def setup(source, pdf_path):
ngrams = NGramSpace(4)
print "parsing documents at %s..." % source
docs = [
extract_row(row, pdf_path, ngrams)
for row in csv.DictReader(open(source, 'r'))
]
print "clustering %d documents..." % len(docs)
clustering = Clustering([doc.parsed for doc in docs])
return (clustering, docs)
def test_pairs(self):
ngrams = NGramSpace(1)
docs = [ngrams.parse(raw) for raw in test_docs]
c = Clustering(docs)
self.assertEqual((1, 0), c.closest_pair([0, 1, 2]))
self.assertEqual((5, 3), c.closest_pair([3, 4, 5]))
self.assertEqual((7, 6), c.closest_pair([6, 7]))
self.assertEqual((2, 0), c.farthest_pair([0, 1, 2]))
self.assertEqual((5, 4), c.farthest_pair([3, 4, 5]))
self.assertEqual((7, 6), c.farthest_pair([6, 7]))
def test_nonseeded_clustering(self):
ngrams = NGramSpace(1)
docs = [ngrams.parse(raw) for raw in test_docs]
c = Clustering(docs)
self.assertEqual((1, 0), c.min_link())
c.merge(1, 0)
self.assertEqual((2, 1), c.min_link())
c.merge(2, 1)
self.assertTrue(c.min_link() in [(4, 3), (5, 3)])
c.merge(3, 4)
c.merge(3, 5)
self.assertEqual((7, 6), c.min_link())
def test_distance(self):
raw_docs = ['a b c', 'b c d', 'd e f']
ngrams = NGramSpace(1)
docs = [ngrams.parse(raw) for raw in raw_docs]
c = Clustering(docs)
self.assertEqual(0, c.distance[0, 0])
self.assertEqual(0.5, c.distance[1, 0])
self.assertEqual(0, c.distance[1, 1])
self.assertEqual(1.0, c.distance[2, 0])
self.assertEqual(0.8, c.distance[2, 1])
self.assertEqual(0, c.distance[2, 2])
def test_nearest_neighbors(self):
ngrams = NGramSpace(1)
docs = [ngrams.parse(raw) for raw in test_docs]
c = Clustering(docs)
c.pp_distance(range(0, len(test_docs)))
self.assertEqual([1], c.closest_neighbors([0], 1))
self.assertEqual([1, 2], c.closest_neighbors([0], 2))
self.assertEqual([1, 2, 3], c.closest_neighbors([0], 3))
self.assertEqual([1, 2, 3, 5], c.closest_neighbors([0], 4))
self.assertEqual([5], c.closest_neighbors([3, 4], 1))
self.assertEqual([5, 1], c.closest_neighbors([3, 4], 2))
def test_trigram(self):
unigrams = NGramSpace(3)
x = unigrams.parse('This is a sentence')
y = unigrams.parse('This is another sentence')
self.assertEqual([1, 2], x)
self.assertEqual([3, 4], y)
self.assertEqual(0, overlap(x, y))
self.assertEqual(0, overlap(y, x))
self.assertEqual(0, jaccard(x, y))
self.assertEqual(0, jaccard(y, x))
def test_bigram(self):
unigrams = NGramSpace(2)
x = unigrams.parse('This is a sentence')
y = unigrams.parse('This is another sentence')
self.assertEqual([1, 2, 3], x)
self.assertEqual([1, 4, 5], y)
self.assertEqual(1, overlap(x, y))
self.assertEqual(1, overlap(y, x))
self.assertEqual(1.0 / 5.0, jaccard(x, y))
self.assertEqual(1.0 / 5.0, jaccard(y, x))
def test_clustering(self):
raw_docs = ['a b c', 'b c d', 'd e f']
ngrams = NGramSpace(1)
docs = [ngrams.parse(raw) for raw in raw_docs]
c = Clustering(docs)
self.assertEqual((1, 0), c.min_link())
c.merge(1, 0)
self.assertEqual([1, 1, 2], c.assignments)
self.assertEqual((2, 1), c.min_link())
c.merge(2, 0)
self.assertEqual([2, 2, 2], c.assignments)
