graph_label[i, 0] -= 1
#===========================================================================
# COMPUTE PROPAGATION KERNELS
#===========================================================================
num_Iteration = 10
w = 1e-4
dist = 'tv' # possible values: 'tv', 'hellinger'
np.random.seed(
1
) # set random seed to get reproducible kernel matrices (to account for randomness in kernel average resutls over several returns of the experiment)
K = graphKernels.propagationKernel(A,
node_label,
gr_id,
num_Iteration,
w,
dist,
'label_diffusion',
SUM=True,
VIS=False,
showEachStep=False)
#----------------------------------------------------------------------
# Cross Validation
#----------------------------------------------------------------------
print '...GP prediction (10-fold CV)'
for t in xrange(num_Iteration + 1):
ACC = [] # accuracy
print 'number of kernel iterations =', t
Matrix = K[:, :, t]
graph_label = data['labels'] # N x 1 graph label array
N = graph_label.shape[0] # number of graphs)
graph_label = np.int8(graph_label)
for i in range(N):
if graph_label[i,0] == 0:
graph_label[i,0] -= 1
#===========================================================================
# COMPUTE PROPAGATION KERNELS
#===========================================================================
num_Iteration = 10
w = 1e-4
dist = 'tv' # possible values: 'tv', 'hellinger'
np.random.seed(1) # set random seed to get reproducible kernel matrices (to account for randomness in kernel average resutls over several returns of the experiment)
K = graphKernels.propagationKernel(A, node_label, gr_id, num_Iteration, w, dist, 'label_diffusion', SUM=True, VIS=False, showEachStep=False)
#----------------------------------------------------------------------
# Cross Validation
#----------------------------------------------------------------------
print('...GP prediction (10-fold CV)')
for t in range(num_Iteration+1):
ACC = [] # accuracy
print('number of kernel iterations =', t)
Matrix = K[:,:,t]
# normalize kernel matrix (not useful for MUTAG)
# Matrix = graphUtil.normalizeKernel(Matrix)
# start cross-validation for this t