def test_run_normalize_words(self):
normalizer = LemmagenLemmatizer()
corpus = normalizer(self.corpus)
words = ["minor", "tree"]
results = run(corpus, words, {}, {ScoringMethods.TF_IDF}, {},
AggregationMethods.MEAN, self.state)
self.assertEqual(len(results.scores), 2)
words = ["minors", "trees"]
results = run(corpus, words, {}, {ScoringMethods.TF_IDF}, {},
AggregationMethods.MEAN, self.state)
self.assertEqual(len(results.scores), 2)
def test_run_with_cached_results(self):
results1 = run(self.corpus, None, {},
{ScoringMethods.TF_IDF, ScoringMethods.YAKE}, {},
AggregationMethods.MEAN, self.state)
with patch("orangecontrib.text.keywords.tfidf_keywords") as mock:
results2 = run(self.corpus, None, results1.all_keywords,
{ScoringMethods.TF_IDF, ScoringMethods.YAKE}, {},
AggregationMethods.MEAN, self.state)
mock.assert_not_called()
self.assertNanEqual(results1.scores, results2.scores)
self.assertNanEqual(results1.labels, results2.labels)
self.assertNanEqual(results1.all_keywords, results2.all_keywords)
def test_run_no_methods(self):
cached_keywords = Mock()
results = run(self.corpus, None, cached_keywords, set(), {},
AggregationMethods.MEAN, Mock())
self.assertEqual(results.scores, [])
self.assertEqual(results.labels, [])
self.assertIs(results.all_keywords, cached_keywords)
def test_run_multiple_methods(self):
results = run(self.corpus, None, {},
{ScoringMethods.TF_IDF, ScoringMethods.YAKE}, {},
AggregationMethods.MEAN, self.state)
self.assertEqual(results.scores[0][0], "system")
self.assertAlmostEqual(results.scores[0][1], 0.114, 2)
self.assertTrue(np.isnan(np.nan))
self.assertEqual(results.labels, ["TF-IDF", "YAKE!"])
def test_run_with_words(self):
words = ["human", "graph", "minors", "trees"]
results = run(self.corpus, words, {}, {ScoringMethods.TF_IDF}, {},
AggregationMethods.MEAN, self.state)
self.assertEqual(len(results.scores), 4)
words = ["foo", "bar"]
results = run(self.corpus, words, {}, {ScoringMethods.TF_IDF}, {},
AggregationMethods.MEAN, self.state)
self.assertEqual(len(results.scores), 0)
words = []
results = run(self.corpus, words, {}, {ScoringMethods.TF_IDF}, {},
AggregationMethods.MEAN, self.state)
self.assertEqual(len(results.scores), 42)
words = None
results = run(self.corpus, words, {}, {ScoringMethods.TF_IDF}, {},
AggregationMethods.MEAN, self.state)
self.assertEqual(len(results.scores), 42)
def test_run_no_data(self):
results = run(None, None, {}, {ScoringMethods.TF_IDF}, {},
AggregationMethods.MEAN, Mock())
self.assertEqual(results.scores, [])
self.assertEqual(results.labels, [])
self.assertEqual(results.all_keywords, {})
def test_run_default(self):
results = run(self.corpus, None, {}, {ScoringMethods.TF_IDF}, {},
AggregationMethods.MEAN, self.state)
self.assertEqual(results.scores[0][0], "system")
self.assertAlmostEqual(results.scores[0][1], 0.114, 2)
self.assertEqual(results.labels, ["TF-IDF"])
