def agreement(ci, buffsz=None):
'''
Takes as input a set of vertex partitions CI of
dimensions [vertex x partition]. Each column in CI contains the
assignments of each vertex to a class/community/module. This function
aggregates the partitions in CI into a square [vertex x vertex]
agreement matrix D, whose elements indicate the number of times any two
vertices were assigned to the same class.
In the case that the number of nodes and partitions in CI is large
(greater than ~1000 nodes or greater than ~1000 partitions), the script
can be made faster by computing D in pieces. The optional input BUFFSZ
determines the size of each piece. Trial and error has found that
BUFFSZ ~ 150 works well.
Parameters
----------
ci : MxN np.ndarray
set of M (possibly degenerate) partitions of N nodes
buffsz : int | None
sets buffer size. If not specified, defaults to 1000
Returns
-------
D : NxN np.ndarray
agreement matrix
'''
ci = np.array(ci)
m, n = ci.shape
if buffsz is None:
buffsz = 1000
if m <= buffsz:
ind = dummyvar(ci)
D = np.dot(ind, ind.T)
else:
a = np.arange(0, m, buffsz)
b = np.arange(buffsz, m, buffsz)
if len(a) != len(b):
b = np.append(b, m)
D = np.zeros((n,))
for i, j in zip(a, b):
y = ci[:, i:j + 1]
ind = dummyvar(y)
D += np.dot(ind, ind.T)
np.fill_diagonal(D, 0)
return D
def agreement(ci, buffsz=None):
'''
Takes as input a set of vertex partitions CI of
dimensions [vertex x partition]. Each column in CI contains the
assignments of each vertex to a class/community/module. This function
aggregates the partitions in CI into a square [vertex x vertex]
agreement matrix D, whose elements indicate the number of times any two
vertices were assigned to the same class.
In the case that the number of nodes and partitions in CI is large
(greater than ~1000 nodes or greater than ~1000 partitions), the script
can be made faster by computing D in pieces. The optional input BUFFSZ
determines the size of each piece. Trial and error has found that
BUFFSZ ~ 150 works well.
Parameters
----------
ci : MxN np.ndarray
set of M (possibly degenerate) partitions of N nodes
buffsz : int | None
sets buffer size. If not specified, defaults to 1000
Returns
-------
D : NxN np.ndarray
agreement matrix
'''
ci = np.array(ci)
m, n = ci.shape
if buffsz is None:
buffsz = 1000
if m <= buffsz:
ind = dummyvar(ci)
D = np.dot(ind, ind.T)
else:
a = np.arange(0, m, buffsz)
b = np.arange(buffsz, m, buffsz)
if len(a) != len(b):
b = np.append(b, m)
D = np.zeros((n, ))
for i, j in zip(a, b):
y = ci[:, i:j + 1]
ind = dummyvar(y)
D += np.dot(ind, ind.T)
np.fill_diagonal(D, 0)
return D
def agreement_weighted(ci, wts):
'''
D = AGREEMENT_WEIGHTED(CI,WTS) is identical to AGREEMENT, with the
exception that each partitions contribution is weighted according to
the corresponding scalar value stored in the vector WTS. As an example,
suppose CI contained partitions obtained using some heuristic for
maximizing modularity. A possible choice for WTS might be the Q metric
(Newman's modularity score). Such a choice would add more weight to
higher modularity partitions.
NOTE: Unlike AGREEMENT, this script does not have the input argument
BUFFSZ.
Parameters
----------
ci : MxN np.ndarray
set of M (possibly degenerate) partitions of N nodes
wts : Mx1 np.ndarray
relative weight of each partition
Returns
-------
D : NxN np.ndarray
weighted agreement matrix
'''
ci = np.array(ci)
m, n = ci.shape
wts = np.array(wts) / np.sum(wts)
D = np.zeros((n, n))
for i in range(m):
d = dummyvar(ci[i, :].reshape(1, n))
D += np.dot(d, d.T) * wts[i]
return D
def agreement_weighted(ci, wts):
'''
D = AGREEMENT_WEIGHTED(CI,WTS) is identical to AGREEMENT, with the
exception that each partitions contribution is weighted according to
the corresponding scalar value stored in the vector WTS. As an example,
suppose CI contained partitions obtained using some heuristic for
maximizing modularity. A possible choice for WTS might be the Q metric
(Newman's modularity score). Such a choice would add more weight to
higher modularity partitions.
NOTE: Unlike AGREEMENT, this script does not have the input argument
BUFFSZ.
Parameters
----------
ci : MxN np.ndarray
set of M (possibly degenerate) partitions of N nodes
wts : Mx1 np.ndarray
relative weight of each partition
Returns
-------
D : NxN np.ndarray
weighted agreement matrix
'''
ci = np.array(ci)
m, n = ci.shape
wts = np.array(wts) / np.sum(wts)
D = np.zeros((n, n))
for i in range(m):
d = dummyvar(ci[i, :].reshape(1, n))
D += np.dot(d, d.T) * wts[i]
return D