def test_added_text(self):
a = self.compute(self.jabberwocky)
b = self.compute(self.jabberwocky +
' - Lewis Carroll (Alice in Wonderland)')
self.assertLessEqual(simhash.num_differing_bits(a, b),
self.MATCH_THRESHOLD)
def test_added_text(self):
a = self.compute(self.jabberwocky)
b = self.compute(
self.jabberwocky + ' - Lewis Carroll (Alice in Wonderland)')
self.assertLessEqual(
simhash.num_differing_bits(a, b),
self.MATCH_THRESHOLD)
def test_simhash():
try:
from simhash import num_differing_bits
except ImportError:
raise SkipTest
from sklearn.feature_extraction.text import HashingVectorizer
from freediscovery.dupdet import SimhashDuplicates
DISTANCE = 4
fe = HashingVectorizer(ngram_range=(4, 4), analyzer='word')
X = fe.fit_transform([
jabberwocky, jabberwocky + jabberwocky_author, jabberwocky_author,
jabberwocky
])
sh = SimhashDuplicates()
sh.fit(X)
# make sure small changes in the text results in a small number of different bytes
assert num_differing_bits(*sh._fit_shash[:2]) <= 3
# different text produces a large number of different bytes
assert num_differing_bits(*sh._fit_shash[1:3]) >= 20
# same text produces a zero bit difference
assert num_differing_bits(*sh._fit_shash[[0, -1]]) == 0
simhash, cluster_id, dup_pairs = sh.query(distance=DISTANCE, blocks=42)
assert str(dup_pairs.dtype) == 'uint64'
assert str(cluster_id.dtype) == 'int64'
assert str(dup_pairs.dtype) == 'uint64'
assert simhash[0] == simhash[
-1] # duplicate documents have the same simhash
assert cluster_id[0] == cluster_id[-1] # and belong to the same cluster
for idx, shash in enumerate(simhash):
if (shash == simhash).sum() == 1: # ignore duplicates
assert sh.get_index_by_hash(shash) == idx
for pairs in dup_pairs:
assert num_differing_bits(*pairs) <= DISTANCE
def hammingCompare(outtweets, innerTwitter):
client = retinasdk.FullClient(apiKey.retina_token,
apiServer="http://api.cortical.io/rest",
retinaName="en_associative")
liteClient = retinasdk.LiteClient(apiKey.retina_token)
res = []
for index, outtweet in enumerate(outtweets):
result = {}
# get simHash
simhash_pair = getSimHash(outtweet[2], innerTwitter, client)
if len(simhash_pair) > 1:
diff_bits = simhash.num_differing_bits(simhash_pair['out_hash'],
simhash_pair['in_hash'])
hashes = [simhash_pair['out_hash'], simhash_pair['in_hash']]
blocks = 4 # Number of blocks to use
distance = 3 # Number of bits that may differ in matching pairs
matches = simhash.find_all(hashes, blocks, distance)
res.append([index, outtweet[2], matches])
return res
def test_inverse(self):
hashes = [0xDEADBEEFDEADBEEF, 0x2152411021524110]
self.assertEqual(64, simhash.num_differing_bits(*hashes))
self.assertEqual(0, simhash.compute(hashes))
def test_different(self):
a = self.compute(self.jabberwocky)
b = self.compute(self.pope)
self.assertGreater(
simhash.num_differing_bits(a, b),
self.MATCH_THRESHOLD)
def test_identical_text(self):
a = self.compute(self.jabberwocky)
b = self.compute(self.jabberwocky)
self.assertEqual(0, simhash.num_differing_bits(a, b))
def test_basic(self):
a = 0xDEADBEEF
b = 0xDEADBEAD
self.assertEqual(2, simhash.num_differing_bits(a, b))
def distance(self, hash):
return num_differing_bits(self.value, hash.value)
def test_basic(self):
a = 0xDEADBEEF
b = 0xDEADBEAD
self.assertEqual(2, simhash.num_differing_bits(a, b))
print(pope)
def test_inverse(self):
hashes = [0xDEADBEEFDEADBEEF, 0x2152411021524110]
self.assertEqual(64, simhash.num_differing_bits(*hashes))
self.assertEqual(0, simhash.compute(hashes))
def test_different(self):
a = self.compute(self.jabberwocky)
b = self.compute(self.pope)
self.assertGreater(simhash.num_differing_bits(a, b),
self.MATCH_THRESHOLD)
def test_identical_text(self):
a = self.compute(self.jabberwocky)
b = self.compute(self.jabberwocky)
self.assertEqual(0, simhash.num_differing_bits(a, b))
def calculate_fingerprint_diff(row):
return simhash.num_differing_bits(row['fingerprint_old'],
row['fingerprint_new'])
