def dice_sim_matrix_po(X):
sumX = pnp.sum(X, axis = 1)
sumX = pnp.reshape(pnp.tile(sumX, len(X)), (len(X), len(X)))
sumX = sumX + pnp.transpose(sumX)
cmpX = pnp.zeros((len(X), len(X)))
for i in range(len(X)):
cmpX[i] = pnp.sum(X * pnp.reshape(pnp.tile(X[i], len(X)), (len(X), len(X[0]))), axis = 1)
result = 2 * cmpX * myreciprocal(sumX * sumX, 0.0)
result = sumX * result
return result
def R2(x, y):
if (np.size(x) != np.size(y)):
print('Warning: input vectors for R2 must be same length!')
return -100.0
else:
avx = pnp.mean(x)
avy = pnp.mean(y)
num = pnp.sum((x - avx) * (y - avy))
num = num * num
denom = pnp.sum((x - avx) * (x - avx)) * pnp.sum((y - avy) * (y - avy))
res = num * pp.reciprocal(denom)
return res
def fdot(A, B):
# flatten dot. Regard A and B as long vector
A = pp.farr(A)
B = pp.farr(B)
A = A * (1.0/A.shape[0])
B = B * (1.0/B.shape[0])
return pnp.sum(A * B)
def jaccard_sim_po(mat):
intersect = pnp.dot(mat, pnp.transpose(mat))
union = pnp.sum(mat, axis = 1)
union = pnp.reshape(pnp.tile(union, len(mat)), (len(mat), len(mat)))
union = union + pnp.transpose(union) - intersect + 0.0
sim = intersect * myreciprocal(union,0.0)
for i in range(sim.shape[0]):
sim[i, i] = pp.sfixed(1.0)
return sim
def RWR_po(A, maxiter, restartProb):
n = len(A)
# normalize the adjacency matrix
A = A + 0.0
tmp_var = pnp.sum(A,axis=0)
tmp_var = myreciprocal(tmp_var,0.0)
tmp_var = pnp.tile(tmp_var,(A.shape[0],1))
P = A * tmp_var
# Personalized PageRank
restart = pnp.eye(n) * restartProb
Q = pnp.eye(n)
for i in range(maxiter):
Q = (1 - restartProb) * pnp.dot(P, Q) + restart
return Q