This repository was archived by the owner on May 3, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 5
/
Copy pathtext_topics.py
122 lines (106 loc) · 4.29 KB
/
text_topics.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
from __future__ import print_function
import unittest
import pandas as pd
import os
class TextTopicsTests(unittest.TestCase):
def setUp(self):
self.df = pd.read_csv(os.path.join("tests", "test_data.csv"))[:200]
self.doc = self.df["text"].values[0]
def test_scikit_lda_topic_model(self):
from pewanalytics.text.topics import TopicModel
model = TopicModel(
self.df, "text", "sklearn_lda", num_topics=5, min_df=10, max_df=0.8
)
model.fit()
scores = model.get_score()
self.assertIn("perplexity", scores.keys())
self.assertIn("score", scores.keys())
features = model.get_features(self.df)
self.assertEqual(
features.shape, (200, len(model.vectorizer.get_feature_names()))
)
topics = model.get_topics()
self.assertEqual(len(topics), 5)
doc_topics = model.get_document_topics(self.df)
self.assertEqual(doc_topics.shape, (200, 5))
def test_scikit_nmf_topic_model(self):
from pewanalytics.text.topics import TopicModel
model = TopicModel(
self.df, "text", "sklearn_nmf", num_topics=5, min_df=10, max_df=0.8
)
model.fit()
scores = model.get_score()
self.assertEqual(len(scores.keys()), 0)
features = model.get_features(self.df)
self.assertEqual(
features.shape, (200, len(model.vectorizer.get_feature_names()))
)
topics = model.get_topics()
self.assertEqual(len(topics), 5)
doc_topics = model.get_document_topics(self.df)
self.assertEqual(doc_topics.shape, (200, 5))
def test_gensim_lda_topic_model(self):
from pewanalytics.text.topics import TopicModel
model = TopicModel(
self.df, "text", "gensim_lda", num_topics=5, min_df=10, max_df=0.8
)
model.fit()
scores = model.get_score()
self.assertEqual(len(scores.keys()), 0)
features = model.get_features(self.df)
self.assertEqual(
features.shape, (200, len(model.vectorizer.get_feature_names()))
)
topics = model.get_topics()
self.assertEqual(len(topics), 5)
doc_topics = model.get_document_topics(self.df)
self.assertEqual(doc_topics.shape, (200, 5))
def test_gensim_lda_topic_model_multicore(self):
from pewanalytics.text.topics import TopicModel
model = TopicModel(
self.df, "text", "gensim_lda", num_topics=5, min_df=10, max_df=0.8
)
model.fit(use_multicore=True)
scores = model.get_score()
self.assertEqual(len(scores.keys()), 0)
features = model.get_features(self.df)
self.assertEqual(
features.shape, (200, len(model.vectorizer.get_feature_names()))
)
topics = model.get_topics()
self.assertEqual(len(topics), 5)
doc_topics = model.get_document_topics(self.df)
self.assertEqual(doc_topics.shape, (200, 5))
def test_gensim_hdp_topic_model(self):
from pewanalytics.text.topics import TopicModel
model = TopicModel(self.df, "text", "gensim_hdp", min_df=10, max_df=0.8)
model.fit()
scores = model.get_score()
self.assertEqual(len(scores.keys()), 0)
features = model.get_features(self.df)
self.assertEqual(
features.shape, (200, len(model.vectorizer.get_feature_names()))
)
topics = model.get_topics()
num_topics = len(topics)
self.assertGreater(num_topics, 0)
doc_topics = model.get_document_topics(self.df)
self.assertEqual(doc_topics.shape, (200, num_topics))
def test_corex_topic_model(self):
from pewanalytics.text.topics import TopicModel
model = TopicModel(
self.df, "text", "corex", num_topics=5, min_df=10, max_df=0.8
)
model.fit()
scores = model.get_score()
self.assertIn("total_correlation", scores.keys())
features = model.get_features(self.df)
self.assertEqual(
features.shape, (200, len(model.vectorizer.get_feature_names()))
)
topics = model.get_topics()
self.assertEqual(len(topics), 5)
doc_topics = model.get_document_topics(self.df)
self.assertEqual(doc_topics.shape, (200, 5))
def tearDown(self):
pass