def test_hash_murmur3():
assert khmer.hash_murmur3('AAAA') == 526240128537019279
assert khmer.hash_murmur3('TTTT') == 526240128537019279
assert khmer.hash_murmur3('CCCC') == 14391997331386449225
assert khmer.hash_murmur3('GGGG') == 14391997331386449225
assert khmer.hash_murmur3('TATATATATATATATATATA') != 0
assert khmer.hash_murmur3('TTTTGCAAAA') != 0
assert khmer.hash_murmur3('GAAAATTTTC') != 0
def test_hash_murmur3():
assert khmer.hash_murmur3('AAAA') == 526240128537019279
assert khmer.hash_murmur3('TTTT') == 526240128537019279
assert khmer.hash_murmur3('CCCC') == 14391997331386449225
assert khmer.hash_murmur3('GGGG') == 14391997331386449225
assert khmer.hash_murmur3('TATATATATATATATATATA') != 0
assert khmer.hash_murmur3('TTTTGCAAAA') != 0
assert khmer.hash_murmur3('GAAAATTTTC') != 0
def add(self, kmer, rev_comp=False):
"""
Add kmer into sketch, keeping sketch sorted, update counts accordingly
"""
_mins = self._mins
_counts = self._counts
_kmers = self._kmers
if rev_comp:
h1 = khmer.hash_murmur3(kmer)
h2 = khmer.hash_murmur3(khmer.reverse_complement(kmer))
#h1 = hash(kmer)
#h2 = hash(khmer.reverse_complement(kmer))
h = min(h1, h2)
if h == h2:
kmer = khmer.reverse_complement(kmer)
else:
h = khmer.hash_murmur3(kmer)
#h = hash(kmer)
h = h % self.p
if self.hash_list: # If I only want to include hashes that occur in hash_list
if h not in self.hash_list: # If the kmer isn't in the hash_list, then break
return
if h >= _mins[-1]:
return
i = bisect.bisect_left(_mins, h) # find index to insert h
if _mins[i] == h: # if h in mins, increment counts
_counts[i] += 1
return
else: # otherwise insert h, initialize counts to 1, and insert kmer if necessary
_mins.insert(i, h)
_mins.pop()
_counts.insert(i, 1)
_counts.pop()
if _kmers:
_kmers.insert(i, np.string_(kmer))
_kmers.pop()
return
assert 0, "should never reach this"
def add(self, kmer, rev_comp=False):
"""
Add kmer into sketch, keeping sketch sorted, update counts accordingly
"""
_mins = self._mins
_counts = self._counts
_kmers = self._kmers
if rev_comp:
h1 = khmer.hash_murmur3(kmer)
h2 = khmer.hash_murmur3(khmer.reverse_complement(kmer))
#h1 = hash(kmer)
#h2 = hash(khmer.reverse_complement(kmer))
h = min(h1, h2)
if h == h2:
kmer = khmer.reverse_complement(kmer)
else:
h = khmer.hash_murmur3(kmer)
#h = hash(kmer)
h = h % self.p
if self.hash_list: # If I only want to include hashes that occur in hash_list
if h not in self.hash_list: # If the kmer isn't in the hash_list, then break
return
if h >= _mins[-1]:
return
i = bisect.bisect_left(_mins, h) # find index to insert h
if _mins[i] == h: # if h in mins, increment counts
_counts[i] += 1
return
else: # otherwise insert h, initialize counts to 1, and insert kmer if necessary
_mins.insert(i, h)
_mins.pop()
_counts.insert(i, 1)
_counts.pop()
if _kmers:
_kmers.insert(i, np.string_(kmer))
_kmers.pop()
return
assert 0, "should never reach this"
def add(self, kmer):
idx = khmer.forward_hash(kmer, self.prefixsize)
E = self.sketches[idx]
hash = khmer.hash_murmur3(kmer)
E.add(hash)
def add(self, kmer):
idx = khmer.forward_hash(kmer, self.prefixsize)
E = self.sketches[idx]
hash = khmer.hash_murmur3(kmer)
E.add(hash)
def test_hash_murmur3():
assert khmer.hash_murmur3("AAAA") == 526240128537019279
assert khmer.hash_murmur3("TTTT") == 526240128537019279
assert khmer.hash_murmur3("CCCC") == 14391997331386449225
assert khmer.hash_murmur3("GGGG") == 14391997331386449225