def launch():
DATA = read_data_sc2('../data/sequences-TZ-45.txt')[:5000]
DATA = reduce_k_length(10, DATA)
results = exhaustive(DATA, '1', top_k=10, enable_i=True)
print_results(results)
def compare_ground_truth():
data = read_data_sc2('../data/sequences-TZ-45.txt')[:5000]
data = reduce_k_length(10, data)
target = '1'
enable_i = True
# if we want to average
nb_launched = 5
pool = Pool(processes=3)
iterations_limit = 50
iteration_step = 1000
data_final = {'WRAcc': [], 'iterations': [], 'Algorithm': []}
# found with exaustive search
ground_truth = 0.008893952000000009
for i in range(10):
print('Iteration: {}'.format(i))
for i in range(nb_launched):
result_ucb_opti = pool.apply_async(
seq_scout, (data, target), {
'enable_i': enable_i,
'time_budget': TIME_BUDGET_XP,
'iterations_limit': iterations_limit
})
data_add_generic(
data_final,
WRAcc=max(0, average_results(result_ucb_opti.get())) /
ground_truth,
iterations=iterations_limit,
Algorithm='seqscout')
iterations_limit += iteration_step
df = pd.DataFrame(data=data_final)
sns.set(rc={'figure.figsize': (8, 6.5)})
plt.clf()
ax = sns.lineplot(data=df, x='iterations', y='WRAcc', hue='Algorithm')
ax.set(xlabel='iterations', ylabel='WRAcc')
plt.savefig('./ground_truth/gt.png')
df.to_pickle('./ground_truth/result')
if SHOW:
plt.show()
def launch():
DATA = read_data_sc2('../data/sequences-TZ-45.txt')[:5000]
#DATA = reduce_k_length(10, DATA)
# DATA = read_data_kosarak('../data/blocks.data')
# DATA = read_data_kosarak('../data/skating.data')
# DATA = read_data_kosarak('../data/context.data')
# DATA = read_data(pathlib.Path(__file__).parent.parent / 'data/promoters.data')
# DATA = read_jmlr('machin', pathlib.Path(__file__).parent.parent / 'data/jmlr/jmlr')
#ITEMS = extract_items(DATA)
#ITEMS, items_to_encoding, encoding_to_items = encode_items(ITEMS)
#DATA = encode_data(DATA, items_to_encoding)
results = seq_scout(DATA,
'1',
time_budget=60,
top_k=5,
enable_i=False,
vertical=False,
iterations_limit=10000)
#results = seq_scout_api(DATA, '+', 10, 5)
print_results(results)
somme = w_k(memo, l_max, m)
for i, value in memo.items():
somme += value
return somme
if __name__ == '__main__':
datasets = [(read_data_kosarak('../data/aslbu.data'), '195', 'aslbu'),
(read_data('../data/promoters.data'), '+', 'promoters'),
(read_data_kosarak('../data/blocks.data'), '1', 'blocks'),
(read_data_kosarak('../data/context.data'), '4', 'context'),
(read_data('../data/splice.data'), 'EI', 'splice'),
(read_data_sc2('../data/sequences-TZ-45.txt')[:5000], '1',
'sc2'),
(read_data_kosarak('../data/skating.data'), '1', 'skating'),
(read_jmlr('svm', '../data/jmlr/jmlr'), 'svm', 'jmlr')]
for dataset in datasets:
DATA, class_target, dataset_name = dataset
# we remove first element wich are useless
for i in range(len(DATA)):
DATA[i] = DATA[i][1:]
#pattern_number, stages = compute_dataset_size(DATA)
#print(pattern_number)
# print(stages)
def seq_scout_api(dataset=conf.DATA,
time_budget=conf.TIME_BUDGET,
top_k=conf.TOP_K):
'''
Launch seq_scout.
This function is for the simplicity of the user, so that she does not needs to specify iterations number,
which is here only for experiments.
'''
if dataset == 'splice':
data = read_data(
pathlib.Path(__file__).parent.parent / 'data/splice.data')
target_class = 'EI'
enable_i = False
elif dataset == 'alsbu':
data = read_data_kosarak(
pathlib.Path(__file__).parent.parent / 'data/aslbu.data')
target_class = '195'
enable_i = False
elif dataset == 'alsbu':
data = read_data_kosarak(
pathlib.Path(__file__).parent.parent / 'data/blocks.data')
target_class = '7'
enable_i = False
elif dataset == 'context':
data = read_data_kosarak(
pathlib.Path(__file__).parent.parent / 'data/context.data')
target_class = '4'
enable_i = False
elif dataset == 'sc2':
data = read_data_sc2(
pathlib.Path(__file__).parent.parent /
'data/sequences-TZ-45.txt')[:5000]
target_class = '1'
enable_i = True
elif dataset == 'skating':
data = read_data_kosarak(
pathlib.Path(__file__).parent.parent / 'data/skating.data')
target_class = '1'
enable_i = False
elif dataset == 'jmlr':
data = read_jmlr(
'svm',
pathlib.Path(__file__).parent.parent / 'data/jmlr/jmlr')
target_class = '+'
enable_i = False
else:
data = read_data(
pathlib.Path(__file__).parent.parent / 'data/promoters.data')
target_class = '+'
enable_i = False
class_present = False
for sequence in data:
if target_class == sequence[0]:
class_present = True
break
if not class_present:
raise ValueError('The target class does not appear in data')
items = extract_items(data)
items, items_to_encoding, encoding_to_items = encode_items(items)
data = encode_data(data, items_to_encoding)
results = seq_scout(data,
target_class,
top_k=top_k,
vertical=False,
time_budget=time_budget,
iterations_limit=10000000000000,
enable_i=enable_i)
print_results_decode(results, encoding_to_items)
return results
datasets = [
(read_data_kosarak(
pathlib.Path(__file__).parent.parent / 'data/aslbu.data'), '195',
False),
(read_data(pathlib.Path(__file__).parent.parent / 'data/promoters.data'),
'+', False),
(read_data_kosarak(
pathlib.Path(__file__).parent.parent / 'data/blocks.data'), '7',
False),
(read_data_kosarak(
pathlib.Path(__file__).parent.parent / 'data/context.data'), '4',
False),
(read_data(pathlib.Path(__file__).parent.parent / 'data/splice.data'),
'EI', False),
(read_data_sc2(
pathlib.Path(__file__).parent.parent /
'data/sequences-TZ-45.txt')[:5000], '1', False),
(read_data_kosarak(
pathlib.Path(__file__).parent.parent / 'data/skating.data'), '1',
False),
(read_jmlr('svm',
pathlib.Path(__file__).parent.parent / 'data/jmlr/jmlr'), '+',
False)
]
datasets_names = [
'aslbu', 'promoters', 'blocks', 'context', 'splice', 'sc2', 'skating',
'jmlr'
]
SHOW = False