def test_chunk_sizes(self):
text = "AAACCCAAA"
chunk_size = 'm'
pattern = "CC"
self.assertTrue((
fftmatch.fft_match_index_n_log_m(text, pattern, chunk_size) == \
np.array(boyermoore.boyer_moore_match_index(text,pattern))).all())
def test_chunk_sizes(self):
text = "AAACCCAAA"
chunk_size = 'm'
pattern = "CC"
self.assertTrue((
fftmatch.fft_match_index_n_log_m(text, pattern, chunk_size) == \
np.array(boyermoore.boyer_moore_match_index(text,pattern))).all())
def test_long_stream(self, func):
np.random.seed(67+2)
text = ''.join(np.random.choice(list('AGCT'), size=100000))
pattern = ''.join(np.random.choice(list('AGTC'), size=3))
self.assertTrue((func(text=text, pattern=pattern) == \
np.array(boyermoore.boyer_moore_match_index(text=text, \
pattern=pattern))).all(),
msg=format_error_message(func))
def test_long_stream(self, func):
np.random.seed(67 + 2)
text = ''.join(np.random.choice(list('AGCT'), size=100000))
pattern = ''.join(np.random.choice(list('AGTC'), size=3))
self.assertTrue((func(text=text, pattern=pattern) == \
np.array(boyermoore.boyer_moore_match_index(text=text, \
pattern=pattern))).all(),
msg=format_error_message(func))
def test_long_stream(self, func):
#if func == fftmatch.fft_match_index_n_sq_log_n_naive:
# return #You shall not pass
np.random.seed(67+2)
texts = np.random.choice(list('AGCT'), size=(10000,31)).tolist()
texts = [''.join(_list) for _list in texts]
pattern = ''.join(np.random.choice(list('AGTC'), size=3))
expected_output = [boyermoore.boyer_moore_match_index(text=text,\
pattern=pattern) for text in texts]
expected_output = np.array(expected_output)
out = func(texts=texts, pattern=pattern)
self.assertTrue(ndarrays_equal(out, expected_output),
msg=format_error_message(func))
def test_long_stream(self, func):
#if func == fftmatch.fft_match_index_n_sq_log_n_naive:
# return #You shall not pass
np.random.seed(67 + 2)
texts = np.random.choice(list('AGCT'), size=(10000, 31)).tolist()
texts = [''.join(_list) for _list in texts]
pattern = ''.join(np.random.choice(list('AGTC'), size=3))
expected_output = [boyermoore.boyer_moore_match_index(text=text,\
pattern=pattern) for text in texts]
expected_output = np.array(expected_output)
out = func(texts=texts, pattern=pattern)
self.assertTrue(ndarrays_equal(out, expected_output),
msg=format_error_message(func))
title = title + str(count[title])
genomes[title] = genome
sorted_genomes = collections.OrderedDict(sorted(genomes.items(),
key=lambda t: t[0]))
genome_strings = sorted_genomes.values()
genome_titles = sorted_genomes.keys()
# Parse args
if args.algorithm == 'nlogn':
for gn in genomes:
matches = fft.fft_match_index_n_log_n(genomes[gn], args.pattern)
print gn, ': Found matches at indices', matches.tolist()
elif args.algorithm == 'nlogm':
if len(genomes) > 1:
matches = fft.fft_match_index_n_sq_log_m(genomes.values(),\
args.pattern[0], args.b)
print 'found matches at', matches.tolist()
else:
for gn in genomes:
matches = fft.fft_match_index_n_log_m(genomes[gn], args.pattern[0],args.b)
print gn, ': Found matches at indices', matches.tolist()
elif args.algorithm == 'boyermoore':
for gn in genomes:
matches = bm.boyer_moore_match_index(genomes[gn], args.pattern)
print gn, ': Found matches at indices', matches.tolist()
elif args.algorithm == 'opencv':
matches = cvmatch.cv_match_index_chunk(genomes.values(), args.pattern[0], args.b)
print genomes[genomes.keys()[0]]
print genomes.keys(), ': Found matches at indices', matches.tolist()
sorted_genomes = collections.OrderedDict(
sorted(genomes.items(), key=lambda t: t[0]))
genome_strings = sorted_genomes.values()
genome_titles = sorted_genomes.keys()
# Parse args
if args.algorithm == 'nlogn':
for gn in genomes:
matches = fft.fft_match_index_n_log_n(genomes[gn], args.pattern)
print gn, ': Found matches at indices', matches.tolist()
elif args.algorithm == 'nlogm':
if len(genomes) > 1:
matches = fft.fft_match_index_n_sq_log_m(genomes.values(),\
args.pattern[0], args.b)
print 'found matches at', matches.tolist()
else:
for gn in genomes:
matches = fft.fft_match_index_n_log_m(genomes[gn], args.pattern[0],
args.b)
print gn, ': Found matches at indices', matches.tolist()
elif args.algorithm == 'boyermoore':
for gn in genomes:
matches = bm.boyer_moore_match_index(genomes[gn], args.pattern)
print gn, ': Found matches at indices', matches.tolist()
elif args.algorithm == 'opencv':
matches = cvmatch.cv_match_index_chunk(genomes.values(), args.pattern[0],
args.b)
print genomes[genomes.keys()[0]]
print genomes.keys(), ': Found matches at indices', matches.tolist()
