def test_downsampling_matrices(self):
nodes_enc = [256,64,32,16,4]
ups = gc.WEI
# Contiguous nodes
self.G_params['type_z'] = ds.CONT
G = ds.create_graph(self.G_params, seed=SEED)
cluster = gc.MultiResGraphClustering(G, nodes_enc, k=4, up_method=ups)
out = np.array(cluster.labels[-1])
for D in cluster.Ds:
out = D.dot(out)/np.sum(D,1)
self.assertTrue(np.array_equal(out, np.unique(cluster.labels[-1])))
# Alternated nodes
self.G_params['type_z'] = ds.ALT
G = ds.create_graph(self.G_params, seed=SEED)
cluster = gc.MultiResGraphClustering(G, nodes_enc, k=4, up_method=ups)
out = np.array(cluster.labels[-1])
for D in cluster.Ds:
out = D.dot(out)/np.sum(D,1)
self.assertTrue(np.array_equal(out, np.unique(cluster.labels[-1])))
# Random nodes
self.G_params['type_z'] = ds.RAND
G = ds.create_graph(self.G_params, seed=SEED)
cluster = gc.MultiResGraphClustering(G, nodes_enc, k=4, up_method=ups)
out = np.array(cluster.labels[-1])
for D in cluster.Ds:
out = D.dot(out)/np.sum(D,1)
self.assertTrue(np.array_equal(out, np.unique(cluster.labels[-1])))
def create_model(Gx, Gy, exp, lrn):
if exp['type'] == 'Linear':
model = LinearModel(exp['N'])
elif exp['type'] == 'Enc_Dec':
clust_x = gc.MultiResGraphClustering(Gx, exp['n_enc'],
k=exp['n_enc'][-1],
up_method=exp['downs'])
clust_y = gc.MultiResGraphClustering(Gy, exp['n_dec'],
k=exp['n_enc'][-1],
up_method=exp['ups'])
net = GraphEncoderDecoder(exp['f_enc'], clust_x.sizes, clust_x.Ds,
exp['f_dec'], clust_y.sizes, clust_y.Us,
exp['f_conv'], As_dec=clust_y.As,
As_enc=clust_x.As, act_fn=lrn['af'],
last_act_fn=lrn['laf'], ups=exp['ups'],
downs=exp['downs'])
elif exp['type'] == 'AutoConv':
net = ConvAutoencoder(exp['f_enc'], exp['kernel_enc'],
exp['f_dec'], exp['kernel_dec'])
elif exp['type'] == 'AutoFC':
net = FCAutoencoder(exp['n_enc'], exp['n_dec'], bias=exp['bias'])
else:
raise RuntimeError('Unknown experiment type')
if exp['type'] != 'Linear':
model = Model(net, learning_rate=lrn['lr'], decay_rate=lrn['dr'],
batch_size=lrn['batch'], epochs=lrn['epochs'],
eval_freq=EVAL_F, max_non_dec=lrn['non_dec'],
verbose=VERBOSE)
return model
def test_upsampling_matrices(self):
nodes_enc = [4,16,32,64,256]
ups = gc.WEI
# Contiguous nodes
self.G_params['type_z'] = ds.CONT
G = ds.create_graph(self.G_params, seed=SEED)
cluster = gc.MultiResGraphClustering(G, nodes_enc, k=4, up_method=ups)
out = np.unique(cluster.labels[0])
for U in cluster.Us:
out = U.dot(out)
self.assertTrue(np.array_equal(out,cluster.labels[0]))
# Alternated nodes
self.G_params['type_z'] = ds.ALT
G = ds.create_graph(self.G_params, seed=SEED)
cluster = gc.MultiResGraphClustering(G, nodes_enc, k=4, up_method=ups)
out = np.unique(cluster.labels[0])
for U in cluster.Us:
out = U.dot(out)
self.assertTrue(np.array_equal(out,cluster.labels[0]))
# Random nodes
self.G_params['type_z'] = ds.RAND
G = ds.create_graph(self.G_params, seed=SEED)
cluster = gc.MultiResGraphClustering(G, nodes_enc, k=4, up_method=ups)
out = np.unique(cluster.labels[0])
for U in cluster.Us:
out = U.dot(out)
self.assertTrue(np.array_equal(out,cluster.labels[0]))
def run(id, Gs, signals, lrn, deltas):
Gx = ds.create_graph(Gs['params'], seed=SEED)
Gy = ds.create_graph(Gs['params_y'], seed=SEED)
data = ds.LinearDS2GS(Gx, Gy, signals['samples'], signals['L'],
deltas, median=signals['median'],
same_coeffs=signals['same_coeffs'])
data.to_unit_norm()
data.add_noise(signals['noise'], test_only=signals['test_only'])
data.to_tensor()
epochs = 0
mean_err = np.zeros(N_EXPS)
med_err = np.zeros(N_EXPS)
mse = np.zeros(N_EXPS)
for i, exp in enumerate(EXPS):
if exp['type'] == 'Linear':
model = LinearModel(exp['N'])
elif exp['type'] == 'Enc_Dec':
clust_x = gc.MultiResGraphClustering(Gx, exp['n_enc'],
k=exp['n_enc'][-1],
up_method=exp['downs'])
clust_y = gc.MultiResGraphClustering(Gy, exp['n_dec'],
k=exp['n_enc'][-1],
up_method=exp['ups'])
net = GraphEncoderDecoder(exp['f_enc'], clust_x.sizes, clust_x.Ds,
exp['f_dec'], clust_y.sizes, clust_y.Us,
exp['f_conv'], As_dec=clust_y.As,
As_enc=clust_x.As, act_fn=lrn['af'],
last_act_fn=lrn['laf'], ups=exp['ups'],
downs=exp['downs'])
elif exp['type'] == 'AutoConv':
net = ConvAutoencoder(exp['f_enc'], exp['kernel_enc'],
exp['f_dec'], exp['kernel_dec'])
elif exp['type'] == 'AutoFC':
net = FCAutoencoder(exp['n_enc'], exp['n_dec'], bias=exp['bias'])
else:
raise RuntimeError('Unknown experiment type')
if exp['type'] != 'Linear':
model = Model(net, learning_rate=lrn['lr'], decay_rate=lrn['dr'],
batch_size=lrn['batch'], epochs=lrn['epochs'],
eval_freq=EVAL_F, max_non_dec=lrn['non_dec'],
verbose=VERBOSE)
epochs, _, _ = model.fit(data.train_X, data.train_Y, data.val_X, data.val_Y)
mean_err[i], med_err[i], mse[i] = model.test(data.test_X, data.test_Y)
print('G: {}, {}-{} ({}): epochs {} - mse {} - MedianErr: {}'
.format(id, i, exp['type'], model.count_params(), epochs,
mse[i], med_err[i]))
return mean_err, med_err, mse
def test_wrong_sizes_dec(self):
nodes = [4, 4, 16, 32, 32, 64, 64, 256, 64, 256, 256]
try:
gc.MultiResGraphClustering(self.G, nodes, k=4, up_method=None)
self.fail()
except:
pass
def setUp(self):
np.random.seed(SEED)
G_params = {}
G_params['type'] = ds.SBM
G_params['N'] = 256
G_params['k'] = 4
G_params['p'] = 0.15
G_params['q'] = 0.01/4
G_params['type_z'] = ds.RAND
G = ds.create_graph(G_params, seed=SEED)
nodes_dec = [4,16,32,64,256]
ups = gc.WEI
self.N = nodes_dec[-1]
self.k = nodes_dec[0]
self.cluster = gc.MultiResGraphClustering(G, nodes_dec, k=4, up_method=ups)
self.model = Sequential()
for i,U in enumerate(self.cluster.Us):
self.add_layer(GraphUpsampling(U, self.cluster.As[i+1],gamma=1))
def estimate_signals(i, G_params, eps_c, eps_d, n_samples, L, nodes_enc,
nodes_dec, ups, feat_enc, feat_dec, feat_only_conv):
# Create graphs
Gx, Gy = data_sets.perturbated_graphs(G_params, eps_c, eps_d, seed=SEED)
# Create graph signals
data = data_sets.LinearDS2GS(Gx,
Gy,
n_samples,
L,
3 * G_params['k'],
median=True)
data.to_unit_norm()
print('Median Diff between Y and X:',
np.median(np.linalg.norm((data.train_X - data.train_Y)**2, 1)))
X = data.train_X
Beta = np.linalg.pinv(X.T.dot(X)).dot(X.T).dot(data.train_Y)
test_Y = data.test_Y
est_Y_test = data.test_X.dot(Beta)
test_err = np.sum(
(est_Y_test - test_Y)**2, axis=1) / np.linalg.norm(data.test_Y)**2
print('Linear model: mean err: {} - median: {}'.format(
np.mean(test_err), np.median(test_err)))
data.to_tensor()
# Obtein clusters
cluster_x = gc.MultiResGraphClustering(Gx, nodes_enc, k=4, up_method=None)
cluster_y = gc.MultiResGraphClustering(Gy, nodes_dec, k=4, up_method=ups)
# Standar ConvAutoenc
net = architecture.GraphEncoderDecoder(feat_enc, [Gx.N] * 7,
cluster_x.Ds,
feat_dec, [Gx.N] * 7,
cluster_y.Us,
feat_only_conv,
As_dec=cluster_y.As,
last_act_fn=nn.Tanh(),
act_fn=nn.Tanh())
model = Model(net,
decay_rate=.9,
epochs=25,
batch_size=100,
learning_rate=0.05,
verbose=True,
eval_freq=1,
max_non_dec=5)
print('Model parameters: ', model.count_params())
model.fit(data.train_X, data.train_Y, data.val_X, data.val_Y)
mean_err, median_err, mse = model.test(data.test_X, data.test_Y)
print(
'Autoencoder: Graph {}: N: {} Mean MSE: {} - Mean Err: {} - Median Err: {}'
.format(i, Gx.N, mse, mean_err, median_err))
# Graph Autoenc
net = architecture.GraphEncoderDecoder(feat_enc,
cluster_x.sizes,
cluster_x.Ds,
feat_dec,
cluster_y.sizes,
cluster_y.Us,
feat_only_conv,
As_dec=cluster_y.As,
last_act_fn=nn.Tanh(),
act_fn=nn.Tanh())
model = Model(net,
decay_rate=.9,
epochs=25,
batch_size=100,
learning_rate=0.05,
verbose=True,
eval_freq=1,
max_non_dec=5)
print('Model parameters: ', model.count_params())
model.fit(data.train_X, data.train_Y, data.val_X, data.val_Y)
mean_err, median_err, mse = model.test(data.test_X, data.test_Y)
print(
'GRAPH ENC-DEC Graph {}: N: {} Mean MSE: {} - Mean Err: {} - Median Err: {}'
.format(i, Gx.N, mse, mean_err, median_err))
return mean_err, mse, model.count_params()
def estimate_signals(id, G_params, n_samples, L, nodes_enc, nodes_dec, ups,
feat_enc, feat_dec, feat_only_conv):
# Create graphs
Gx, Gy = data_sets.perturbated_graphs(G_params,
creat,
dest,
pct=pct,
seed=SEED)
diff_links = np.sum(Gx.A != Gy.A) / 2 / Gx.Ne * 100
print('Links different(%):', diff_links)
# Create graph signals
data = data_sets.NonLinearDS2GS(Gx,
Gy,
n_samples,
L,
deltas,
median=median,
same_coeffs=same_coeffs)
data.to_unit_norm()
data.add_noise(p_n, test_only=True)
mean_dist = np.median(np.linalg.norm(data.train_X - data.train_Y, axis=1))
print('Distance signals:', mean_dist)
data.to_tensor()
N = G_params['N']
k = G_params['k']
model = LinearModel(N)
model.fit(data.train_X, data.train_Y, data.val_X, data.val_Y)
mean_err, med_err, mse = model.test(data.test_X, data.test_Y)
print(
'LINEAR Graph {}: N: {} Mean MSE: {} - Mean Err: {} - Median Err: {}'.
format(id, Gx.N, mse, mean_err, med_err))
# Obtein clusters
cluster_x = gc.MultiResGraphClustering(Gx, nodes_enc, k=k, up_method=ups)
cluster_y = gc.MultiResGraphClustering(Gy, nodes_dec, k=k, up_method=ups)
# Graph Autoenc
net = architecture.GraphEncoderDecoder(feat_enc,
cluster_x.sizes,
cluster_x.Ds,
feat_dec,
cluster_y.sizes,
cluster_y.Us,
feat_only_conv,
As_dec=cluster_y.As,
As_enc=cluster_x.As,
ups=ups,
last_act_fn=nn.Tanh(),
downs=ups,
act_fn=nn.Tanh())
model = Model(net,
decay_rate=dr,
epochs=epochs,
batch_size=bs,
learning_rate=lr,
verbose=False,
eval_freq=1,
max_non_dec=10)
print('Model parameters: ', model.count_params())
iters, _, _ = model.fit(data.train_X, data.train_Y, data.val_X, data.val_Y)
mean_err, med_err, mse = model.test(data.test_X, data.test_Y)
print('G: {}, ({}): epochs {} - mse {} - MedianErr: {}'.format(
id, model.count_params(), iters, mse, med_err))
return mean_err, mse, med_err, diff_links, mean_dist, iters
signals['deltas'], median=signals['median'],
same_coeffs=signals['same_coeffs'])
data.to_unit_norm()
data.add_noise(p_n, test_only=signals['test_only'])
data.to_tensor()
epochs = 0
mean_err = np.zeros(N_EXPS)
med_err = np.zeros(N_EXPS)
mse = np.zeros(N_EXPS)
for i, exp in enumerate(EXPS):
if exp['type'] == 'Linear':
model = LinearModel(exp['N'])
elif exp['type'] == 'Enc_Dec':
clust_x = gc.MultiResGraphClustering(Gx, exp['n_enc'],
k=exp['n_enc'][-1],
up_method=exp['downs'])
clust_y = gc.MultiResGraphClustering(Gy, exp['n_dec'],
k=exp['n_enc'][-1],
up_method=exp['ups'])
net = GraphEncoderDecoder(exp['f_enc'], clust_x.sizes, clust_x.Ds,
exp['f_dec'], clust_y.sizes, clust_y.Us,
exp['f_conv'], As_dec=clust_y.As,
As_enc=clust_x.As, act_fn=lrn['af'],
last_act_fn=lrn['laf'], ups=exp['ups'],
downs=exp['downs'])
elif exp['type'] == 'AutoConv':
net = ConvAutoencoder(exp['f_enc'], exp['kernel_enc'],
exp['f_dec'], exp['kernel_dec'])
elif exp['type'] == 'AutoFC':
net = FCAutoencoder(exp['n_enc'], exp['n_dec'], bias=exp['bias'])
def run(id, Gs, signals, lrn, p_n):
Gx, Gy = ds.perturbated_graphs(Gs['params'],
Gs['pct_val'][0],
Gs['pct_val'][1],
pct=Gs['pct'],
seed=SEED)
data = ds.LinearDS2GS(Gx,
Gy,
signals['samples'],
signals['L'],
signals['deltas'],
median=signals['median'],
same_coeffs=signals['same_coeffs'])
# data = ds.NonLinearDS2GS(Gx, Gy, signals['samples'], signals['L'],
# signals['deltas'], median=signals['median'],
# same_coeffs=signals['same_coeffs'])
data.to_unit_norm()
data.add_noise(p_n, test_only=signals['test_only'])
median_dist = np.median(np.linalg.norm(data.train_X - data.train_Y,
axis=1))
print('Signal {}: distance {}'.format(id, median_dist))
data.to_tensor()
med_err = np.zeros(N_EXPS)
mse = np.zeros(N_EXPS)
epochs = np.zeros(N_EXPS)
for i, exp in enumerate(EXPS):
clust_x = gc.MultiResGraphClustering(Gx,
exp['n_enc'],
k=exp['n_enc'][-1],
up_method=exp['downs'])
clust_y = gc.MultiResGraphClustering(Gy,
exp['n_dec'],
k=exp['n_enc'][-1],
up_method=exp['ups'])
net = GraphEncoderDecoder(exp['f_enc'],
clust_x.sizes,
clust_x.Ds,
exp['f_dec'],
clust_y.sizes,
clust_y.Us,
exp['f_conv'],
As_dec=clust_y.As,
As_enc=clust_x.As,
act_fn=lrn['af'],
last_act_fn=lrn['laf'],
ups=exp['ups'],
downs=exp['downs'])
model = Model(net,
learning_rate=lrn['lr'],
decay_rate=lrn['dr'],
batch_size=lrn['batch'],
epochs=lrn['epochs'],
eval_freq=EVAL_F,
max_non_dec=lrn['non_dec'],
verbose=VERBOSE)
epochs[i], _, _ = model.fit(data.train_X, data.train_Y, data.val_X,
data.val_Y)
_, med_err[i], mse[i] = model.test(data.test_X, data.test_Y)
print('G: {}, {}-{} ({}): epochs {} - mse {} - MedianErr: {}'.format(
id, i, exp['type'], model.count_params(), epochs[i], mse[i],
med_err[i]))
return med_err, mse, epochs
def run(id, Gs, Signals, lrn, pert):
if Gs['params']['type'] == ds.SBM:
Gx, Gy = ds.nodes_perturbated_graphs(Gs['params'],
pert,
seed=SEED,
perm=True)
elif Gs['params']['type'] == ds.BA:
Gx = ds.create_graph(Gs['params'], SEED)
G_params_y = Gs['params'].copy()
G_params_y['N'] = Gs['params']['N'] - pert
Gy = ds.create_graph(G_params_y, 2 * SEED)
else:
raise RuntimeError("Choose a valid graph type")
data = ds.LinearDS2GSNodesPert(Gx,
Gy,
Signals['samples'],
Signals['L'],
Signals['deltas'],
median=Signals['median'],
same_coeffs=Signals['same_coeffs'],
neg_coeffs=Signals['neg_coeffs'])
data.to_unit_norm()
data.add_noise(Signals['noise'], test_only=Signals['test_only'])
data.to_tensor()
epochs = 0
params = np.zeros(N_EXPS)
med_err = np.zeros(N_EXPS)
mse = np.zeros(N_EXPS)
for i, exp in enumerate(EXPS):
if exp['type'] == 'Linear':
model = LinearModel(exp['N'])
elif exp['type'] == 'Enc_Dec':
exp['n_dec'][-1] = Gy.N
clust_x = gc.MultiResGraphClustering(Gx,
exp['n_enc'],
k=exp['n_enc'][-1],
up_method=exp['downs'])
clust_y = gc.MultiResGraphClustering(Gy,
exp['n_dec'],
k=exp['n_enc'][-1],
up_method=exp['ups'])
net = GraphEncoderDecoder(exp['f_enc'],
clust_x.sizes,
clust_x.Ds,
exp['f_dec'],
clust_y.sizes,
clust_y.Us,
exp['f_conv'],
As_dec=clust_y.As,
K_dec=exp['K_dec'],
K_enc=exp['K_enc'],
As_enc=clust_x.As,
act_fn=lrn['af'],
last_act_fn=lrn['laf'],
ups=exp['ups'],
downs=exp['downs'])
elif exp['type'] == 'AutoConv':
conv = exp['convs'][PERT.index(pert)]
net = ConvAutoencoder(conv['f_enc'], conv['kernel_enc'],
conv['f_dec'], conv['kernel_dec'])
elif exp['type'] == 'AutoFC':
exp['n_dec'][-1] = Gy.N
net = FCAutoencoder(exp['n_enc'], exp['n_dec'], bias=exp['bias'])
else:
raise RuntimeError('Unknown experiment type')
if exp['type'] != 'Linear':
model = Model(net,
learning_rate=lrn['lr'],
decay_rate=lrn['dr'],
batch_size=lrn['batch'],
epochs=lrn['epochs'],
eval_freq=EVAL_F,
max_non_dec=lrn['non_dec'],
verbose=VERBOSE,
early_stop=exp['early_stop'])
epochs, _, _ = model.fit(data.train_X, data.train_Y, data.val_X,
data.val_Y)
_, med_err[i], mse[i] = model.test(data.test_X, data.test_Y)
params[i] = model.count_params()
print('G: {}, {}-{} ({}): epochs {} - mse {} - MedianErr: {}'.format(
id, i, exp['type'], params[i], epochs, mse[i], med_err[i]))
return params, med_err, mse
def all_sizes_repeated(self):
nodes = [256,256,256]
cluster = gc.MultiResGraphClustering(self.G, nodes, k=4, up_method=None)
self.assertEqual(len(nodes), len(cluster.sizes))
self.assertEqual(len([]),len(cluster.Ds))
def repeated_sizes_dec(self):
nodes = [4,4,16,32,32,64,256,256,256]
no_rep_nodes = set(nodes)
cluster = gc.MultiResGraphClustering(self.G, nodes, k=4, up_method=None)
self.assertEqual(len(nodes), len(cluster.sizes))
self.assertEqual(len(no_rep_nodes)-1, len(cluster.Us))
def all_sizes_diff_dec(self):
nodes = [4,16,32,64,256]
cluster = gc.MultiResGraphClustering(self.G, nodes, k=4, up_method=None)
self.assertEqual(len(nodes), len(cluster.sizes))
self.assertEqual(len(nodes)-1, len(cluster.Us))
def all_sizes_diff_enc(self):
nodes = [256, 64, 32, 16, 4]
cluster = gc.MultiResGraphClustering(self.G, nodes, k=4, up_method=None)
self.assertEqual(len(nodes), len(cluster.sizes))
self.assertEqual(len(nodes)-1, len(cluster.Ds))