def g2dgm(i,
g=None,
fil='deg',
fil_d='sub',
norm=False,
one_hom=False,
debug_flag=False,
**kwargs):
"""
a wrapper of node_fil_ for parallel computing dgms.
:param g:
:param fil:
:param fil_d: sub/super
:param norm: False by default
:param one_hom: False by default
:param debug_flag: False by default
:param kwargs:
:return:
"""
# assert 'gs' in globals().keys()
# g = gs[i].copy()
if debug_flag:
print('processing %s-th graph where fil is %s and fil_d is %s' %
(i, fil, fil_d))
components = component_graphs(g)
dgm = d.Diagram([])
for component in components:
if fil in ['jaccard', 'ricci', 'edge_p']:
tmp_dgm = edge_fil_(component,
fil=fil,
fil_d=fil_d,
norm=norm,
one_hom=one_hom,
**kwargs)
print_dgm(tmp_dgm)
else:
tmp_dgm = node_fil_(component,
fil=fil,
fil_d=fil_d,
norm=norm,
one_hom=one_hom,
**kwargs)
dgm = add_dgm(dgm, tmp_dgm)
dgm = dgm_filter(dgm)
dgm = dgm_filter(dgm) # handle the case when comonents is empty
return dgm
def gs2dgms(gs,
fil='deg',
fil_d='sub',
norm=False,
one_hom=False,
debug_flag=False,
**kwargs):
"""
serial computing dgms
:param gs: a list of raw nx graphs(no function value)
:param fil: filtration(deg, ricci)
:param fil_d : sub or sup
:param norm: whether normalize or not
:param one_hom: one homology or not
:param debug_flag: False by default
:return: dgms: a list of dgm
"""
dgms = []
for i in range(len(gs)):
if debug_flag:
print(
f'process {i}-th graph({len(gs[i])}/{len(nx.edges(gs[i]))}) where one_hom is {one_hom} fil is {fil} and fil_d is {fil_d}'
)
components = component_graphs(gs[i]) # todo chnage back to 4
# components4 = component_graphs(gs[i], threshold=4) #todo
# components5 = component_graphs(gs[i], threshold=5) #todo
# print(f'threshold 4/5 has {len(components4)}/{len(components5)}')
if len(components) == 0: return d.Diagram([[0, 0]])
dgm = d.Diagram([])
for component in components:
tmp_dgm = node_fil_(g=component,
fil=fil,
fil_d=fil_d,
norm=norm,
one_hom=one_hom,
**kwargs)
dgm = add_dgm(dgm, tmp_dgm)
dgm = dgm_filter(dgm)
# TODO: implement edge_fil_
assert len(dgm) > 0
dgms.append(dgm)
return dgms
def load_clfdgm(idx=1, ntda=False):
dgm = d.Diagram([[np.random.random(), 1]])
for fil_d in ['sub']: #['sub', 'sup', 'epd']:
dir = os.path.join(DIRECT, graph, fil, fil_d, 'norm_True', '')
if ntda:
dir = os.path.join(DIRECT, graph, 'ntda_True', fil, fil_d,
'norm_True', '')
f = dir + str(idx) + '.csv'
try:
tmp_dgm = load_dgm(dir, filename=f)
except FileNotFoundError:
print(
f'{f} of size {all_dataset[idx].pos.shape[0]}/{all_dataset[idx].face.shape[1]} not found. Added a dummy one'
)
tmp_dgm = d.Diagram([[0, 0]])
dgm = add_dgm(dgm, tmp_dgm)
# print(f'finsih {idx}-th diagram')
return dgm
def gs2dgms(gs,
fil='deg',
fil_d='sub',
norm=False,
one_hom=False,
debug_flag=False,
**kwargs):
"""
serial computing dgms
:param gs: a list of nx graphs
:param fil: filtration(deg, ricci)
:param fil_d : sub or sup
:param norm: whether normalize or not
:param one_hom: one homology or not
:param debug_flag: False by default
:return: dgms: a list of dgm
"""
dgms = []
for i in range(len(gs)):
if debug_flag:
print('processing %s-th graph where fil is %s and fil_d is %s' %
(i, fil, fil_d))
components = component_graphs(gs[i])
if len(components) == 0: return d.Diagram([[0, 0]])
dgm = d.Diagram([])
for component in components:
tmp_dgm = node_fil_(component,
fil=fil,
fil_d=fil_d,
norm=norm,
one_hom=one_hom,
**kwargs)
dgm = add_dgm(dgm, tmp_dgm)
dgm = dgm_filter(dgm)
assert len(dgm) > 0
dgms.append(dgm)
return dgms
def g2dgm(i,
g=None,
fil='deg',
fil_d='sub',
norm=False,
one_hom=False,
debug_flag=False,
**kwargs):
"""
a wrapper of node_fil_ for parallel computing dgms.
:param g:
:param fil:
:param fil_d:
:param norm: False by default
:param one_hom: False by default
:param debug_flag: False by default
:param kwargs:
:return:
"""
# assert 'gs' in globals().keys()
# g = gs[i].copy()
if len(g) > 60000:
return d.Diagram([[0, 0]]) # todo better handling
if debug_flag:
print('in g2dm', kwargs)
i += kwargs.get('a', 0)
print(
f'processing {i}-th graph({len(g)}/{len(g.edges)}) where fil is {fil} and fil_d is {fil_d} and one_hom is {one_hom}'
)
if kwargs.get('write', None) == True: # 一个后门
fil_d_ = 'epd' if one_hom == True else fil_d
# if check_single_dgm(graph = 'mn'+version, fil = fil, fil_d=fil_d_, norm=norm, idx=i): return
components = component_graphs(g)
dgm = d.Diagram([])
for component in components:
if fil in ['jaccard']:
tmp_dgm = edge_fil_(component,
fil=fil,
fil_d=fil_d,
norm=norm,
one_hom=one_hom,
**kwargs)
print_dgm(tmp_dgm)
else:
tmp_dgm = node_fil_(g=component,
fil=fil,
fil_d=fil_d,
norm=norm,
one_hom=one_hom,
**kwargs)
dgm = add_dgm(dgm, tmp_dgm)
dgm = dgm_filter(dgm)
dgm = dgm_filter(dgm) # handle the case when comonents is empty
if kwargs.get('write', None) == True: # 一个后门
if one_hom == True: fil_d = 'epd'
fil_save = fil + '_nbr' + str(args.nbr_size) + '_exp' + str(args.exp)
ntda = 'ntda_' + str(kwargs.get('ntda', 'NotFound'))
dir = os.path.join(
'/home/cai.507/anaconda3/lib/python3.6/site-packages/save_dgms/',
'mn' + version, ntda, fil_save, fil_d, 'norm_' + str(norm), '')
export_dgm(dgm, dir=dir, filename=str(i) + '.csv', print_flag=True)
return dgm