class TestLdaDiff(unittest.TestCase):
def setUp(self):
texts = [
['human', 'interface', 'computer'],
['survey', 'user', 'computer', 'system', 'response', 'time'],
['eps', 'user', 'interface', 'system'],
['system', 'human', 'system', 'eps'],
['user', 'response', 'time'],
['trees'],
['graph', 'trees'],
['graph', 'minors', 'trees'],
['graph', 'minors', 'survey'],
]
self.dictionary = Dictionary(texts)
self.corpus = [self.dictionary.doc2bow(text) for text in texts]
self.num_topics = 5
self.n_ann_terms = 10
self.model = LdaModel(corpus=self.corpus,
id2word=self.dictionary,
num_topics=self.num_topics,
passes=10)
def testBasic(self):
mdiff, annotation = self.model.diff(self.model,
n_ann_terms=self.n_ann_terms)
self.assertEqual(mdiff.shape, (self.num_topics, self.num_topics))
self.assertEquals(len(annotation), self.num_topics)
self.assertEquals(len(annotation[0]), self.num_topics)
def testIdentity(self):
for dist_name in ["hellinger", "kulback_leibler", "jaccard"]:
mdiff, annotation = self.model.diff(self.model,
n_ann_terms=self.n_ann_terms,
distance=dist_name)
for row in annotation:
for (int_tokens, diff_tokens) in row:
self.assertEquals(diff_tokens, [])
self.assertEquals(len(int_tokens), self.n_ann_terms)
self.assertTrue(
np.allclose(np.diag(mdiff),
np.zeros(mdiff.shape[0], dtype=mdiff.dtype)))
if dist_name == "jaccard":
self.assertTrue(
np.allclose(mdiff, np.zeros(mdiff.shape,
dtype=mdiff.dtype)))
def testInput(self):
self.assertRaises(ValueError,
self.model.diff,
self.model,
n_ann_terms=self.n_ann_terms,
distance='something')
self.assertRaises(ValueError,
self.model.diff, [],
n_ann_terms=self.n_ann_terms,
distance='something')
class TestLdaDiff(unittest.TestCase):
def setUp(self):
self.dictionary = common_dictionary
self.corpus = common_corpus
self.num_topics = 5
self.n_ann_terms = 10
self.model = LdaModel(corpus=self.corpus, id2word=self.dictionary, num_topics=self.num_topics, passes=10)
def test_basic(self):
# test for matrix case
mdiff, annotation = self.model.diff(self.model, n_ann_terms=self.n_ann_terms)
self.assertEqual(mdiff.shape, (self.num_topics, self.num_topics))
self.assertEqual(len(annotation), self.num_topics)
self.assertEqual(len(annotation[0]), self.num_topics)
# test for diagonal case
mdiff, annotation = self.model.diff(self.model, n_ann_terms=self.n_ann_terms, diagonal=True)
self.assertEqual(mdiff.shape, (self.num_topics,))
self.assertEqual(len(annotation), self.num_topics)
def test_identity(self):
for dist_name in ["hellinger", "kullback_leibler", "jaccard"]:
# test for matrix case
mdiff, annotation = self.model.diff(self.model, n_ann_terms=self.n_ann_terms, distance=dist_name)
for row in annotation:
for (int_tokens, diff_tokens) in row:
self.assertEqual(diff_tokens, [])
self.assertEqual(len(int_tokens), self.n_ann_terms)
self.assertTrue(np.allclose(np.diag(mdiff), np.zeros(mdiff.shape[0], dtype=mdiff.dtype)))
if dist_name == "jaccard":
self.assertTrue(np.allclose(mdiff, np.zeros(mdiff.shape, dtype=mdiff.dtype)))
# test for diagonal case
mdiff, annotation = \
self.model.diff(self.model, n_ann_terms=self.n_ann_terms, distance=dist_name, diagonal=True)
for (int_tokens, diff_tokens) in annotation:
self.assertEqual(diff_tokens, [])
self.assertEqual(len(int_tokens), self.n_ann_terms)
self.assertTrue(np.allclose(mdiff, np.zeros(mdiff.shape, dtype=mdiff.dtype)))
if dist_name == "jaccard":
self.assertTrue(np.allclose(mdiff, np.zeros(mdiff.shape, dtype=mdiff.dtype)))
def test_input(self):
self.assertRaises(ValueError, self.model.diff, self.model, n_ann_terms=self.n_ann_terms, distance='something')
self.assertRaises(ValueError, self.model.diff, [], n_ann_terms=self.n_ann_terms, distance='something')
class TestLdaDiff(unittest.TestCase):
def setUp(self):
self.dictionary = common_dictionary
self.corpus = common_corpus
self.num_topics = 5
self.n_ann_terms = 10
self.model = LdaModel(corpus=self.corpus, id2word=self.dictionary, num_topics=self.num_topics, passes=10)
def testBasic(self):
# test for matrix case
mdiff, annotation = self.model.diff(self.model, n_ann_terms=self.n_ann_terms)
self.assertEqual(mdiff.shape, (self.num_topics, self.num_topics))
self.assertEqual(len(annotation), self.num_topics)
self.assertEqual(len(annotation[0]), self.num_topics)
# test for diagonal case
mdiff, annotation = self.model.diff(self.model, n_ann_terms=self.n_ann_terms, diagonal=True)
self.assertEqual(mdiff.shape, (self.num_topics,))
self.assertEqual(len(annotation), self.num_topics)
def testIdentity(self):
for dist_name in ["hellinger", "kullback_leibler", "jaccard"]:
# test for matrix case
mdiff, annotation = self.model.diff(self.model, n_ann_terms=self.n_ann_terms, distance=dist_name)
for row in annotation:
for (int_tokens, diff_tokens) in row:
self.assertEqual(diff_tokens, [])
self.assertEqual(len(int_tokens), self.n_ann_terms)
self.assertTrue(np.allclose(np.diag(mdiff), np.zeros(mdiff.shape[0], dtype=mdiff.dtype)))
if dist_name == "jaccard":
self.assertTrue(np.allclose(mdiff, np.zeros(mdiff.shape, dtype=mdiff.dtype)))
# test for diagonal case
mdiff, annotation = \
self.model.diff(self.model, n_ann_terms=self.n_ann_terms, distance=dist_name, diagonal=True)
for (int_tokens, diff_tokens) in annotation:
self.assertEqual(diff_tokens, [])
self.assertEqual(len(int_tokens), self.n_ann_terms)
self.assertTrue(np.allclose(mdiff, np.zeros(mdiff.shape, dtype=mdiff.dtype)))
if dist_name == "jaccard":
self.assertTrue(np.allclose(mdiff, np.zeros(mdiff.shape, dtype=mdiff.dtype)))
def testInput(self):
self.assertRaises(ValueError, self.model.diff, self.model, n_ann_terms=self.n_ann_terms, distance='something')
self.assertRaises(ValueError, self.model.diff, [], n_ann_terms=self.n_ann_terms, distance='something')
class TestLdaDiff(unittest.TestCase):
def setUp(self):
texts = [
['human', 'interface', 'computer'],
['survey', 'user', 'computer', 'system', 'response', 'time'],
['eps', 'user', 'interface', 'system'],
['system', 'human', 'system', 'eps'],
['user', 'response', 'time'],
['trees'],
['graph', 'trees'],
['graph', 'minors', 'trees'],
['graph', 'minors', 'survey'],
]
self.dictionary = Dictionary(texts)
self.corpus = [self.dictionary.doc2bow(text) for text in texts]
self.num_topics = 5
self.n_ann_terms = 10
self.model = LdaModel(corpus=self.corpus, id2word=self.dictionary, num_topics=self.num_topics, passes=10)
def testBasic(self):
mdiff, annotation = self.model.diff(self.model, n_ann_terms=self.n_ann_terms)
self.assertEqual(mdiff.shape, (self.num_topics, self.num_topics))
self.assertEquals(len(annotation), self.num_topics)
self.assertEquals(len(annotation[0]), self.num_topics)
def testIdentity(self):
for dist_name in ["hellinger", "kullback_leibler", "jaccard"]:
mdiff, annotation = self.model.diff(self.model, n_ann_terms=self.n_ann_terms, distance=dist_name)
for row in annotation:
for (int_tokens, diff_tokens) in row:
self.assertEquals(diff_tokens, [])
self.assertEquals(len(int_tokens), self.n_ann_terms)
self.assertTrue(np.allclose(np.diag(mdiff), np.zeros(mdiff.shape[0], dtype=mdiff.dtype)))
if dist_name == "jaccard":
self.assertTrue(np.allclose(mdiff, np.zeros(mdiff.shape, dtype=mdiff.dtype)))
def testInput(self):
self.assertRaises(ValueError, self.model.diff, self.model, n_ann_terms=self.n_ann_terms, distance='something')
self.assertRaises(ValueError, self.model.diff, [], n_ann_terms=self.n_ann_terms, distance='something')
def plot_distances(lda: models.LdaModel,
distance='jaccard',
num_words=50,
title=None,
other_model=None):
comparison = True
if not other_model:
comparison = False
other_model = lda
mdiff, annotations = lda.diff(other_model,
distance=distance,
num_words=num_words)
topic_difference_heatmap(mdiff=mdiff, title=title, diff_models=comparison)
try:
get_ipython()
import plotly.offline as py
except Exception:
plot_difference = plot_difference_matplotlib
else:
py.init_notebook_mode()
plot_difference = plot_difference_plotly
# In[ ]:
# Heatmap to compare the correlation between LDA and Multicore LDA
mdiff, annotation = ldamodel.diff(ldamulticore,
distance='jaccard',
num_words=30)
plot_difference(
mdiff,
title="LDA vs LDA Multicore Topic difference by Jaccard distance",
annotation=annotation)
# In[ ]:
# Convert LdaMallet model to a gensim model for Visualization
from gensim.models.ldamodel import LdaModel
def convertldaMalletToldaGen(mallet_model):
model_gensim = LdaModel(id2word=mallet_model.id2word,
