def main():
plot_queue = multiprocessing.Queue()
confusion_queue = multiprocessing.Queue()
start_plot(plot_queue, confusion_queue)
first = (SingleClassifier, semeval.TrainSemEvalSelfLearning, semeval.TestSemEval)
second = (HierarchicalClassifier, semeval.TrainSemEvalSelfLearning, semeval.TestSemEval)
extractor = FeatureExtractor(tokenizer=tokenizer)
extractor.min_n, extractor.max_n = 1, 2
config = get_config()
chunk_size = config.getint("sentiment", "chunk_size")
first_chunk = config.getint("sentiment", "first_chunk")
titles = json.loads(config.get("sentiment", "titles"))
experiment = run_experiment(first, second, extractor, chunk_size, first_chunk)
try:
for data in experiment:
data[titles[0]] = parse_performance(data[titles[0]])
data[titles[1]] = parse_performance(data[titles[1]])
plot_queue.put(data)
confusion_queue.put(data)
print data[titles[0]]["count"], data[titles[0]]["SemEval"], data[titles[1]]["SemEval"], data[titles[0]][
"vocab"
], data[titles[1]]["vocab"]
except KeyboardInterrupt:
pass
finally:
plot_queue.put(None)
plot_queue.close()
confusion_queue.put(None)
confusion_queue.close()
print "Done processing."
def setup(self):
self.extractor = FeatureExtractor()
self.document = 'I am so happy about this project'
class TestFeatureExtractor(object):
"""Extract features from text for use in classification."""
def setup(self):
self.extractor = FeatureExtractor()
self.document = 'I am so happy about this project'
def test_no_features(self):
result = self.extractor.extract(self.document)
assert result == []
def test_tokenize_default(self):
result = self.extractor.tokenize(self.document)
expected = self.document.split()
assert result == expected
def test_tokenize_custom(self):
def custom(document):
return document.lower().split(' ')
self.extractor = FeatureExtractor(tokenizer=custom)
assert self.extractor.tokenize is custom
def test_ngrams(self):
test = [(1, 1, ['I', 'am', 'so', 'happy', 'about', 'this', 'project']),
(2, 2, [
'__start__ I', 'I am', 'am so', 'so happy', 'happy about',
'about this', 'this project', 'project __end__'
]),
(3, 3, [
'__start__ I am', 'I am so', 'am so happy',
'so happy about', 'happy about this', 'about this project',
'this project __end__'
])]
test.append((1, 2, test[0][2] + test[1][2]))
test.append((2, 3, test[1][2] + test[2][2]))
test.append((1, 3, test[0][2] + test[1][2] + test[2][2]))
failed = []
for min_n, max_n, expected in test:
self.extractor.min_n, self.extractor.max_n = min_n, max_n
result = sorted(self.extractor.extract(self.document))
# Convert expected to a tuple.
expected = [tuple(x.split()) for x in expected]
expected = sorted(expected)
if result != expected:
failed.append(((min_n, max_n), result, expected))
# This explicitly shows the expected tuple return type.
document = 'this is a test'
expected = [('__start__', 'this'), ('this', 'is'), ('is', 'a'),
('a', 'test'), ('test', '__end__')]
expected = sorted(expected)
self.extractor.min_n, self.extractor.max_n = 2, 2
result = sorted(self.extractor.extract(document))
if result != expected:
failed.append(((2, 2), result, expected))
assert not failed
def test_ngrams_multinomialnb(self):
# Integration test with Naive Bayes classifier.
classifier = MultinomialNB()
self.extractor.min_n, self.extractor.max_n = 1, 3
features = self.extractor.extract(self.document)
classifier.train([features, 'positive'])
def test_ngrams_non_zero(self):
bad_ranges = [(0, 1), (1, 0)]
for min_n, max_n in bad_ranges:
self.extractor.min_n, self.extractor.max_n = min_n, max_n
assert_raises(ValueError, self.extractor.extract, self.document)
def test_ngrams_non_negative(self):
bad_ranges = [(-1, 1), (1, -1), (-2, -1), (-1, 0), (0, -1)]
for min_n, max_n in bad_ranges:
self.extractor.min_n, self.extractor.max_n = min_n, max_n
assert_raises(ValueError, self.extractor.extract, self.document)
def test_ngrams_non_reversed(self):
bad_ranges = [(2, 1), (3, 1), (3, 2)]
for min_n, max_n in bad_ranges:
self.extractor.min_n, self.extractor.max_n = min_n, max_n
assert_raises(ValueError, self.extractor.extract, self.document)
def test_tokenize_custom(self):
def custom(document):
return document.lower().split(' ')
self.extractor = FeatureExtractor(tokenizer=custom)
assert self.extractor.tokenize is custom
class TestFeatureExtractor(object):
"""Extract features from text for use in classification."""
def setup(self):
self.extractor = FeatureExtractor()
self.document = "I am so happy about this project"
def test_no_features(self):
result = self.extractor.extract(self.document)
assert result == []
def test_tokenize_default(self):
result = self.extractor.tokenize(self.document)
expected = self.document.split()
assert result == expected
def test_tokenize_custom(self):
def custom(document):
return document.lower().split(" ")
self.extractor = FeatureExtractor(tokenizer=custom)
assert self.extractor.tokenize is custom
def test_ngrams(self):
test = [
(1, 1, ["I", "am", "so", "happy", "about", "this", "project"]),
(
2,
2,
[
"__start__ I",
"I am",
"am so",
"so happy",
"happy about",
"about this",
"this project",
"project __end__",
],
),
(
3,
3,
[
"__start__ I am",
"I am so",
"am so happy",
"so happy about",
"happy about this",
"about this project",
"this project __end__",
],
),
]
test.append((1, 2, test[0][2] + test[1][2]))
test.append((2, 3, test[1][2] + test[2][2]))
test.append((1, 3, test[0][2] + test[1][2] + test[2][2]))
failed = []
for min_n, max_n, expected in test:
self.extractor.min_n, self.extractor.max_n = min_n, max_n
result = sorted(self.extractor.extract(self.document))
# Convert expected to a tuple.
expected = [tuple(x.split()) for x in expected]
expected = sorted(expected)
if result != expected:
failed.append(((min_n, max_n), result, expected))
# This explicitly shows the expected tuple return type.
document = "this is a test"
expected = [("__start__", "this"), ("this", "is"), ("is", "a"), ("a", "test"), ("test", "__end__")]
expected = sorted(expected)
self.extractor.min_n, self.extractor.max_n = 2, 2
result = sorted(self.extractor.extract(document))
if result != expected:
failed.append(((2, 2), result, expected))
assert not failed
def test_ngrams_multinomialnb(self):
# Integration test with Naive Bayes classifier.
classifier = MultinomialNB()
self.extractor.min_n, self.extractor.max_n = 1, 3
features = self.extractor.extract(self.document)
classifier.train([features, "positive"])
def test_ngrams_non_zero(self):
bad_ranges = [(0, 1), (1, 0)]
for min_n, max_n in bad_ranges:
self.extractor.min_n, self.extractor.max_n = min_n, max_n
assert_raises(ValueError, self.extractor.extract, self.document)
def test_ngrams_non_negative(self):
bad_ranges = [(-1, 1), (1, -1), (-2, -1), (-1, 0), (0, -1)]
for min_n, max_n in bad_ranges:
self.extractor.min_n, self.extractor.max_n = min_n, max_n
assert_raises(ValueError, self.extractor.extract, self.document)
def test_ngrams_non_reversed(self):
bad_ranges = [(2, 1), (3, 1), (3, 2)]
for min_n, max_n in bad_ranges:
self.extractor.min_n, self.extractor.max_n = min_n, max_n
assert_raises(ValueError, self.extractor.extract, self.document)
def test_tokenize_custom(self):
def custom(document):
return document.lower().split(" ")
self.extractor = FeatureExtractor(tokenizer=custom)
assert self.extractor.tokenize is custom
def setup(self):
self.extractor = FeatureExtractor()
self.document = "I am so happy about this project"
