def test_contains_id(self):
dim = 100
act = 10
gen = Generator(dim, act)
sign_index = SignIndex(gen)
id = 0
self.assertFalse(sign_index.contains_id(id))
def test_get(self):
dim = 100
act = 10
gen = Generator(dim, act)
sign_index = SignIndex(gen)
sign_index.add("0")
ri0 = sign_index.get_ri("0")
self.assertIsInstance(ri0, RandomIndex)
self.assertEqual(ri0.dim, dim)
def test_contains(self):
dim = 100
act = 10
gen = Generator(dim, act)
sign_index = SignIndex(generator=gen)
sign_index.add("0")
self.assertTrue(sign_index.contains("0"))
self.assertFalse(sign_index.contains("1"))
sign_index.remove("0")
self.assertFalse(sign_index.contains("0"))
def test_size(self):
gen = Generator(100, 10)
sign_index = SignIndex(generator=gen)
# adding elements should increase size
self.assertEqual(len(sign_index), 0)
sign_index.add("0")
self.assertEqual(len(sign_index), 1)
self.assertEqual(sign_index.nextID, sign_index.get_id("0") + 1)
# duplicated elements are not added
sign_index.add("0")
self.assertEqual(len(sign_index), 1)
sign_index.add("1")
self.assertEqual(len(sign_index), 2)
# removing elements should reduce size
size_before = len(sign_index)
sign_index.remove("0")
size_after = len(sign_index)
self.assertEqual(size_after, size_before - 1)
def setUp(self):
dim = 10
act = 4
self.generator = Generator(dim=dim, num_active=act)
self.sign_index = SignIndex(self.generator)
def setUp(self):
dim = 10
act = 2
self.generator = Generator(dim=dim, num_active=act)
self.sign_index = SignIndex(self.generator)
self.perm_generator = PermutationGenerator(dim=dim)
result_path = home + "/data/results/"
corpus_file = home + corpus_file
print("Reading hdf5 dataset from: ", corpus_file)
dataset_name = "sentences_lemmatised"
# open hdf5 file and get the dataset
h5f = h5py.File(corpus_file, 'r')
dataset = h5f[dataset_name]
return dataset
# do something with the dataset
# Create Sign RI Index
ri_gen = Generator(dim=ri_dim, num_active=ri_num_active)
sign_index = SignIndex(ri_gen)
max_sentences = 200000
def load_spacy():
t0 = time.time()
# load tokenizer only
nlp = English(entity=False, load_vectors=False, parser=True, tagger=True)
t1 = time.time()
print("Done: {0:.2f} secs ".format(t1 - t0))
return nlp
nlp = load_spacy()