def test_nan ():
import cPickle as pickle
import os, os.path as osp
with open(osp.join(os.getenv('HOME'), 'Research/Data/ActiveSearch/ben/forumthreadsSparseMatrix.pkl'),'r') as fl:
X = pickle.load(fl)
X = X.T
# import IPython
# IPython.embed()
X = X[np.squeeze(np.array(np.nonzero(X.sum(axis=1))[0])),:]
X = X[:,np.squeeze(np.array(np.nonzero(X.sum(axis=0))[1]))]
X = X[np.squeeze(np.array(np.nonzero(X.sum(axis=1))[0])),:]
X = X[:,np.squeeze(np.array(np.nonzero(X.sum(axis=0))[1]))]
print X.shape
r,n = X.shape
nt = int(0.05*n)
num_eval = 50
Y = np.array([1]*nt + [0]*(n-nt), dtype=int)
nr.shuffle(Y)
pi = sum(Y)/len(Y)
init_pt = 537
# import IPython
# IPython.embed()
# A = np.array((X.T.dot(X)).todense())
t1 = time.time()
verbose = True
prms = ASI.Parameters(pi=pi,sparse=True, verbose=verbose)
kAS = ASI.kernelAS(prms)
kAS.initialize(X)
init_lbls = {init_pt:1}
kAS.firstMessage(init_pt)
# fs2 = [kAS.f]
import IPython
IPython.embed()
for i in range(num_eval):
idx1 = kAS.getNextMessage()
kAS.setLabelCurrent(Y[idx1])
init_lbls[idx1] = Y[idx1]
import IPython
IPython.embed()
def test_CC ():
nac = np.allclose
n = 1000
r = 100
nt = 200
rcross = 0
X,Y = createFakeData3(n, r, nt, rcross)
num_eval = 50
pi = sum(Y)/len(Y)
init_pt = 5
# import IPython
# IPython.embed()
A = X.T.dot(X)
t1 = time.time()
verbose = True
prms = ASI.Parameters(pi=pi,sparse=False, verbose=verbose)
kAS = ASI.kernelAS(prms)
kAS.initialize(X)
sAS = ASI.shariAS(prms)
sAS.initialize(A)
#sAS2 = ASI.naiveShariAS(prms)
kAS.firstMessage(init_pt)
sAS.firstMessage(init_pt)
# fs2 = [kAS.f]
for i in range(num_eval):
idx1 = kAS.getNextMessage()
kAS.setLabelCurrent(Y[idx1])
# init_lbls[idx1] = Y[idx1]
idx2 = sAS.getNextMessage()
sAS.setLabelCurrent(Y[idx2])
print('NEXT')
print idx1==idx2
print nac(kAS.f, sAS.f)
# fs2.append(kAS.f)
# fs3.append(sAS.f)
import IPython
IPython.embed()
def test_interface ():
verbose = False
#ts_data = ef.load_timestamps (tsfile)
Xfull = load_sparse_csr('Xfull1.npz')
r,n = Xfull.shape
nt = int(0.05*n)
num_eval = 1000
# num_eval = nt*2
Y = np.array([1]*nt + [0]*(n-nt), dtype=int)
pi = sum(Y)/len(Y)
init_pt = 100
t1 = time.time()
prms = ASI.Parameters(pi=pi,sparse=True, verbose=verbose)
kAS = ASI.kernelAS(prms)
kAS.initialize(Xfull)
kAS.firstMessage(init_pt)
fs2 = [kAS.f]
for i in range(num_eval):
idx = kAS.getNextMessage()
kAS.setLabelCurrent(Y[idx])
fs2.append(kAS.f)
t2 = time.time()
f1,h1,s1,fs1,dtinv1 = AS.kernel_AS (Xfull, Y, pi=pi, num_eval=num_eval, init_pt=init_pt, verbose=verbose,all_fs=True,tinv=True,sparse=True)
t3 = time.time()
checks = [np.allclose(fs1[i],fs2[i]) for i in range(len(fs1))]
import IPython
IPython.embed()
X, Y = change_prev(X0, Y0, prev)
act_prev = Y.mean()
# --
# Seed labels
init_pt = np.random.choice(np.where(Y)[0], n_init, replace=False)
init_labels = {p:1 for p in init_pt}
# --
# Initialize search
vsimp = SimpleLAS(X, init_labels=init_labels, pi=act_prev, eta=0.5, alpha=0.1)
params = ASI.Parameters(pi=act_prev, sparse=False, eta=0.5, alpha=0.1)
ref = ASI.linearizedAS(params)
ref.initialize(X, init_labels=init_labels)
assert((vsimp.f == ref.f).mean() == 1)
# --
# Compare performance
simp_idx = vsimp.next_message
vsimp.setLabel(simp_idx, Y[simp_idx])
ref_idx = ref.getNextMessage()
ref.setLabelCurrent(Y[ref_idx])
assert(ref_idx == simp_idx)
def test_warm_start ():
verbose = True
nac = np.allclose
#ts_data = ef.load_timestamps (tsfile)
Xfull = load_sparse_csr('Xfull1.npz')
# print Xfull.shape
# Xfull = Xfull[np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=1))[0])),:]
# Xfull = Xfull[:,np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=0))[1]))]
# # r,n = Xfull.shape
# print Xfull.shape
# Xfull = Xfull[np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=1))[0])),:]
# Xfull = Xfull[:,np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=0))[1]))]
# getting rid of features which are zero for all these elements
n = 300
r = 600
X = Xfull[:,:n]
X = X[np.squeeze(np.array(np.nonzero(X.sum(axis=1))[0])),:]
X = X[:,np.squeeze(np.array(np.nonzero(X.sum(axis=0))[1]))]
X = X[:r,:]
X = X[np.squeeze(np.array(np.nonzero(X.sum(axis=1))[0])),:]
X = X[:,np.squeeze(np.array(np.nonzero(X.sum(axis=0))[1]))]
print X.shape
#X = np.load('X11.npy')
r,n = X.shape
nt = int(0.05*n)
num_eval = 50
Y = np.array([1]*nt + [0]*(n-nt), dtype=int)
nr.shuffle(Y)
pi = sum(Y)/len(Y)
init_pt = 5
# import IPython
# IPython.embed()
A = np.array((X.T.dot(X)).todense())
t1 = time.time()
prms = ASI.Parameters(pi=pi,sparse=True, verbose=verbose)
kAS = ASI.kernelAS(prms)
kAS.initialize(X)
kAS2 = ASI.kernelAS(prms)
sAS = ASI.shariAS(prms)
sAS2 = ASI.naiveShariAS(prms)
# import IPython
# IPython.embed()
init_lbls = {init_pt:1}
kAS.firstMessage(init_pt)
fs2 = [kAS.f]
for i in range(num_eval):
idx1 = kAS.getNextMessage()
kAS.setLabelCurrent(Y[idx1])
init_lbls[idx1] = Y[idx1]
# sAS.setLabelCurrent(Y[idx2])
# fs2.append(kAS.f)
# fs3.append(sAS.f)
print("Batch initializing:")
print("Kernel AS:")
kAS2.initialize(X, init_lbls)
print("Shari AS:")
sAS.initialize(A, init_lbls)
print("Naive Shari AS:")
sAS2.initialize(A, init_lbls)
import IPython
IPython.embed()
def test_interface3 ():
verbose = True
nac = np.allclose
#ts_data = ef.load_timestamps (tsfile)
Xfull = load_sparse_csr('Xfull1.npz')
print Xfull.shape
Xfull = Xfull[np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=1))[0])),:]
Xfull = Xfull[:,np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=0))[1]))]
# r,n = Xfull.shape
print Xfull.shape
Xfull = Xfull[np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=1))[0])),:]
Xfull = Xfull[:,np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=0))[1]))]
# getting rid of features which are zero for all these elements
# n = 300
# r = 600
X = Xfull#[:,:n]
# X = X[np.squeeze(np.array(np.nonzero(X.sum(axis=1))[0])),:]
# X = X[:,np.squeeze(np.array(np.nonzero(X.sum(axis=0))[1]))]
# X = X[:r,:]
# X = X[np.squeeze(np.array(np.nonzero(X.sum(axis=1))[0])),:]
# X = X[:,np.squeeze(np.array(np.nonzero(X.sum(axis=0))[1]))]
# print X.shape
# #X = np.load('X11.npy')
r,n = X.shape
nt = int(0.05*n)
num_eval = 50
Y = np.array([1]*nt + [0]*(n-nt), dtype=int)
pi = sum(Y)/len(Y)
init_pt = 5
# import IPython
# IPython.embed()
A = np.array((X.T.dot(X)).todense())
t1 = time.time()
prms = ASI.Parameters(pi=pi,sparse=True, verbose=verbose)
kAS = ASI.kernelAS(prms)
kAS.initialize(X)
sAS = ASI.shariAS(prms)
sAS.initialize(A)
# ofk = kAS.f
# ofs = sAS.f
# import IPython
# IPython.embed()
kAS.firstMessage(init_pt)
fs2 = [kAS.f]
sAS.firstMessage(init_pt)
fs3 = [sAS.f]
# #
# lbl = 1
# idx = 5
# B = np.ones(n)/(1+prms.w0)
# D = A.sum(axis=1)
# BDinv = np.diag(np.squeeze(B*1./D))
# IA = np.eye(n) - BDinv.dot(A)
# IAi = np.matrix(nlg.inv(IA))
# IAk = nlg.inv(np.eye(n) + kAS.BDinv.dot(X.T.dot(nlg.inv(np.eye(r) - X.dot(kAS.BDinv.dot(X.T))))).dot(X.todense()))
# IAki = nlg.inv(IAk)
# t = (1+prms.w0)*(1-prms.eta)
# e = np.zeros((n,1))
# e[idx] = 1
# IA2 = IA + (1-t)*e.dot(e.T).dot(BDinv.dot(A))
# ai = (1./D)[idx]/(1+ prms.w0)*A[idx,:]
# Ad = (1-t)*IAi[:,idx].dot(ai.dot(IAi))/(1 + (1-t)*ai.dot(IAi[:,idx]))
# IA2i = IAi - Ad
#
# import IPython
# IPython.embed()
for i in range(num_eval):
idx1 = kAS.getNextMessage()
idx2 = sAS.getNextMessage()
print('NEXT')
print idx1==idx2
print nac(kAS.f, sAS.f)
# import IPython
# IPython.embed()
kAS.setLabelCurrent(Y[idx1])
sAS.setLabelCurrent(Y[idx2])
fs2.append(kAS.f)
fs3.append(sAS.f)
t2 = time.time()
# f1,h1,s1,fs1,dtinv1 = AS.kernel_AS (Xfull, Y, pi=pi, num_eval=num_eval, init_pt=init_pt, verbose=verbose,all_fs=True,tinv=True,sparse=True)
t3 = time.time()
# checks = [np.allclose(fs1[i],fs2[i]) for i in range(len(fs1))]
import IPython
IPython.embed()
def test_interface2 ():
verbose = True
nac = np.allclose
#ts_data = ef.load_timestamps (tsfile)
Xfull = load_sparse_csr('Xfull1.npz')
print Xfull.shape
# Xfull = Xfull[np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=1))[0])),:]
# Xfull = Xfull[:,np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=0))[1]))]
# r,n = Xfull.shape
# print Xfull.shape
# Xfull = Xfull[np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=1))[0])),:]
# Xfull = Xfull[:,np.squeeze(np.asarray(np.nonzero(Xfull.sum(axis=0))[1]))]
# getting rid of features which are zero for all these elements
n = 300
r = 600
X = Xfull[:,:n]
X = X[np.squeeze(np.array(np.nonzero(X.sum(axis=1))[0])),:]
X = X[:,np.squeeze(np.array(np.nonzero(X.sum(axis=0))[1]))]
X = X[:r,:]
X = X[np.squeeze(np.array(np.nonzero(X.sum(axis=1))[0])),:]
X = X[:,np.squeeze(np.array(np.nonzero(X.sum(axis=0))[1]))]
print X.shape
#X = np.load('X11.npy')
r,n = X.shape
nt = int(0.05*n)
num_eval = 50
Y = np.array([1]*nt + [0]*(n-nt), dtype=int)
pi = sum(Y)/len(Y)
init_pt = 5
# import IPython
# IPython.embed()
A = np.array((X.T.dot(X)).todense())
t1 = time.time()
prms = ASI.Parameters(pi=pi,sparse=True, verbose=verbose)
kAS = ASI.kernelAS(prms)
kAS.initialize(X)
sAS = ASI.naiveShariAS(prms)
sAS.initialize(A)
import IPython
IPython.embed()
kAS.firstMessage(init_pt)
fs2 = [kAS.f]
sAS.firstMessage(init_pt)
fs3 = [sAS.f]
import IPython
IPython.embed()
for i in range(num_eval):
idx1 = kAS.getNextMessage()
idx2 = sAS.getNextMessage()
print('NEXT')
print idx1==idx2
print nac(kAS.f, sAS.f)
# import IPython
# IPython.embed()
kAS.setLabelCurrent(Y[idx1])
sAS.setLabelCurrent(Y[idx2])
fs2.append(kAS.f)
fs3.append(sAS.f)
t2 = time.time()
# f1,h1,s1,fs1,dtinv1 = AS.kernel_AS (Xfull, Y, pi=pi, num_eval=num_eval, init_pt=init_pt, verbose=verbose,all_fs=True,tinv=True,sparse=True)
t3 = time.time()
# checks = [np.allclose(fs1[i],fs2[i]) for i in range(len(fs1))]
import IPython
IPython.embed()
