Exemple #1
0
 def test_jarcard_index(self):
     r1 = range(10000)
     m1 = MaxHash(8192)
     r2 = range(2000, 10000)
     m2 = MaxHash(8192)
     for i in r1:
         m1.add(str(i))
     for i in r2:
         m2.add(str(i))
     ix = MaxHash.get_jaccard_index([m1, m2])
     self.assertAlmostEqual(ix, 0.80, 2)
Exemple #2
0
 def test_add(self):
     m = MaxHash(8192)
     m.add(str(1))
     m.add(str(2))
     m.add(str(3))
     m.add(str(4))
     self.assertEqual(len(m.uniq()), 4)
Exemple #3
0
 def _inner_hll_accumulate(a, v):
     from maxhash import MaxHash
     a.merge(MaxHash.loads(v))
     return a
Exemple #4
0
 def test_union(self):
     r1 = range(10000)
     m1 = MaxHash(8192)
     r2 = range(2000, 12000)
     m2 = MaxHash(8192)
     r3 = range(15000)
     m3 = MaxHash(8192)
     for i in r1:
         m1.add(str(i))
     for i in r2:
         m2.add(str(i))
     for i in r3:
         m3.add(str(i))
     m4 = m1.union(m2)
     ix = MaxHash.get_jaccard_index([m3, m4])
     self.assertAlmostEqual(ix, 0.80, 2)
Exemple #5
0
 def test_merge(self):
     r1 = range(10000)
     m1 = MaxHash(8192)
     r2 = range(2000, 12000)
     m2 = MaxHash(8192)
     r3 = range(15000)
     m3 = MaxHash(8192)
     for i in r1:
         m1.add(str(i))
     for i in r2:
         m2.add(str(i))
     for i in r3:
         m3.add(str(i))
     m2.merge(m1)
     ix = MaxHash.get_jaccard_index([m2, m3])
     self.assertAlmostEqual(ix, 0.80, 2)
Exemple #6
0
 def _inner_hll_accumulate(a, v):
     from maxhash import MaxHash
     a.merge(MaxHash.loads(v))
     return a
Exemple #7
0
 def _inner_deault():
     from maxhash import MaxHash
     return MaxHash()