def sequence_idp(params, patterns):
for p in patterns:
print p
indices = set([seq.id for seq in patterns])
nonclosed_indices = set()
# closed pattern mining by generated IDP code
idp_gen = IDPGenerator(params)
path, filename = os.path.split(params["data"])
idp_program_name = "{0}_{1}_{2}".format(params["dominance"], params["type"], filename.split(".")[0])
if params["dominance"] == "closed":
support_mapping = make_grouping_by_support(patterns)
else:
support_mapping = None
attribute_mapping = make_attribute_mapping(patterns)
for support, group in support_mapping.items():
if len(group) == 1:
print group
continue
check_mapping = defaultdict(set)
for seq in group:
patterns_to_check = get_attribute_intersection(seq, attribute_mapping, support_mapping)
if patterns_to_check:
check_mapping[seq] = patterns_to_check
if len(check_mapping.values()) != 0:
idp_gen.gen_IDP_code_group(check_mapping, idp_program_name)
idp_output = idp_gen.run_IDP(idp_program_name)
lines = idp_output.split("\n")
for line in lines:
if "selected_seq" in line:
nonclosed_indices.add(int(line[19]))
indices = indices - nonclosed_indices
print indices
"""
for seq in tqdm(patterns):
#if we make it a function, is_closed(seq)
#then we need just need async_map(is_closed,patterns)
patterns_to_check = get_attribute_intersection(seq,mapping,support_mapping)
if len(patterns_to_check) > 1: #the pattern itself and other patterns
# generate idp code for finding pattern with constraints for this seq
idp_gen.gen_IDP_code(patterns_to_check, idp_program_name, seq.id)
idp_output = idp_gen.run_IDP(idp_program_name)
if 'Unsatisfiable' in idp_output:
print(seq.id)
os.system("cp IDP/closed_sequence_test.idp tmp/seq_test_{id}".format(id=seq.id))
return # break here look at the INDEX, it should be 1 but it is 2 for some reason;
# the same for the case of id = 5, it is selected as 2 for some reason
indices.append(seq.id)
else:
indices.append(seq.id)
"""
return indices
def itemset_idp_new(params, patterns):
indices = []
# closed pattern mining by generated IDP code
idp_gen = IDPGenerator(params)
path, filename = os.path.split(params["data"])
idp_program_name = "{0}_{1}_{2}".format(params["dominance"], params["type"], filename.split(".")[0])
if params["dominance"] == "closed":
support_mapping = make_grouping_by_support(patterns)
else:
support_mapping = None
mapping = make_attribute_mapping(patterns)
return indices
def sequence_idp_multiple(params, patterns):
indices = set([seq.id for seq in patterns])
nonclosed_indices = set()
# closed pattern mining by generated IDP code
idp_gen = IDPGenerator(params)
path, filename = os.path.split(params["data"])
idp_program_name = "{0}_{1}_{2}".format(params["dominance"], params["type"], filename.split(".")[0])
if params["dominance"] == "closed":
support_mapping = make_grouping_by_support(patterns)
else:
support_mapping = None
attribute_mapping = make_attribute_mapping(patterns)
""" group testing """
mapping_groups = []
for group in support_mapping.values():
if len(group) == 1:
print group
continue
check_mapping = defaultdict(set)
for seq in group:
patterns_to_check = get_attribute_intersection(seq, attribute_mapping, support_mapping)
if len(patterns_to_check) > 1:
check_mapping[seq] = patterns_to_check
if check_mapping:
mapping_groups.append(check_mapping)
nonclosed_indices = async_mapping(mapping_groups, idp_gen, idp_program_name)
# nonclosed_indices = async_mapping_withoutLock(mapping_groups, idp_gen, idp_program_name)
"""
lines = idp_output.split('\n')
for line in lines:
if 'selected_seq' in line:
nonclosed_indices.add(int(line[19]))
"""
indices = indices - nonclosed_indices
print indices
return indices
