def create_machine_datadir(datadir_path, machinedir_path, machine_name):
pathobj= config.paths(datadir= datadir_path)
new_pathobj= config.paths(datadir= machinedir_path)
paths= [os.path.join(pathobj.TS_DIR, machine_name + "-" + name + ".data") for name in find_machine_timeseries(machine_name)]
json_paths= [os.path.join(pathobj.TS_JSON_DIR, machine_name + "-" + name + ".data") for name in find_machine_timeseries(machine_name)]
if not os.path.exists(new_pathobj.DATA_DIR):
os.mkdir(new_pathobj.DATA_DIR)
if not os.path.exists(new_pathobj.TS_DIR):
os.mkdir(new_pathobj.TS_DIR)
if not os.path.exists(new_pathobj.TS_JSON_DIR):
os.mkdir(new_pathobj.TS_JSON_DIR)
for json_path, path in zip(json_paths, paths):
shutil.copy(path, new_pathobj.TS_DIR)
def find_machine_timeseries(
machine_name
): # returns list of timeseries names for a given machine name
pathobj = config.paths()
imp_file = open(os.path.join(pathobj.DATA_BASE_DIR, "important.json"), 'r')
names = json.load(imp_file)
imp_file.close()
return names[machine_name]
def create_machine_datadir(datadir_path, machinedir_path, machine_name):
pathobj = config.paths(datadir=datadir_path)
new_pathobj = config.paths(datadir=machinedir_path)
paths = [
os.path.join(pathobj.TS_DIR, machine_name + "-" + name + ".data")
for name in find_machine_timeseries(machine_name)
]
json_paths = [
os.path.join(pathobj.TS_JSON_DIR, machine_name + "-" + name + ".data")
for name in find_machine_timeseries(machine_name)
]
if not os.path.exists(new_pathobj.DATA_DIR):
os.mkdir(new_pathobj.DATA_DIR)
if not os.path.exists(new_pathobj.TS_DIR):
os.mkdir(new_pathobj.TS_DIR)
if not os.path.exists(new_pathobj.TS_JSON_DIR):
os.mkdir(new_pathobj.TS_JSON_DIR)
for json_path, path in zip(json_paths, paths):
shutil.copy(path, new_pathobj.TS_DIR)
def find_corr_matrix(dataset):
paths = config.paths(dataset)
anomaly_dict = dict()
for index, path in enumerate([os.path.join(paths.TS_DIR, f) for f in os.listdir(paths.TS_DIR)]):
anomaly_dict[path] = gateway.get_anomalies(path, "combined_hmm", None, percent=0.5)
# print(path)
paths = list()
cor_mat = list()
for i, path in enumerate(anomaly_dict):
print i, anomaly_dict[path]
paths.append(path)
cor_mat.append(list())
weights = anomalies_to_onesided_expweights(anomaly_dict[path])
for j, otherpath in enumerate(anomaly_dict):
cor_mat[i].append(anomaly_weight_overlap(anomaly_dict[otherpath], weights))
return paths, cor_mat
def find_corr_matrix(dataset):
paths = config.paths(dataset)
anomaly_dict = dict()
for index, path in enumerate(
[os.path.join(paths.TS_DIR, f) for f in os.listdir(paths.TS_DIR)]):
anomaly_dict[path] = gateway.get_anomalies(path,
"combined_hmm",
None,
percent=0.5)
#print(path)
paths = list()
cor_mat = list()
for i, path in enumerate(anomaly_dict):
print i, anomaly_dict[path]
paths.append(path)
cor_mat.append(list())
weights = anomalies_to_onesided_expweights(anomaly_dict[path])
for j, otherpath in enumerate(anomaly_dict):
cor_mat[i].append(
anomaly_weight_overlap(anomaly_dict[otherpath], weights))
return paths, cor_mat
def find_machine_timeseries(machine_name): # returns list of timeseries names for a given machine name
pathobj= config.paths()
imp_file= open(os.path.join(pathobj.DATA_BASE_DIR, "important.json"), 'r')
names= json.load(imp_file)
imp_file.close()
return names[machine_name]
