def main(args, **kwargs):
X = utils.load_raw(args)
train_size = int(X.shape[0] * 0.7)
if (args.cs):
random_time_step = rd.randint(0, train_size)
top_k = int(args.random_rate/100 * X.shape[1])
if (top_k < 1): top_k = 1
top_k_index = utils.largest_indices(X[random_time_step], top_k)
top_k_index = np.sort(top_k_index)[0]
if (args.top_k_random):
top_k_index = np.random.randint(X.shape[1], size=top_k_index.shape[0])
X = X[:train_size, top_k_index]
dataset = args.dataset.split('_')[0]
print('Data Shape: {}'.format(X.shape))
print("Time period you want to know ? h='Hour', d='Day', m='Month'")
time_period = input()
if (dataset=='abilene'):
if (time_period=='h'):
data = np.array([np.mean(X[i: i+12], axis=0) for i in
range(0, X.shape[0]-X.shape[0]%12, 12)])
elif (time_period=='d'):
data = np.array([np.mean(X[i: i+288], axis=0) for i in
range(0, X.shape[0]-X.shape[0]%288, 288)])
elif (time_period=='m'):
data = np.array([np.mean(X[i: i+8640], axis=0) for i in
range(0, X.shape[0]-X.shape[0]%8640, 8640)])
elif (dataset=='geant'):
if (time_period=='h'):
data = np.array([np.mean(X[i: i+4], axis=0) for i in
range(0, X.shape[0]-X.shape[0]%4, 4)])
elif (time_period=='d'):
data = np.array([np.mean(X[i: i+96], axis=0) for i in
range(0, X.shape[0]-X.shape[0]%96, 96)])
elif (time_period=='m'):
data = np.array([np.mean(X[i: i+2880], axis=0) for i in
range(0, X.shape[0]-X.shape[0]%2880, 2880)])
elif (dataset=='brain'):
if (time_period=='h'):
data = np.array([np.mean(X[i: i+60], axis=0) for i in
range(0, X.shape[0]-X.shape[0]%60, 60)])
elif (time_period=='d'):
data = np.array([np.mean(X[i: i+1440], axis=0) for i in
range(0, X.shape[0]-X.shape[0]%1440, 1440)])
elif (time_period=='m'): print('Brain data was measured under 7 days!!')
# data = data.reshape(-1, 1)
print('MAX: {}, MIN: {}'.format(np.max(data), np.min(data)))
# if not os.path.exists(os.path.join(os.getcwd(), 'plot_traffic')): os.mkdir('plot_traffic')
# plt.hist(data, bins=12, color='green', range=(np.min(data), np.max(data)), log=True, density=1)
# plt.title(dataset + '_' + time_period)
# plt.savefig('plot_traffic/' + dataset + '_' + time_period + '.png')
var = np.var(data, axis=0)
if (time_period=='h'): print('Variance of {} by Hour: {}'.format(dataset, var))
elif (time_period=='d'): print('Variance of {} by Day: {}'.format(dataset, var))
elif (time_period=='m'): print('Variance of {} by Month: {}'.format(dataset, var))
def get_phi(args, top_k_index):
X = utils.load_raw(args)
G = np.zeros((top_k_index.shape[0], X.shape[1]))
for i, j in enumerate(G):
j[top_k_index[i]] = 1
return G
def get_R(args):
X = utils.load_raw(args)
k_sparse = int(args.random_rate / 100 * X.shape[1])
R = np.zeros((k_sparse, X.shape[1]))
for i in range(R.shape[1]):
d = np.random.randint(R.shape[0] * 2)
if d < k_sparse: R[d, i] = 1
else: continue
return R
def test_load_roadnet_ca(self):
path = raw_roadnet_ca
graph = load_raw(path)
assert is_weighted(graph) is False
assert is_directed(graph) is False
assert graph.has_edge('418', '5')
assert graph.has_edge('108', '13')
assert graph.has_edge('3248', '19')
assert graph.has_edge('108', '8') is False
assert graph.has_edge('16', '14') is False
dump_graphml(graph, processed_roadnet_ca)
def test_load_usair97(self):
path = raw_usair97
graph = load_raw(path)
assert is_weighted(graph) is True
assert is_directed(graph) is False
assert graph['2']['1']['weight'] == 0.0436
assert graph['13']['6']['weight'] == 0.0143
assert graph['144']['8']['weight'] == 0.2746
assert graph['119']['95']['weight'] == 0.0323
assert graph.has_edge('321', '163') is False
assert graph.has_edge('230', '168') is False
dump_graphml(graph, processed_usair97)
def test_load_openflights(self):
path = raw_openflights
graph = load_raw(path)
assert is_weighted(graph) is False
assert is_directed(graph) is True
assert graph.has_edge('2', '4')
assert graph.has_edge('4', '2')
assert graph.has_edge('482', '61')
assert graph.has_edge('592', '308')
assert graph.has_edge('551', '375')
assert graph.has_edge('375', '551') is False
dump_graphml(graph, processed_openflights)
def test_load_roadnet_pa(self):
path = raw_roadnet_pa
graph = load_raw(path)
assert is_weighted(graph) is False
assert is_directed(graph) is False
assert graph.has_edge('6299', '1')
assert graph.has_edge('1', '6299')
assert graph.has_edge('98292', '98290')
assert graph.has_edge('450790', '450673')
assert graph.has_edge('1068204', '592388')
assert graph.has_edge('783720', '733101') is False
assert graph.has_edge('290980', '168570') is False
assert graph.has_edge('98260', '98318') is False
dump_graphml(graph, processed_roadmap_pa)
def test_load_power(self):
path = raw_power
graph = load_raw(path)
assert is_weighted(graph) is False
assert is_directed(graph) is False
assert graph.has_edge('387', '1')
assert graph.has_edge('1813', '1308')
assert graph.has_edge('1517', '1440')
assert graph.has_edge('1527', '1440')
assert graph.has_edge('4599', '4580')
assert graph.has_edge('3797', '4724') is False
assert graph.has_edge('2475', '1070') is False
assert graph.has_edge('420', '425') is False
assert graph.has_edge('465', '4576') is False
dump_graphml(graph, processed_power)
def get_psi(args, samples=10000, iterator=100):
X = utils.load_raw(args)
X = X[:samples, :]
X_temp = np.array([np.max(X[args.seq_len_x + i: \
args.seq_len_x + i + args.seq_len_y], axis=0) for i in range(samples - args.seq_len_x - args.seq_len_y)]).T
size_D = int(math.sqrt(X.shape[1]))
D = RandomDictionary(size_D, size_D)
psi, _ = KSVD(D, MatchingPursuit,
int(args.random_rate / 100 * X.shape[1])).fit(
X_temp, iterator)
return psi
def load_image(self, path):
file = self.bucket.get_object(path)
bytes = file.read()
return load_raw(bytes)