def main(graph, fil, norm, permute, ss, epd, n_cv, flip, feat, feat_kwargs,
ntda):
"""
All hyperprameter goes here.
:param graph: graph dataset
:param fil: filtration function
:param norm: normalize or not
:param permute: whether permute dgm
:param ss: both sublevel and superlevel or not
:param epd: include extended persistence or not
:param n_cv: number of cross validation
:return:
"""
global gs
print('feat kwargs', feat_kwargs)
db = get_tda_db()
params = {
'graph': graph,
'fil': fil,
'norm': norm,
'permute': permute,
'ss': ss,
'epd': epd,
'n_cv': n_cv,
'flip': flip,
'feat': feat,
'ntda': ntda,
'feat_kwargs': feat_kwargs
}
if check_duplicate(db, params): return
label_flag = dgms_dir_test(fil=fil, fil_d='sub', norm=norm, graph=graph)[1]
# gs, labels = load_graphs(dataset=graph, labels_only=label_flag) # step 1
gs, labels = load_tugraphs(
graph, labels_only=False
) # labels_only true means gs is None. Turned on for high speed
# parallel
# subdgms = gs2dgms(gs, n_jobs=-1, fil=fil, fil_d='sub', norm=norm, graph = graph, ntda = ntda, debug_flag=True)
subdgms = gs2dgms_parallel(n_jobs=-1,
fil=fil,
fil_d='sub',
norm=norm,
graph=graph,
ntda=ntda)
supdgms = gs2dgms_parallel(n_jobs=-1,
fil=fil,
fil_d='sup',
norm=norm,
graph=graph,
ntda=ntda)
epddgms = gs2dgms_parallel(n_jobs=-1,
fil=fil,
one_hom=True,
norm=norm,
graph=graph,
ntda=ntda)
dgms = combine_dgms(subdgms, supdgms, epddgms, ss=ss, epd=epd, flip=flip)
dgms = permute_dgms(dgms, permute_flag=permute) # old way
dgms_summary(dgms)
swdgms = dgms2swdgms(dgms)
if feat == 'sw':
print(feat_kwargs)
k, _ = sw_parallel(swdgms,
swdgms,
parallel_flag=True,
kernel_type='sw',
**feat_kwargs)
print(k.shape)
cmargs = {'print_flag': 'off'} # confusion matrix
clf = classifier(labels,
labels,
method='svm',
n_cv=n_cv,
kernel=k,
**cmargs)
clf.svm_kernel_(n_splits=10)
elif feat == 'pi': # vector
params = {
'bandwidth': 1.0,
'weight': (1, 1),
'im_range': [0, 1, 0, 1],
'resolution': [5, 5]
}
images = merge_dgms(subdgms,
supdgms,
epddgms,
vectype='pi',
ss=ss,
epd=epd,
**params)
clf = classifier(images, labels, method='svm', n_cv=n_cv)
clf.svm(n_splits=10)
elif feat == 'pss':
k, _ = sw_parallel(swdgms,
swdgms,
parallel_flag=True,
kernel_type='pss',
**feat_kwargs)
# print(k.shape, k, np.max(k))
clf = classifier(labels, labels, method='svm', n_cv=n_cv, kernel=k)
clf.svm_kernel_(n_splits=10)
elif feat == 'wg':
k, _ = sw_parallel(swdgms,
swdgms,
parallel_flag=True,
kernel_type='wg',
**feat_kwargs)
print(k.shape)
clf = classifier(labels, labels, method='svm', n_cv=n_cv, kernel=k)
clf.svm_kernel_(n_splits=10)
elif feat == 'pervec':
cmargs = {'print_flag': 'on'} # confusion matrix
pd_vector = dgms2vec(dgms, vectype='pervec', **feat_kwargs)
clf = classifier(pd_vector, labels, method='svm', n_cv=n_cv, **cmargs)
clf.svm(n_splits=10)
elif feat == 'pf':
k, _ = sw_parallel(swdgms,
swdgms,
parallel_flag=False,
kernel_type='pf',
**feat_kwargs)
clf = classifier(labels, labels, method='svm', n_cv=n_cv, kernel=k)
clf.svm_kernel_(n_splits=10)
else:
raise Exception('No such feat %s' % feat)
print(clf.stat)
print_line()
return clf.stat
subdgms = gs2dgms_parallel(n_jobs=-1, fil=fil, fil_d='sub', norm=norm)
supdgms = gs2dgms_parallel(n_jobs=-1, fil=fil, fil_d='sup', norm=norm)
epddgms = gs2dgms_parallel(n_jobs=-1, fil=fil, one_hom=True, norm=norm)
# serial
# subdgms = gs2dgms(gs, fil=fil, fil_d='sub', norm=norm, one_hom=False) # step2 # TODO: need to add interface
# supdgms = gs2dgms(gs, fil=fil, fil_d='sup', norm=norm, one_hom=False) # step2 #
# epddgms = gs2dgms(gs, fil=fil, norm=norm, one_hom=True) # step2 # TODO
dgms = combine_dgms(subdgms, supdgms, epddgms, args)
dgms = permute_dgms(dgms, permute_flag=args.permute, permute_ratio=0.5)
dgms_summary(dgms)
# sw kernel
swdgms = dgms2swdgms(dgms)
kwargs = {'bw': args.bw, 'n_directions': 10, 'K': 1, 'p': 1}
sw_kernel, _ = sw_parallel(swdgms,
swdgms,
parallel_flag=True,
kernel_type='sw',
**kwargs)
print(sw_kernel.shape)
clf = classifier(labels,
labels,
method='svm',
n_cv=args.n_cv,
kernel=sw_kernel)
clf.svm_kernel_(n_splits=10)
print(clf.stat)
# print(f'sanity dgm is {print_dgm(sanity_dgms[10])} \n')
print(f'another fake dgm is {print_dgm(another_fake_dgms[10])} \n')
all_dgms = true_dgms + fake_dgms
indicator_labels = [1] * len(true_dgms) + [-1] * len(fake_dgms)
if args.doublefake:
all_dgms = fake_dgms + another_fake_dgms
indicator_labels = [1] * len(fake_dgms) + [-1] * len(another_fake_dgms)
all_dgms = dgms2swdgms(all_dgms)
# classify true diagrams from fake ones
feat_kwargs = {'n_directions': 10, 'bw': 1}
k, _ = sw_parallel(all_dgms,
all_dgms,
parallel_flag=True,
kernel_type='sw',
**feat_kwargs)
print(k.shape)
cmargs = {'print_flag': 'off'} # confusion matrix
clf = classifier(indicator_labels,
indicator_labels,
method='svm',
n_cv=1,
kernel=k,
**cmargs)
clf.svm_kernel_(n_splits=10)
if not args.viz: sys.exit('-' * 50)
feat_kwargs = {'n_directions': 10, 'bw': 1}
def main(graph, fil, norm, permute, ss, epd, n_cv, flip, feat, feat_kwargs):
"""
All hyperprameter goes here.
:param graph: graph dataset
:param fil: filtration function
:param norm: normalize or not
:param permute: whether permute dgm
:param ss: both sublevel and superlevel or not
:param epd: include extended persistence or not
:param n_cv: number of cross validation
:return:
"""
global gs
print('kwargs', feat_kwargs)
label_flag = dgms_dir_test(fil=fil, fil_d='sub', norm=norm, graph=graph)[1]
# gs, labels = load_graphs(dataset=graph, labels_only=label_flag) # step 1
gs, labels = load_tugraphs(graph, labels_only=True)
# parallel
subdgms = gs2dgms_parallel(n_jobs=-1,
fil=fil,
fil_d='sub',
norm=norm,
graph=graph)
supdgms = gs2dgms_parallel(n_jobs=-1,
fil=fil,
fil_d='sup',
norm=norm,
graph=graph)
epddgms = gs2dgms_parallel(n_jobs=-1,
fil=fil,
one_hom=True,
norm=norm,
graph=graph)
dgms = combine_dgms(subdgms, supdgms, epddgms, ss=ss, epd=epd, flip=flip)
dgms = permute_dgms(dgms, permute_flag=permute, permute_ratio=0.5)
dgms_summary(dgms)
swdgms = dgms2swdgms(dgms)
if feat == 'sw':
print(feat_kwargs)
k, _ = sw_parallel(swdgms,
swdgms,
parallel_flag=True,
kernel_type='sw',
**feat_kwargs)
clf = classifier(labels, labels, method='svm', n_cv=n_cv, kernel=k)
clf.svm_kernel_(n_splits=10)
print(clf.stat)
return clf.stat
elif feat == 'pi':
params = {
'bandwidth': 1.0,
'weight': (1, 1),
'im_range': [0, 1, 0, 1],
'resolution': [5, 5]
}
images = merge_dgms(subdgms,
supdgms,
epddgms,
vectype='pi',
ss=ss,
epd=epd,
**params)
clf = classifier(images, labels, method='svm', n_cv=n_cv)
clf.svm(n_splits=10)
return clf.stat
elif feat == 'pss':
k, _ = sw_parallel(swdgms,
swdgms,
parallel_flag=False,
kernel_type='pss',
**feat_kwargs)
print(k.shape, k, np.max(k))
clf = classifier(labels, labels, method='svm', n_cv=n_cv, kernel=k)
clf.svm_kernel_(n_splits=10)
print(clf.stat)
return clf.stat
elif feat == 'wg':
k, _ = sw_parallel(swdgms,
swdgms,
parallel_flag=True,
kernel_type='wg',
**feat_kwargs)
print(k.shape)
clf = classifier(labels, labels, method='svm', n_cv=n_cv, kernel=k)
clf.svm_kernel_(n_splits=10)
print(clf.stat)
return clf.stat
elif feat == 'pdvector':
pass
# viz fv value
# val = dict(nx.get_node_attributes(gs[i], 'fv')).values()
# plt.plot(val)
# plt.title('q: %s, i: %s'%(q, i))
# plt.show()
# sys.exit()
print('Finish computing lapfeat')
dgms = alldgms(gs,
radius=float('inf'),
dataset='',
recompute_flag=True,
method='serial',
n=2 * n,
zigzag=zigzag) # compute dgms in parallel
print('Finish computing dgms')
swdgms = dgms2swdgms(dgms)
feat_kwargs = {'n_directions': 10, 'bw': 1}
sw_kernel, _ = sw_parallel(swdgms,
swdgms,
kernel_type='sw',
parallel_flag=True,
**feat_kwargs)
clf = classifier(np.zeros((len(labels), 10)),
labels,
method=None,
kernel=sw_kernel)
print(clf.svm_kernel_())
print(p, q, edge_kwargs)
gs2 = sbms(n=n, n1=75, n2=75, p=p, q=q)
gs = gs2 + gs1
labels = [1] * n + [2] * n
# node filtration is fiedler vector.
# edge_kwargs = {'h': 0.3, 'edgefunc': 'edge_prob'}
# for i in range(len(gs)):
# g = gs[i]
# lp = LaplacianEigenmaps(d=1)
# lp.learn_embedding(g, weight='weight')
# lapfeat = lp.get_embedding()
# gs[i] = fil_strategy(g, lapfeat, method=fil_method, viz_flag=False, **edge_kwargs)
# print('Finish computing lapfeat')
# compute diagrams
dgms = gs2dgms(gs, fil='deg', fil_d='sub', norm=True)
# compute kernel and evaluation
swdgms = dgms2swdgms(dgms)
kwargs = {'bw': 1, 'n_directions': 10}
sw_kernel, _ = sw_parallel(swdgms,
swdgms,
kernel_type='sw',
parallel_flag=False,
**kwargs)
clf = classifier(np.zeros((len(labels), 10)),
labels,
method=None,
kernel=sw_kernel)
print(clf.svm_kernel_())