def test_empty_corpus(self):
"""
Test the token extractor with an empty corpus.
"""
extractor = TokenExtractor()
candidates = extractor.extract([])
self.assertFalse(len(candidates))
def test_sorting(self):
"""
Test that the resolver sorts the tokens in descending order of score.
"""
"""
Create the test data
"""
tokenizer = Tokenizer(min_length=3, stem=False, case_fold=True)
posts = [
"Manchester United falter against Tottenham Hotspur",
"Manchester United unable to avoid defeat to Tottenham",
"Tottenham lose again",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
"""
Ensure that the more common candidates are ranked towards the beginning.
"""
candidates = TokenExtractor().extract(corpus)
scores = TFScorer().score(candidates)
scores = ThresholdFilter(0).filter(scores)
self.assertTrue(scores)
resolved, unresolved = Resolver().resolve(scores)
self.assertEqual(set(scores.keys()), set(resolved))
self.assertEqual([], unresolved)
self.assertEqual('tottenham', resolved[0])
self.assertEqual(set(['manchester', 'united']), set(resolved[1:3]))
def test_sorting(self):
"""
Test that the resolver sorts the tokens in descending order of score.
"""
"""
Create the test data
"""
tokenizer = Tokenizer(min_length=3, stem=False, case_fold=True)
posts = [
"Manchester United falter against Tottenham Hotspur",
"Manchester United unable to avoid defeat to Tottenham",
"Tottenham lose again",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
candidates = TokenExtractor().extract(corpus)
scores = TFScorer().score(candidates)
scores = ThresholdFilter(0).filter(scores)
resolved, unresolved = TokenResolver(tokenizer, corpus).resolve(scores)
self.assertEqual('tottenham', resolved[0])
self.assertEqual(set(['manchester', 'united']), set(resolved[1:3]))
self.assertEqual(
set([
'falter', 'against', 'hotspur', 'unable', 'avoid', 'defeat',
'lose', 'again'
]), set(resolved[3:]))
def test_repeated_tokens(self):
"""
Test that when tokens are repeated, the frequency that is returned is the term frequency.
"""
"""
Create the test data.
"""
tokenizer = Tokenizer(stem=False)
posts = [
"After Erdogan's statement, Damascus says Erdogan 'disconnected from reality' after threats",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
extractor = TokenExtractor(tokenizer=tokenizer)
scorer = TFScorer()
candidates = extractor.extract(corpus)
scores = scorer.score(candidates, normalize_scores=False)
self.assertEqual(2, scores.get('erdogan'))
def test_score_across_multiple_documents(self):
"""
Test that the score is based on term frequency.
"""
"""
Create the test data.
"""
tokenizer = Tokenizer(stem=False)
posts = [
"Erdogan with threats to attack regime forces 'everywhere' in Syria",
"After Erdogan's statement, Damascus says Erdogan 'disconnected from reality' after threats",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
extractor = TokenExtractor(tokenizer=tokenizer)
scorer = TFScorer()
candidates = extractor.extract(corpus)
scores = scorer.score(candidates, normalize_scores=False)
self.assertEqual(3, scores.get('erdogan'))
def test_normalization(self):
"""
Test that when normalization is disabled, the returned scores are integers.
"""
"""
Create the test data.
"""
tokenizer = Tokenizer(stem=False)
posts = [
"Erdogan with threats to attack regime forces 'everywhere' in Syria",
"After Erdogan's statement, Damascus says Erdogan 'disconnected from reality' after threats",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
extractor = TokenExtractor()
scorer = TFScorer()
candidates = extractor.extract(corpus)
scores = scorer.score(candidates, normalize_scores=False)
self.assertEqual(2, scores.get('erdogan'))
def test_max_score(self):
"""
Test that the maximum score is 1 when normalization is enabled.
"""
"""
Create the test data.
"""
tokenizer = Tokenizer(stem=False)
posts = [
"Erdogan with threats to attack regime forces 'everywhere' in Syria",
"Damascus says Erdogan 'disconnected from reality' after threats",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
extractor = TokenExtractor()
scorer = TFScorer()
candidates = extractor.extract(corpus)
scores = scorer.score(candidates)
self.assertTrue(all(score <= 1 for score in scores.values()))
def test_score_of_unknown_token(self):
"""
Test that the score of an unknown token is 0.
"""
"""
Create the test data.
"""
tokenizer = Tokenizer(stem=False)
posts = [
"Erdogan with threats to attack regime forces 'everywhere' in Syria",
"Damascus says Erdogan 'disconnected from reality' after threats",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
extractor = TokenExtractor()
scorer = TFScorer()
candidates = extractor.extract(corpus)
scores = scorer.score(candidates)
self.assertFalse(scores.get('unknown'))
def test_return_length(self):
"""
Test that the token extractor returns as many token sets as the number of documents given.
"""
"""
Create the test data.
"""
tokenizer = Tokenizer(stopwords=stopwords.words("english"), stem=False)
posts = [
"Manchester United falter against Tottenham Hotspur",
"",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
extractor = TokenExtractor()
candidates = extractor.extract(corpus)
self.assertEqual(2, len(candidates))
self.assertEqual(
set(["manchester", "united", "falter", "tottenham", "hotspur"]),
set(candidates[0]))
self.assertEqual(set([]), set(candidates[1]))
def test_logarithm_base(self):
"""
Test that when a logarithmic base is provided, it is used instead of the default base.
"""
"""
Create the test data.
"""
tokenizer = Tokenizer(stem=False)
posts = [
"Erdogan with threats to attack regime forces 'everywhere' in Syria",
"After Erdogan's statement, Damascus says Erdogan 'disconnected from reality' after threats",
]
corpus = [ Document(post, tokenizer.tokenize(post)) for post in posts ]
extractor = TokenExtractor()
scorer = LogDFScorer(base=2)
candidates = extractor.extract(corpus)
scores = scorer.score(candidates, normalize_scores=False)
self.assertEqual(math.log(2 + 1, 2), scores.get('erdogan')) # apply Laplace smoothing
def test_tf_scorer(self):
"""
Test the basic functionality of the TF scorer.
"""
"""
Create the test data.
"""
tokenizer = Tokenizer(stem=False)
posts = [
"Erdogan with threats to attack regime forces 'everywhere' in Syria",
"Damascus says Erdogan 'disconnected from reality' after threats",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
extractor = TokenExtractor()
scorer = TFScorer()
candidates = extractor.extract(corpus)
scores = scorer.score(candidates)
self.assertEqual(1, scores.get('erdogan', 0))
self.assertEqual(0.5, scores.get('damascus', 0))
self.assertEqual(1, scores.get('threats', 0))
def test_token_extractor(self):
"""
Test the token extractor with normal input.
"""
"""
Create the test data.
"""
tokenizer = Tokenizer(stopwords=stopwords.words("english"), stem=False)
posts = [
"Manchester United falter against Tottenham Hotspur",
"Mourinho under pressure as Manchester United follow with a loss",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
extractor = TokenExtractor()
candidates = extractor.extract(corpus)
self.assertEqual(
set(["manchester", "united", "falter", "tottenham", "hotspur"]),
set(candidates[0]))
self.assertEqual(
set([
"mourinho", "pressure", "manchester", "united", "follow",
"loss"
]), set(candidates[1]))
def test_empty_corpus(self):
"""
Test that when an empty corpus is given, all candidates are unresolved.
"""
"""
Create the test data
"""
tokenizer = Tokenizer(min_length=1, stem=False)
posts = [
"Manchester United falter against Tottenham Hotspur",
"Manchester United unable to avoid defeat to Tottenham",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
candidates = TokenExtractor().extract(corpus)
scores = TFScorer().score(candidates)
scores = ThresholdFilter(0).filter(scores)
resolved, unresolved = TokenResolver(tokenizer, []).resolve(scores)
self.assertEqual(len(scores), len(unresolved))
def test_unknown_token(self):
"""
Test that when an unknown candidate is given, it is unresolved.
"""
"""
Create the test data
"""
tokenizer = Tokenizer(min_length=1, stem=False)
posts = [
"Manchester United falter against Tottenham Hotspur",
"Manchester United unable to avoid defeat to Tottenham",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
candidates = TokenExtractor().extract(corpus)
scores = TFScorer().score(candidates)
scores = ThresholdFilter(0).filter(scores)
resolved, unresolved = TokenResolver(tokenizer,
corpus).resolve({'unknown': 1})
self.assertTrue('unknown' in unresolved)
def test_token_resolver(self):
"""
Test the token resolver.
"""
"""
Create the test data
"""
tokenizer = Tokenizer(min_length=1, stem=False)
posts = [
"Manchester United falter against Tottenham Hotspur",
"Manchester United unable to avoid defeat to Tottenham",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
candidates = TokenExtractor().extract(corpus)
scores = TFScorer().score(candidates)
scores = ThresholdFilter(0).filter(scores)
resolved, unresolved = TokenResolver(tokenizer, corpus).resolve(scores)
self.assertTrue('manchester' in resolved)
self.assertTrue('united' in resolved)
self.assertTrue('tottenham' in resolved)
self.assertTrue('hotspur' in resolved)
def test_different_tokenizer(self):
"""
Test that when a different tokenizer is used than the one used in extraction, it is used.
"""
"""
Create the test data
"""
tokenizer = Tokenizer(min_length=1, stem=False)
posts = [
"Manchester United falter against Tottenham Hotspur",
"Manchester United unable to avoid defeat to Tottenham",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
candidates = TokenExtractor().extract(corpus)
scores = TFScorer().score(candidates)
scores = ThresholdFilter(0).filter(scores)
resolved, unresolved = TokenResolver(tokenizer, corpus).resolve(scores)
self.assertTrue('to' in resolved)
resolved, unresolved = TokenResolver(
Tokenizer(min_length=3, stem=False), corpus).resolve(scores)
self.assertTrue('to' in unresolved)
def test_resolve_all(self):
"""
Test that when resolving candidates, all of them are returned.
"""
"""
Create the test data
"""
tokenizer = Tokenizer(min_length=3, stem=False, case_fold=True)
posts = [
"Manchester United falter against Tottenham Hotspur",
"Manchester United unable to avoid defeat to Tottenham",
"Tottenham lose again",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
"""
Ensure that all candidates are resolved.
"""
candidates = TokenExtractor().extract(corpus)
scores = TFScorer().score(candidates)
scores = ThresholdFilter(0).filter(scores)
self.assertTrue(scores)
resolved, unresolved = Resolver().resolve(scores)
self.assertEqual(set(scores.keys()), set(resolved))
self.assertEqual([], unresolved)
def test_case_folding(self):
"""
Test that when case-folding is set, the case does not matter.
In this test, the stem 'report' can be formed by:
#. Reporters - appears twice
#. reporters - appears twice
#. reports - appears three times
Without case-folding, 'reports' would be chosen to represent the token 'report'.
'reports' appears three times, and 'Reporters' and 'reporters' appear twice.
With case-folding, 'reports' still appears three times, but 'reporters' appears four times.
"""
"""
Create the test data
"""
tokenizer = Tokenizer(min_length=1, stem=True)
posts = [
"Reporters Without Borders issue statement after reporters are harrassed",
"Reporters left waiting all night long: reports",
"Two reporters injured before gala: reports",
"Queen reacts: reports of her falling ill exaggerated"
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
candidates = TokenExtractor().extract(corpus)
scores = TFScorer().score(candidates)
scores = ThresholdFilter(0).filter(scores)
resolved, unresolved = TokenResolver(tokenizer,
corpus,
case_fold=False).resolve(scores)
self.assertTrue('reports' in resolved)
resolved, unresolved = TokenResolver(tokenizer, corpus,
case_fold=True).resolve(scores)
self.assertTrue('reporters' in resolved)
def test_repeated_tokens_with_custom_tokenizer(self):
"""
Test that when a custom tokenizer is given, repeated tokenizers appear multiple times.
"""
"""
Create the test data.
"""
tokenizer = Tokenizer(stopwords=stopwords.words("english"), stem=False)
posts = [
"Manchester United back to winning ways after defeating Manchester City.",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
extractor = TokenExtractor()
candidates = extractor.extract(corpus)
self.assertEqual(1, candidates[0].count('manchester'))
extractor = TokenExtractor(tokenizer=tokenizer)
candidates = extractor.extract(corpus)
self.assertEqual(2, candidates[0].count('manchester'))
def test_extract_with_custom_tokenizer(self):
"""
Test that when a custom tokenizer is given, it is used instead of the dimensions.
"""
"""
Create the test data, which uses stemming.
"""
tokenizer = Tokenizer(stopwords=stopwords.words("english"), stem=True)
posts = [
"Manchester United back to winning ways",
]
corpus = [Document(post, tokenizer.tokenize(post)) for post in posts]
extractor = TokenExtractor()
candidates = extractor.extract(corpus)
self.assertEqual(set(["manchest", "unit", "back", "win", "way"]),
set(candidates[0]))
extractor = TokenExtractor(tokenizer=Tokenizer(
stopwords=stopwords.words('english'), stem=False))
candidates = extractor.extract(corpus)
self.assertEqual(
set(["manchester", "united", "back", "winning", "ways"]),
set(candidates[0]))
