def setUp(self):
folder = "docs/"
extension = ".csv"
self.file_name = "description"
self.file_name_1000 = "description_1000"
self.description = pd.read_csv(folder + self.file_name + extension)
self.description_1000 = pd.read_csv(folder + self.file_name_1000 + extension)
self.dp = DocsPreprocessor()
# self.test_array1
# ['a', 'easy', 'way', 'to', 'use', 'android', 'sharepreference']
self.test_array1 = [
'a', 'easy', 'way', 'to', 'use', 'android', 'sharepreference']
# self.test_array2
# [['A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
# 'Registry', 'API']]
self.test_array2 = [[
'A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
'Registry', 'API']]
# self.test_array3
# [['A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
# 'Registry', 'API', '2']]
self.test_array3 = [[
'A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
'Registry', 'API', '2']]
# self.test_array4
# [['A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
# 'Registry', 'API', 'two']]
self.test_array4 = [[
'A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
'Registry', 'API', 'two']]
# self.test_array5
# [['a', 'boilerplate', 'for', 'a', 'Koa', 'Redux', 'React',
# 'application', 'with', 'Webpack,', 'Mocha', 'and', 'SASS']]
self.test_array5 = [[
'a', 'boilerplate', 'for', 'a', 'Koa', 'Redux', 'React',
'application', 'with', 'Webpack,', 'Mocha', 'and', 'SASS'
]]
# self.test_array6
# 'Many', 'corpora', 'have', 'better', 'values', 'than',
# 'you', 'think'
self.test_array6 = [[
'Many', 'corpora', 'have', 'better', 'values', 'than',
'you', 'think'
]]
class TestNMF(unittest.TestCase):
"""
Test the NMF class.
"""
def setUp(self):
self.description_csv = pd.read_csv("docs/description.csv")
self.description_1000_csv = pd.read_csv("docs/description_1000.csv")
self.dp = DocsPreprocessor()
self.description_1000 = self.dp.process(self.description_1000_csv)
self.nmf = NMF(self.description_1000)
def test_type(self):
self.assertEqual(type(self.nmf.docs), list)
""" def test_vectorize(self):
vect, terms = self.nmf.vectorize()
self.assertTrue(len(terms) == 2381)
self.assertEqual((vect.shape[0], vect.shape[1]), (1000, 2381)) """
""" def test_create_model(self):
self.nmf.create_model(10) """
""" def test_run_topic_models(self):
self.nmf.run_topic_models(10, 30, 10) """
""" def test_create_word_embedding_model(self):
w_model = self.nmf.create_word_embedding_model() """
def test_process_models(self):
self.nmf.process_models(10, 30, 10, 20)
class TestBTM(unittest.TestCase):
"""
Test the BTM class.
"""
def setUp(self):
self.description_csv = pd.read_csv("docs/description.csv")
self.description_1000_csv = pd.read_csv("docs/description_1000.csv")
self.dp = DocsPreprocessor()
self.description_1000 = self.dp.process(self.description_1000_csv)
self.btm = BTM(self.description_1000)
def test_btm(self):
self.btm.compute_values(2, 10, 2)
class TestLDA(unittest.TestCase):
"""
Test the LDA class.
"""
def setUp(self):
self.description_csv = pd.read_csv("docs/description.csv")
self.description_1000_csv = pd.read_csv("docs/description_1000.csv")
self.dp = DocsPreprocessor()
self.description_1000 = self.dp.process(self.description_1000_csv)
self.lda = LDA(self.description_1000)
def test_1(self):
k_values, coherence_values, topic_list = self.lda.compute_coherence_values(
5, 20, 5)
def setUp(self):
self.description_csv = pd.read_csv("docs/description.csv")
self.description_1000_csv = pd.read_csv("docs/description_1000.csv")
self.dp = DocsPreprocessor()
self.description_1000 = self.dp.process(self.description_1000_csv)
self.nmf = NMF(self.description_1000)
class TestDocsPreprocessor(unittest.TestCase):
"""
Test the DocsPreprocessor class.
"""
def setUp(self):
folder = "docs/"
extension = ".csv"
self.file_name = "description"
self.file_name_1000 = "description_1000"
self.description = pd.read_csv(folder + self.file_name + extension)
self.description_1000 = pd.read_csv(folder + self.file_name_1000 + extension)
self.dp = DocsPreprocessor()
# self.test_array1
# ['a', 'easy', 'way', 'to', 'use', 'android', 'sharepreference']
self.test_array1 = [
'a', 'easy', 'way', 'to', 'use', 'android', 'sharepreference']
# self.test_array2
# [['A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
# 'Registry', 'API']]
self.test_array2 = [[
'A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
'Registry', 'API']]
# self.test_array3
# [['A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
# 'Registry', 'API', '2']]
self.test_array3 = [[
'A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
'Registry', 'API', '2']]
# self.test_array4
# [['A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
# 'Registry', 'API', 'two']]
self.test_array4 = [[
'A', 'Go', 'API', 'client', 'for', 'the', 'v2', 'Docker',
'Registry', 'API', 'two']]
# self.test_array5
# [['a', 'boilerplate', 'for', 'a', 'Koa', 'Redux', 'React',
# 'application', 'with', 'Webpack,', 'Mocha', 'and', 'SASS']]
self.test_array5 = [[
'a', 'boilerplate', 'for', 'a', 'Koa', 'Redux', 'React',
'application', 'with', 'Webpack,', 'Mocha', 'and', 'SASS'
]]
# self.test_array6
# 'Many', 'corpora', 'have', 'better', 'values', 'than',
# 'you', 'think'
self.test_array6 = [[
'Many', 'corpora', 'have', 'better', 'values', 'than',
'you', 'think'
]]
# Use this test for outputting clean data
def test_process_1000(self):
result = self.dp.process(self.description_1000, self.file_name_1000)
# Use this test for outputting clean data
def test_process_full(self):
result = self.dp.process(self.description, self.file_name)