def test_iter_topic(self, _s3_mock):
weights = classifier.SimpleWeights.load(classifier.s3_key_xreadlines())
self.assertItemsEqual(
weights.iter_topics("About 75% of New York City School students qualify "
"for free or reduced-price lunch.", 'Healthcare'),
[('Healthcare', 0)]
)
def test_classify(self, _s3_mock):
weights = classifier.SimpleWeights.load(classifier.s3_key_xreadlines())
self.assertEqual(
weights.classify("About 75% of New York City School students qualify "
"for free or reduced-price lunch."),
{'Healthcare': 0,
'Education': atan_norm(0.6 + 0.9)} # students, school
)
def test_iter_topic_phrase_linking(self, _s3_mock):
weights = classifier.SimpleWeights.load(classifier.s3_key_xreadlines())
self.assertItemsEqual(
weights.iter_topics(
"Home-schooling parents and teachers can include our fun and free "
"preschool activities and worksheets in their lesson plans",
'Education'
),
[('Education', 0.9 + 0.9 + 0.9 + 0.9)] # home schooling, teachers, pre school, lesson plans
)
def test_load(self, _s3_mock):
weights = classifier.SimpleWeights.load(classifier.s3_key_xreadlines())
self.assertEqual(len(weights), 2)
topic_data = [line.split(',') for line in DATA.splitlines()]
for (topic, info) in weights.iteritems():
topic_lines = [
(phrase, float(weight), bool(int(skip)))
for (topic1, phrase, weight, skip) in topic_data
if topic1 == topic
]
topic_info = [topic_info[:3] for topic_info in info]
self.assertEqual(topic_info, topic_lines)
def test_chunked_content_no_trailer(self):
chunks = CHUNKED_DATA[:-1]
stripped = CHUNKED_DATA[-1].strip()
with s3_data_patch(chunks + [stripped]):
self.assertEqual(''.join(classifier.s3_key_xreadlines()), DATA.strip())
def test_chunked_content(self, _s3_mock):
self.assertEqual(list(classifier.s3_key_xreadlines()), StringIO(DATA).readlines())
def test_short_content(self, _s3_mock):
self.assertEqual(list(classifier.s3_key_xreadlines()), StringIO(SHORT_DATA).readlines())
def test_no_creds(self, _s3_mock):
with self.assertRaises(StopIteration):
next(classifier.s3_key_xreadlines())