def testcluster_query(lamBda=0.00001, ncluster=2, kx=65, rate=0.001, func=sign,
query_func = query.queryZero, queryNum=50):
S = zeros([n_total, n_total])
r_index, l_index = randindex(n_total, rate, -1)
S[r_index, l_index] = groundTruth[r_index, l_index]
# function varctorization
sign = func
sign = np.vectorize(sign)
S = sign(S + S.T)
S = sparse.csr_matrix(S)
#
U, D = idc.inductive(X, S, kx, ncluster, lamBda, 50)
#
# active query
### ADD: how to calculate the estimated similarity matrix?
est_S = U.dot(D).dot(U.T)
#queryNum = math.floor(query_rate * n_total)
seed = -1
r_query, l_query = query_func(est_S, queryNum, r_index, l_index, seed)
S = zeros([n_total, n_total])
S[r_index + r_query, l_index + l_query] = groundTruth[r_index + r_query, l_index + l_query ]
# function varctorization
sign = func
sign = np.vectorize(sign)
S = sign((S + S.T))
S = sparse.csr_matrix(S)
#
U, D = idc.inductive(X, S, kx, ncluster, lamBda, 50)
# kmeans
Xresult = matrix(U[:, 0:ncluster])
Xresult = Xresult / (matlib.repmat(np.sqrt(np.square(Xresult).sum(axis=1)),
1,
ncluster) * 1.0)
label = KMeans(n_clusters=ncluster).fit_predict(Xresult)
label = array(label)
predictA = - ones([n_total, n_total])
#
#for i in range(ncluster):
# pos = np.where(label == i)[0]
# for j in pos:
# for k in pos:
# predictA[j, k] = 1
for i in range(n_total):
for j in range(n_total):
if label[i] == label[j]:
predictA[i, j] = 1
#
accbias = sum(predictA != groundTruth).sum() / float(np.product(groundTruth.shape))
print('sample rate: ', rate, " ", "query rate:", queryNum, "err: ", accbias)
return accbias
def testcluster(lamBda=0.00001, ncluster=2, kx=50, rate=0.001, func=sign):
S = zeros([n_total, n_total])
r_index, l_index = randindex(n_total, rate, -1)
S[r_index, l_index] = groundTruth[r_index, l_index]
# function varctorization
sign = func
sign = np.vectorize(sign)
S = sign(S + S.T)
S = sparse.csr_matrix(S)
#
U, D = idc.inductive(X, S, kx, ncluster, lamBda, 50)
#
Xresult = matrix(U[:, 0:ncluster])
Xresult = Xresult / (matlib.repmat(np.sqrt(np.square(Xresult).sum(axis=1)),
1,
ncluster) * 1.0)
label = KMeans(n_clusters=ncluster).fit_predict(Xresult)
label = array(label)
predictA = - ones([n_total, n_total])
#
for i in range(ncluster):
pos = np.where(label == i)[0]
for j in pos:
for k in pos:
predictA[j, k] = 1
#
accbias = sum(predictA != groundTruth).sum() / float(np.product(groundTruth.shape))
print 'sample rate: ', rate, " ", "err: ", accbias
