def test_sharing():
data = Frame(create_test_data())
f1 = FrameRef(data, index=toindex([0, 1, 2, 3]))
f2 = FrameRef(data, index=toindex([2, 3, 4, 5, 6]))
# test read
for k, v in f1.items():
assert U.allclose(data[k].data[0:4], v)
for k, v in f2.items():
assert U.allclose(data[k].data[2:7], v)
f2_a1 = f2['a1'].data
# test write
# update own ref should not been seen by the other.
f1[Index(th.tensor([0, 1]))] = {
'a1': th.zeros([2, D]),
'a2': th.zeros([2, D]),
'a3': th.zeros([2, D]),
}
assert U.allclose(f2['a1'], f2_a1)
# update shared space should been seen by the other.
f1[Index(th.tensor([2, 3]))] = {
'a1': th.ones([2, D]),
'a2': th.ones([2, D]),
'a3': th.ones([2, D]),
}
f2_a1[0:2] = th.ones([2, D])
assert U.allclose(f2['a1'], f2_a1)
def test_slicing():
data = Frame(create_test_data(grad=True))
f1 = FrameRef(data, index=toindex(slice(1, 5)))
f2 = FrameRef(data, index=toindex(slice(3, 8)))
# test read
for k, v in f1.items():
assert U.allclose(data[k].data[1:5], v)
f2_a1 = f2['a1'].data
# test write
f1[Index(th.tensor([0, 1]))] = {
'a1': th.zeros([2, D]),
'a2': th.zeros([2, D]),
'a3': th.zeros([2, D]),
}
assert U.allclose(f2['a1'], f2_a1)
f1[Index(th.tensor([2, 3]))] = {
'a1': th.ones([2, D]),
'a2': th.ones([2, D]),
'a3': th.ones([2, D]),
}
f2_a1[toindex(slice(0, 2))] = 1
assert U.allclose(f2['a1'], f2_a1)
f1[toindex(slice(2, 4))] = {
'a1': th.zeros([2, D]),
'a2': th.zeros([2, D]),
'a3': th.zeros([2, D]),
}
f2_a1[toindex(slice(0, 2))] = 0
assert U.allclose(f2['a1'], f2_a1)
def test_slicing():
data = Frame(create_test_data(grad=True))
f1 = FrameRef(data, index=toindex(slice(1, 5)))
f2 = FrameRef(data, index=toindex(slice(3, 8)))
# test read
for k, v in f1.items():
assert F.allclose(F.narrow_row(data[k].data, 1, 5), v)
f2_a1 = f2['a1'] # is a tensor
# test write
f1[Index(F.tensor([0, 1]))] = {
'a1': F.zeros([2, D]),
'a2': F.zeros([2, D]),
'a3': F.zeros([2, D]),
}
assert F.allclose(f2['a1'], f2_a1)
f1[Index(F.tensor([2, 3]))] = {
'a1': F.ones([2, D]),
'a2': F.ones([2, D]),
'a3': F.ones([2, D]),
}
F.narrow_row_set(f2_a1, 0, 2, 1)
assert F.allclose(f2['a1'], f2_a1)
f1[toindex(slice(2, 4))] = {
'a1': F.zeros([2, D]),
'a2': F.zeros([2, D]),
'a3': F.zeros([2, D]),
}
F.narrow_row_set(f2_a1, 0, 2, 0)
assert F.allclose(f2['a1'], f2_a1)
def test_sharing():
data = Frame(create_test_data())
f1 = FrameRef(data, index=toindex([0, 1, 2, 3]))
f2 = FrameRef(data, index=toindex([2, 3, 4, 5, 6]))
# test read
for k, v in f1.items():
assert F.allclose(F.narrow_row(data[k].data, 0, 4), v)
for k, v in f2.items():
assert F.allclose(F.narrow_row(data[k].data, 2, 7), v)
f2_a1 = f2['a1']
# test write
# update own ref should not been seen by the other.
f1[Index(F.tensor([0, 1]))] = {
'a1': F.zeros([2, D]),
'a2': F.zeros([2, D]),
'a3': F.zeros([2, D]),
}
assert F.allclose(f2['a1'], f2_a1)
# update shared space should been seen by the other.
f1[Index(F.tensor([2, 3]))] = {
'a1': F.ones([2, D]),
'a2': F.ones([2, D]),
'a3': F.ones([2, D]),
}
F.narrow_row_set(f2_a1, 0, 2, F.ones([2, D]))
assert F.allclose(f2['a1'], f2_a1)
def test_row1():
# test row getter/setter
data = create_test_data()
f = FrameRef(Frame(data))
# getter
# test non-duplicate keys
rowid = Index(F.tensor([0, 2]))
rows = f[rowid]
for k, v in rows.items():
assert tuple(F.shape(v)) == (len(rowid), D)
assert F.allclose(v, F.gather_row(data[k], F.tensor(rowid.tousertensor())))
# test duplicate keys
rowid = Index(F.tensor([8, 2, 2, 1]))
rows = f[rowid]
for k, v in rows.items():
assert tuple(F.shape(v)) == (len(rowid), D)
assert F.allclose(v, F.gather_row(data[k], F.tensor(rowid.tousertensor())))
# setter
rowid = Index(F.tensor([0, 2, 4]))
vals = {'a1' : F.zeros((len(rowid), D)),
'a2' : F.zeros((len(rowid), D)),
'a3' : F.zeros((len(rowid), D)),
}
f[rowid] = vals
for k, v in f[rowid].items():
assert F.allclose(v, F.zeros((len(rowid), D)))
# setting rows with new column should raise error with error initializer
f.set_initializer(lambda shape, dtype : assert_(False))
def failed_update_rows():
vals['a4'] = F.ones((len(rowid), D))
f[rowid] = vals
assert check_fail(failed_update_rows)
def test_row4():
# test updating row with empty frame but has preset num_rows
f = FrameRef(Frame(num_rows=5))
rowid = Index(th.tensor([0, 2, 4]))
f[rowid] = {'h': th.ones((3, 2))}
ans = th.zeros((5, 2))
ans[th.tensor([0, 2, 4])] = th.ones((3, 2))
assert U.allclose(f['h'], ans)
def test_row2():
# test row getter/setter autograd compatibility
data = create_test_data(grad=True)
f = FrameRef(Frame(data))
with F.record_grad():
# getter
c1 = f['a1']
# test non-duplicate keys
rowid = Index(F.tensor([0, 2]))
rows = f[rowid]
y = rows['a1']
F.backward(y, F.ones((len(rowid), D)))
assert F.allclose(
F.grad(c1)[:, 0], F.tensor([1., 0., 1., 0., 0., 0., 0., 0., 0., 0.]))
f['a1'] = F.attach_grad(f['a1'])
with F.record_grad():
c1 = f['a1']
# test duplicate keys
rowid = Index(F.tensor([8, 2, 2, 1]))
rows = f[rowid]
y = rows['a1']
F.backward(y, F.ones((len(rowid), D)))
assert F.allclose(
F.grad(c1)[:, 0], F.tensor([0., 1., 2., 0., 0., 0., 0., 0., 1., 0.]))
f['a1'] = F.attach_grad(f['a1'])
with F.record_grad():
# setter
c1 = f['a1']
rowid = Index(F.tensor([0, 2, 4]))
vals = {
'a1': F.attach_grad(F.zeros((len(rowid), D))),
'a2': F.attach_grad(F.zeros((len(rowid), D))),
'a3': F.attach_grad(F.zeros((len(rowid), D))),
}
f[rowid] = vals
c11 = f['a1']
F.backward(c11, F.ones((N, D)))
assert F.allclose(
F.grad(c1)[:, 0], F.tensor([0., 1., 0., 1., 0., 1., 1., 1., 1., 1.]))
assert F.allclose(F.grad(vals['a1']), F.ones((len(rowid), D)))
assert F.is_no_grad(vals['a2'])
def test_add_rows():
data = Frame()
f1 = FrameRef(data)
f1.add_rows(4)
x = th.randn(1, 4)
f1[Index(th.tensor([0]))] = {'x': x}
ans = th.cat([x, th.zeros(3, 4)])
assert U.allclose(f1['x'], ans)
f1.add_rows(4)
f1[toindex(slice(4, 8))] = {'x': th.ones(4, 4), 'y': th.ones(4, 5)}
ans = th.cat([ans, th.ones(4, 4)])
assert U.allclose(f1['x'], ans)
ans = th.cat([th.zeros(4, 5), th.ones(4, 5)])
assert U.allclose(f1['y'], ans)
def test_add_rows():
data = Frame()
f1 = FrameRef(data)
f1.add_rows(4)
x = F.randn((1, 4))
f1[Index(F.tensor([0]))] = {'x': x}
ans = F.cat([x, F.zeros((3, 4))], 0)
assert F.allclose(f1['x'], ans)
f1.add_rows(4)
f1[toindex(slice(4, 8))] = {'x': F.ones((4, 4)), 'y': F.ones((4, 5))}
ans = F.cat([ans, F.ones((4, 4))], 0)
assert F.allclose(f1['x'], ans)
ans = F.cat([F.zeros((4, 5)), F.ones((4, 5))], 0)
assert F.allclose(f1['y'], ans)
def test_row2():
# test row getter/setter autograd compatibility
data = create_test_data(grad=True)
f = FrameRef(Frame(data))
# getter
c1 = f['a1']
# test non-duplicate keys
rowid = Index(th.tensor([0, 2]))
rows = f[rowid]
rows['a1'].backward(th.ones((len(rowid), D)))
assert U.allclose(c1.grad[:, 0],
th.tensor([1., 0., 1., 0., 0., 0., 0., 0., 0., 0.]))
c1.grad.data.zero_()
# test duplicate keys
rowid = Index(th.tensor([8, 2, 2, 1]))
rows = f[rowid]
rows['a1'].backward(th.ones((len(rowid), D)))
assert U.allclose(c1.grad[:, 0],
th.tensor([0., 1., 2., 0., 0., 0., 0., 0., 1., 0.]))
c1.grad.data.zero_()
# setter
c1 = f['a1']
rowid = Index(th.tensor([0, 2, 4]))
vals = {
'a1': Variable(th.zeros((len(rowid), D)), requires_grad=True),
'a2': Variable(th.zeros((len(rowid), D)), requires_grad=True),
'a3': Variable(th.zeros((len(rowid), D)), requires_grad=True),
}
f[rowid] = vals
c11 = f['a1']
c11.backward(th.ones((N, D)))
assert U.allclose(c1.grad[:, 0],
th.tensor([0., 1., 0., 1., 0., 1., 1., 1., 1., 1.]))
assert U.allclose(vals['a1'].grad, th.ones((len(rowid), D)))
assert vals['a2'].grad is None
def __init__(self, name, self_loop, device, degree_as_nlabel=False, line_graph=False):
"""Initialize the dataset."""
self.name = name # MUTAG
self.ds_name = 'nig'
self.extract_dir = self._download()
self.file = self._file_path()
self.device = device
self.self_loop = self_loop
self.line_graph = line_graph
self.graphs = []
self.labels = []
# relabel
self.glabel_dict = {}
self.nlabel_dict = {}
self.elabel_dict = {}
self.ndegree_dict = {}
# global num
self.N = 0 # total graphs number
self.n = 0 # total nodes number
self.m = 0 # total edges number
# global num of classes
self.gclasses = 0
self.nclasses = 0
self.eclasses = 0
self.dim_nfeats = 0
# flags
self.degree_as_nlabel = degree_as_nlabel
self.nattrs_flag = False
self.nlabels_flag = False
self.verbosity = False
# calc all values
self._load()
self._deg = []
self._edges = []
self.in_degrees = lambda g: g.in_degrees(
Index(np.arange(0, g.number_of_nodes()))).unsqueeze(1).float()
self._adj = []
if self.line_graph:
self._lgs = []
self._lgs_deg = []
self._lgs_edges = []
self._pm = []
self._pd = []
self._preprocess()
if self.degree_as_nlabel:
self._deg_as_feature()
elif self.name == 'PROTEINS' or self.name == 'PTC' or self.name == 'MUTAG':
self._attr_as_feature()
def extract_deg_adj(graph_list):
in_degrees = lambda g: g.in_degrees(
Index(np.arange(0, g.number_of_nodes()))).unsqueeze(1).float()
degs = [in_degrees(g) for g in graph_list]
adjs = [g.adjacency_matrix() for g in graph_list]
return degs, adjs