def test8():
n = 500
r = 50
nt = 100
#rcross = 50
d = 50
hubs = 1
verbose = False
num_eval = 100
#X, Y = createFakeData(n, r, nt, rcross)
#X, Y = createFakeData2(n, r, nt, hubs)
X,Y = np.load('t8data.npy')
# import IPython
# IPython.embed()
init_pt = np.nonzero(Y)[0][0]
ker = True
pi = sum(Y)/len(Y)
print "Constructing the similarity matrix:"
A = X.T.dot(X)
t1 = time.time()
if ker:
print "Performing Kernel AS"
f1,h1,s1,fs1 = AS.kernel_AS (X, Y, pi=pi, num_eval=num_eval, init_pt=init_pt, verbose=verbose,all_fs=True)
t2 = time.time()
#print "Performing Eigen decmop"
#Xe, b, w, deg = eigenmap(A, d)
#t3 = time.time()
if ker:
print "Performing Naive Shari AS"
f2,h2,s2,fs2 = AS.shari_activesearch_probs_naive(A, labels=Y, pi=pi, w0=None, eta=None, num_eval=num_eval, init_pt=init_pt, verbose=verbose, all_fs=True)
#f2,h2,s2,fs2 = AS.lreg_AS (Xe, deg, d, alpha=0.0, labels=Y, options={'num_eval':num_eval,'pi':pi,'n_conncomp':b}, verbose=verbose)
t4 = time.time()
print "Time taken for kernel:", t2-t1
#print "Time taken for eigenmap + computing X.T*X:", t3-t2
print "Time taken for Shari's method (naive):", t4-t2
if ker:
print "h_kernel: %i/%i"%(h1[-1],num_eval)
print "h_lreg: %i/%i"%(h2[-1],num_eval)
import IPython
IPython.embed()
def test9():
verbose = True
datadir = osp.join(os.getenv('HOME'), 'Research/Data/ActiveSearch/sibi_matrices')
tsfile = osp.join(datadir, 'timestamps.csv')
tffile = osp.join(datadir, 'tfidf_pretranspose.txt')
contactsfile = osp.join(datadir, 'email_person_bitarray.txt')
#ts_data = ef.load_timestamps (tsfile)
Xfull = load_sparse_csr('Xfull1.npz')
n = 5000
r = 2000
nt = 15#int(0.1*n)
num_eval = nt*2
# getting rid of features which are zero for all these elements
X = np.array((Xfull[:,:n]).todense())
X = X[np.nonzero(X.sum(axis=1))[0],:]
X = X[:,np.nonzero(X.sum(axis=0))[1]]
# import IPython
# IPython.embed()
X = X[:r,:]
X = X[np.nonzero(X.sum(axis=1))[0],:]
X = X[:,np.nonzero(X.sum(axis=0))[1]]
# import IPython
# IPython.embed()
r,n = X.shape
d = 20
nt = 10#int(0.1*n)
num_eval = 15#nt*2
Y = np.array([1]*nt + [0]*(n-nt), dtype=int)
pi = nt*1.0/n
init_pt = 100
A = X.T.dot(X)
import IPython
IPython.embed()
t1 = time.time()
print "Kernel method"
#f1,h1,s1,fs1,dt = AS.kernel_AS (X, Y, pi=pi, num_eval=num_eval, init_pt=init_pt, verbose=verbose,all_fs=True,tinv=True)
t2 = time.time()
print "Eigen map"
#Xe, b, w, deg = eigenmap(A, d)
#np.save('eigenstuff',[Xe, b, w, deg])
Xe, b, w, deg = np.load('eigenstuff.npy')
# import IPython
# IPython.embed()
t3 = time.time()
print "Shari method"
#f2,h2,s2 = AS.lreg_AS (Xe, deg, d, alpha=0.0, labels=Y, options={'num_eval':num_eval,'pi':pi,'n_conncomp':b,'init_pt':init_pt}, verbose=verbose)
t4 = time.time()
f3,h3,s3,fs3 = AS.shari_activesearch_probs_naive(A, labels=Y, pi=pi, w0=None, eta=None, num_eval=num_eval, init_pt=init_pt, verbose=verbose, all_fs=True)
print "Time taken for kernel:", t2-t1
#print "Time taken for inverse:", dt
print "Time taken for eigen decomp:", t3 - t2
print "Time taken for lreg:", t4-t3
#f1 = np.squeeze(f1)
import IPython
IPython.embed()
