def test_pickle(self):
forest = MinHashLSHForest()
m1 = MinHash()
m1.update("a".encode("utf8"))
m2 = MinHash()
m2.update("b".encode("utf8"))
forest.add("a", m1)
forest.add("b", m2)
forest.index()
forest2 = pickle.loads(pickle.dumps(forest))
result = forest.query(m1, 1)
self.assertTrue("a" in result)
result = forest.query(m2, 1)
self.assertTrue("b" in result)
def test_query(self):
forest = MinHashLSHForest()
mg = WeightedMinHashGenerator(10)
m1 = mg.minhash(np.random.uniform(1, 10, 10))
m2 = mg.minhash(np.random.uniform(1, 10, 10))
forest.add("a", m1)
forest.add("b", m2)
forest.index()
result = forest.query(m1, 2)
self.assertTrue("a" in result)
self.assertTrue("b" in result)
mg = WeightedMinHashGenerator(10, 5)
m3 = mg.minhash(np.random.uniform(1, 10, 10))
self.assertRaises(ValueError, forest.query, m3, 1)