def test_equal_independent(self):
for seed in range(TEST_CASES):
generator = IndependentGenerator(alphabet_size=4, seed=seed)
random.seed(seed)
sequence1 = generator.generate(length=random.randint(10, 100))
distance1 = dp_edit_distance(sequence1, sequence1)
string1 = "".join(chr(s + 97) for s in sequence1)
distance2 = Levenshtein.distance(string1, string1)
assert distance1 == 0, 'dp_edit_distance on equal sequences different from 0'
assert distance2 == 0, 'Levenshtein.distance on equal sequences different from 0'
def test_100_independent(self):
for seed in range(TEST_CASES):
generator = IndependentGenerator(alphabet_size=4, seed=seed)
sequence1 = generator.generate(length=100)
sequence2 = generator.generate(length=100)
distance1 = dp_edit_distance(sequence1, sequence2)
string1 = "".join(chr(s + 97) for s in sequence1)
string2 = "".join(chr(s + 97) for s in sequence2)
distance2 = Levenshtein.distance(string1, string2)
assert distance1 == distance2, \
'Mismatch between dp_edit_distance and Levenshtein.distance'
def test_100independent_5independent(self):
for seed in range(TEST_CASES):
generator = IndependentGenerator(alphabet_size=4, seed=seed)
sequence = generator.generate(length=100)
pattern = generator.generate(length=5)
random.seed(seed)
matches = {}
for algorithm in EXACT_MATCHING_ALGORITHMS.keys():
matches[algorithm] = sorted(
EXACT_MATCHING_ALGORITHMS[algorithm](pattern, sequence))
for algorithm in EXACT_MATCHING_ALGORITHMS.keys():
if algorithm != 'brute_force':
assert matches[algorithm] == matches['brute_force'], \
'Mismatch between brute force and ' + algorithm + ": " + str(matches)
def __init__(self, methodName):
super().__init__(methodName)
self.generator = IndependentGenerator(alphabet_size=ALPHABET_SIZE,
seed=0)
self.dataset = EditDistanceDatasetGenerator(
N_batches={
"train": 4,
"val": 2,
"test": 3
},
batch_size={
"train": 5,
"val": 3,
"test": 4
},
len_sequence={
"train": 10,
"val": 10,
"test": 10
},
max_changes={
"train": 4,
"val": 4,
"test": 4
},
string_generator=self.generator,
seed=0)
def __init__(self, methodName):
super().__init__(methodName)
self.generator = IndependentGenerator(alphabet_size=ALPHABET_SIZE,
seed=0)
self.dataset = ClosestStringDatasetGenerator(
N_reference=10,
N_query=15,
len_sequence=20,
min_changes=3,
max_changes=10,
initials=3,
string_generator=self.generator,
seed=0)
def generate_dataset_and_parser():
folder_name = ''.join(random.choice(string.ascii_lowercase) for _ in range(10))
generator = IndependentGenerator(alphabet_size=ALPHABET_SIZE, seed=0)
edit_dataset_name = folder_name + '/test_ed.pkl'
strings = [generate_random_dna(50)] + [generate_random_dna(random.randint(10, 50)) for _ in range(19)]
strings_dict = {'train': strings[:10], 'val': strings[10:15], 'test': strings[15:]}
edit_dataset = EditDistanceGenomicDatasetGenerator(strings=strings_dict)
edit_dataset.save_as_pickle(edit_dataset_name)
parser = general_arg_parser()
args = parser.parse_args()
args.data = edit_dataset_name
args.epochs = 2
args.print_every = 1
args.construct_msa_tree = 'True'
return folder_name, edit_dataset_name, args
def generate_dataset_and_parser():
folder_name = ''.join(
random.choice(string.ascii_lowercase) for _ in range(10))
generator = IndependentGenerator(alphabet_size=ALPHABET_SIZE, seed=0)
edit_dataset_name = folder_name + '/test_ed.pkl'
edit_dataset = EditDistanceDatasetGenerator(N_batches={
"train": 2,
"val": 2,
"test": 2
},
batch_size={
"train": 5,
"val": 3,
"test": 3
},
len_sequence={
"train": 10,
"val": 10,
"test": 10
},
max_changes={
"train": 2,
"val": 2,
"test": 2
},
string_generator=generator,
seed=0)
edit_dataset.save_as_pickle(edit_dataset_name)
hc_dataset_name = folder_name + '/test_hc.pkl'
hc_dataset = HierarchicalClusteringDatasetGenerator(
N_reference=3,
N_leaves=4,
len_sequence=10,
min_changes=2,
max_changes=4,
string_generator=generator,
seed=0)
hc_dataset.save_as_pickle(hc_dataset_name)
parser = general_arg_parser()
args = parser.parse_args()
args.data = edit_dataset_name
args.epochs = 2
args.print_every = 1
args.hierarchical_data_path = hc_dataset_name
return folder_name, edit_dataset_name, hc_dataset_name, args
def generate_dataset_and_parser():
folder_name = ''.join(random.choice(string.ascii_lowercase) for _ in range(10))
generator = IndependentGenerator(alphabet_size=ALPHABET_SIZE, seed=0)
dataset_name = folder_name + '/test_ed_model.pkl'
dataset = EditDistanceDatasetGenerator(
N_batches={"train": 2, "val": 2, "test": 2},
batch_size={"train": 5, "val": 3, "test": 3},
len_sequence={"train": 10, "val": 10, "test": 10},
max_changes={"train": 2, "val": 2, "test": 2},
string_generator=generator, seed=0)
dataset.save_as_pickle(dataset_name)
parser = general_arg_parser()
args = parser.parse_args()
args.data = dataset_name
args.epochs = 2
args.print_every = 1
args.distance = "euclidean"
return folder_name, dataset_name, args
def __init__(self, methodName):
super().__init__(methodName)
self.generator = IndependentGenerator(alphabet_size=ALPHABET_SIZE, seed=0)
self.dataset = HierarchicalClusteringDatasetGenerator(N_reference=10, N_leaves=15, len_sequence=20,
min_changes=3, max_changes=10,
string_generator=self.generator, seed=0)
help='Number of references')
parser.add_argument('--N_query',
type=int,
default=1000,
help='Number of queries')
parser.add_argument('--len_sequence',
type=int,
default=1024,
help='Length of sequences')
parser.add_argument('--min_changes',
type=float,
default=50,
help='Minimum number of mutations')
parser.add_argument('--max_changes',
type=float,
default=600,
help='Maximum number of mutations')
parser.add_argument('--initials',
type=float,
default=200,
help='Initial independently generated sequences')
parser.add_argument('--seed', type=int, default=0, help='Random seed')
args = parser.parse_args()
generator = IndependentGenerator(seed=args.seed)
data = ClosestStringDatasetGenerator\
(N_reference=args.N_reference, N_query=args.N_query,
len_sequence=args.len_sequence, min_changes=args.min_changes, max_changes=args.max_changes,
seed=args.seed, string_generator=generator, initials=args.initials)
data.save_as_pickle(args.out)