model"),
],
)
def test_find_topics(model, request):
topic_model = copy.deepcopy(request.getfixturevalue(model))
similar_topics, similarity = topic_model.find_topics("car")
assert np.mean(similarity) > 0.1
assert len(similar_topics) > 0