def test_nmf():
img_file = 'boat.png'
try:
img = Image.open(img_file)
except:
print("Cannot load image %s : skipping test" %img_file)
return None
I = np.array(img) / 255.
if I.ndim == 3:
A = np.asfortranarray(I.reshape((I.shape[0],I.shape[1] * I.shape[2])),dtype = myfloat)
rgb = True
else:
A = np.asfortranarray(I,dtype = myfloat)
rgb = False
m = 16;n = 16;
X = spams.im2col_sliding(A,m,n,rgb)
X = X[:,::10]
X = np.asfortranarray(X / np.tile(np.sqrt((X * X).sum(axis=0)),(X.shape[0],1)),dtype = myfloat)
########## FIRST EXPERIMENT ###########
tic = time.time()
(U,V) = spams.nmf(X,return_lasso= True,K = 49,numThreads=4,iter = -5)
tac = time.time()
t = tac - tic
print('time of computation for Dictionary Learning: %f' %t)
print('Evaluating cost function...')
Y = X - U * V
R = np.mean(0.5 * (Y * Y).sum(axis=0))
print('objective function: %f' %R)
return None
def test_nmf():
img_file = 'boat.png'
try:
img = Image.open(img_file)
except:
print "Cannot load image %s : skipping test" %img_file
return None
I = np.array(img) / 255.
if I.ndim == 3:
A = np.asfortranarray(I.reshape((I.shape[0],I.shape[1] * I.shape[2])),dtype = myfloat)
rgb = True
else:
A = np.asfortranarray(I,dtype = myfloat)
rgb = False
m = 16;n = 16;
X = spams.im2col_sliding(A,m,n,rgb)
X = X[:,::10]
X = np.asfortranarray(X / np.tile(np.sqrt((X * X).sum(axis=0)),(X.shape[0],1)),dtype = myfloat)
########## FIRST EXPERIMENT ###########
tic = time.time()
(U,V) = spams.nmf(X,return_lasso= True,K = 49,numThreads=4,iter = -5)
tac = time.time()
t = tac - tic
print 'time of computation for Dictionary Learning: %f' %t
print 'Evaluating cost function...'
Y = X - U * V
R = np.mean(0.5 * (Y * Y).sum(axis=0))
print 'objective function: %f' %R
return None
def smaf(X, d, lda1, lda2, maxItr=10, UW=None, posW=False, posU=True, use_chol=False, module_lower=500,
activity_lower=5, donorm=False, mode=1, mink=5, U0=[], U0_delta=0.1, doprint=False):
# use Cholesky when we expect a very sparse result
# this tends to happen more on the full vs subsampled matrices
if UW == None:
U, W = spams.nmf(np.asfortranarray(X), return_lasso=True, K=d, numThreads=THREADS)
W = np.asarray(W.todense())
else:
U, W = UW
Xhat = U.dot(W)
Xnorm = np.linalg.norm(X) ** 2 / X.shape[1]
for itr in range(maxItr):
if mode == 1:
# In this mode the ldas correspond to an approximate desired fit
# Higher lda will be a worse fit, but will result in a sparser sol'n
U = spams.lasso(np.asfortranarray(X.T), D=np.asfortranarray(W.T),
lambda1=lda2 * Xnorm, mode=1, numThreads=THREADS, cholesky=use_chol, pos=posU)
U = np.asarray(U.todense()).T
elif mode == 2:
if len(U0) > 0:
U = projected_grad_desc(W.T, X.T, U.T, U0.T, lda2, U0_delta, maxItr=400)
U = U.T
else:
U = spams.lasso(np.asfortranarray(X.T), D=np.asfortranarray(W.T),
lambda1=lda2, lambda2=0.0, mode=2, numThreads=THREADS, cholesky=use_chol, pos=posU)
U = np.asarray(U.todense()).T
if donorm:
U = U / np.linalg.norm(U, axis=0)
U[np.isnan(U)] = 0
if mode == 1:
wf = (1 - lda2)
W = sparse_decode(X, U, lda1, worstFit=wf, mink=mink)
elif mode == 2:
if len(U0) > 0:
W = projected_grad_desc(U, X, W, [], lda1, 0., nonneg=posW, maxItr=400)
else:
W = spams.lasso(np.asfortranarray(X), D=np.asfortranarray(U),
lambda1=lda1, lambda2=1.0, mode=2, numThreads=THREADS, cholesky=use_chol, pos=posW)
W = np.asarray(W.todense())
Xhat = U.dot(W)
module_size = np.average([np.exp(entropy(u)) for u in U.T if u.sum() > 0])
activity_size = np.average([np.exp(entropy(abs(w))) for w in W.T])
if doprint:
print distance.correlation(X.flatten(), Xhat.flatten()), module_size, activity_size, lda1, lda2
if module_size < module_lower:
lda2 /= 2.
if activity_size < activity_lower:
lda2 /= 2.
return U, W
def online_NMF(self,n_components=30,method='nnsc',lambda1=100,iterations=-5,batchsize=512,model=None,**kwargs):
""" Method performing online matrix factorization and using the spams (http://spams-devel.gforge.inria.fr/doc-python/html/index.html) package from Inria.
Implements bith the nmf and nnsc methods
Parameters
----------
n_components: int
method: 'nnsc' or 'nmf' (see http://spams-devel.gforge.inria.fr/doc-python/html/index.html)
lambda1: see http://spams-devel.gforge.inria.fr/doc-python/html/index.html
iterations: see http://spams-devel.gforge.inria.fr/doc-python/html/index.html
batchsize: see http://spams-devel.gforge.inria.fr/doc-python/html/index.html
model: see http://spams-devel.gforge.inria.fr/doc-python/html/index.html
**kwargs: more arguments to be passed to nmf or nnsc
Return:
-------
time_comps
space_comps
"""
try:
import spams
except:
print("You need to install the SPAMS package")
raise
T,d1,d2=np.shape(self)
d=d1*d2
X=np.asfortranarray(np.reshape(self,[T,d],order='F'))
if method == 'nmf':
(time_comps,V) = spams.nmf(X,return_lasso= True ,K = n_components,numThreads=4,iter = iterations,**kwargs)
elif method == 'nnsc':
(time_comps,V) = spams.nnsc(X,return_lasso=True,K=n_components, lambda1 = lambda1,iter = iterations, model = model, **kwargs)
else:
raise Exception('Method unknown')
space_comps=[]
for idx,mm in enumerate(V):
space_comps.append(np.reshape(mm.todense(),(d1,d2),order='F'))
return time_comps,np.array(space_comps)
def snmf(self, img):
"""Sparse Non-negative Matrix Factorization with spams."""
img = np.asfortranarray(img)
(W, H) = spams.nmf(img, K=2, return_lasso=True)
H = np.array(H.todense())
return W, H
'map input file (libsvm) to <argv[3]> topics, output csv' from sklearn.datasets import load_svmlight_file import numpy as np import spams import sys input_file = sys.argv[1] output_file = sys.argv[2] try: num_topics = int( sys.argv[3] ) except IndexError: num_topics = 50 x_train, y_train = load_svmlight_file( input_file ) x_train_t = np.transpose( x_train ) u = spams.nmf( x_train_t, return_lasso = False, K = num_topics ) mapped_x = x_train * u y_train.shape = y_train.shape[0], 1 np.savetxt( output_file, np.hstack(( y_train, mapped_x )), delimiter = ",", fmt = '%.6f' )
#%%
mcr = cm.load('/home/andrea/NEL-LAB Dropbox/Andrea Giovannucci/Kaspar-Andrea/exampledata/Other/403106_3min_rois_mc_lp_crop_2.hdf5')
#%%
fname = '/home/nel/data/voltage_data/Marton/454597/Cell_0/40x_patch1/movie/40x_patch1_000_mc_small.hdf5'
#%%
mcr = cm.load(fname)
ycr = mcr.to_2D()
ycr = ycr - ycr.min()
mcr_lc = local_correlations_movie_offline(fname)
ycr_lc = mcr_lc.to_2D()
#%%
D_lc,tr_lc = spams.nmf(np.asfortranarray(ycr_lc.T), K=2, return_lasso=True)
plt.figure();plt.plot(tr_lc.T.toarray())
plt.figure();plt.imshow(D_lc[:,0].reshape(mcr.shape[1:], order='F'), cmap='gray')
#%%
D,tr = spams.trainDL(np.asfortranarray(ycr.T), K=2, D=D_lc, lambda1=0)
#%%
D,tr = spams.nnsc(np.asfortranarray(ycr.T), K=2, return_lasso=True, lambda1=0)
#%%
D,tr = spams.nmf(np.asfortranarray(np.abs(ycr.T)), K=2, return_lasso=True)
#%%
D,tr = spams.nnsc(np.asfortranarray(ycr.T), K=2, return_lasso=True, lambda1=1)
#%%
plt.figure();plt.plot(tr.T.toarray())
plt.figure();plt.imshow(D[:,1].reshape(mcr.shape[1:], order='F'), cmap='gray');plt.title('comp1')
Psi=ua,
snr=SNR,
use_ridge=False)
Results['SVD (training)'] = compare_results(xa, x1a)
x1b, phi, y, w, d, psi = recover_system_knownBasis(xb,
measurements,
sparsity,
Psi=ua,
snr=SNR,
use_ridge=False)
Results['SVD (testing)'] = compare_results(xb, x1b)
np.save("./Data/linedata/GSE78779_svd.npy", x1b)
ua, va = spams.nmf(np.asfortranarray(xa),
return_lasso=True,
K=dictionary_size,
clean=True,
numThreads=THREADS)
x2a, phi, y, w, d, psi = recover_system_knownBasis(xa,
measurements,
sparsity,
Psi=ua,
snr=SNR,
use_ridge=False)
Results['sparse NMF (training)'] = compare_results(xa, x2a)
x2b, phi, y, w, d, psi = recover_system_knownBasis(xb,
measurements,
sparsity,
Psi=ua,
snr=SNR,
use_ridge=False)
u, s, vt = np.linalg.svd(xa, full_matrices=False)
variance_fraction = np.cumsum(s**2 / (s**2).sum())
basis_size = np.where(variance_fraction > 1 - ERROR_THRESH)[0][0]
basis_size = min(MAX_BASIS, basis_size)
ua = u[:, :basis_size]
va = np.diag(s[:basis_size]).dot(vt[:basis_size])
xh_svd = ua.dot(va)
fit_svd = 1 - np.linalg.norm(xa - xh_svd)**2 / np.linalg.norm(xa)**2
module_size_svd = np.array([np.exp(entropy(abs(x))) for x in ua.T])
usage_svd = np.array([np.exp(entropy(abs(x))) for x in va.T])
ua_svd = ua
w_svd = va
ds = basis_size
while True:
ua, va = spams.nmf(np.asfortranarray(xa),
return_lasso=True,
K=ds,
numThreads=THREADS)
va = np.asarray(va.todense())
x0 = ua.dot(va)
d = 1 - np.linalg.norm(xa - x0)**2 / np.linalg.norm(xa)**2
if (d > 1 - ERROR_THRESH) or (ds > xa.shape[1] * .4) or (ds >
MAX_BASIS):
break
ds += max(1, ds / 10)
xh_nmf = ua.dot(va)
fit_nmf = 1 - np.linalg.norm(xa - xh_nmf)**2 / np.linalg.norm(xa)**2
module_size_nmf = np.array([np.exp(entropy(abs(x))) for x in ua.T])
usage_nmf = np.array([np.exp(entropy(abs(x))) for x in va.T])
ua_nmf = ua
w_nmf = va
k = min(int(xa.shape[1] * 1.5), ds * 4)
# NMf accepts onlt non-negative data, So it should not be centered.
if m != 'nmf':
X_m = X_m - X_m.mean(axis=0)
# normalizing..
X_m = np.asfortranarray(X_m / np.sqrt((X_m * X_m).sum(axis=0)),
dtype=np.float64)
if m == 'pca':
svd = TruncatedSVD(n_components=D, n_iter=7)
W = svd.fit_transform(X_m)
else:
param = {'K': D, 'numThreads': -1, 'batchsize': 256, 'iter': 1000}
if m == 'nmf':
W = nmf(X_m, **param)
else:
param['verbose'] = False
if m == 'spca':
param['lambda1'] = 0.1
param['gamma1'] = 0.1
param['modeD'] = 1
W = trainDL(X_m, **param)
elif m == 'dl':
param['lambda1'] = 0.1
param['mode'] = 2
W = trainDL(X_m, **param)
# resulting basisvectors will be visualized as image patches.
img = displayPatches(W)
img = np.uint8(img[:, :, 0] * 255.)
def online_NMF(self,
n_components=30,
method='nnsc',
lambda1=100,
iterations=-5,
batchsize=512,
model=None,
**kwargs):
""" Method performing online matrix factorization and using the spams (http://spams-devel.gforge.inria.fr/doc-python/html/index.html) package from Inria.
Implements bith the nmf and nnsc methods
Parameters
----------
n_components: int
method: 'nnsc' or 'nmf' (see http://spams-devel.gforge.inria.fr/doc-python/html/index.html)
lambda1: see http://spams-devel.gforge.inria.fr/doc-python/html/index.html
iterations: see http://spams-devel.gforge.inria.fr/doc-python/html/index.html
batchsize: see http://spams-devel.gforge.inria.fr/doc-python/html/index.html
model: see http://spams-devel.gforge.inria.fr/doc-python/html/index.html
**kwargs: more arguments to be passed to nmf or nnsc
Return:
-------
time_comps
space_comps
"""
try:
import spams
except:
print "You need to install the SPAMS package"
raise
T, d1, d2 = np.shape(self)
d = d1 * d2
X = np.asfortranarray(np.reshape(self, [T, d], order='F'))
if method == 'nmf':
(time_comps, V) = spams.nmf(X,
return_lasso=True,
K=n_components,
numThreads=4,
iter=iterations,
**kwargs)
elif method == 'nnsc':
(time_comps, V) = spams.nnsc(X,
return_lasso=True,
K=n_components,
lambda1=lambda1,
iter=iterations,
model=model,
**kwargs)
else:
raise Exception('Method unknown')
space_comps = []
for idx, mm in enumerate(V):
space_comps.append(np.reshape(mm.todense(), (d1, d2), order='F'))
return time_comps, np.array(space_comps)
