def __init__(self,
X,
XAxis,
Y,
R,
outerIter=70,
testSize=0.5,
samples=10,
seed=10):
self.X = X
self.axisInfo = np.array(XAxis[0], dtype="int")
self.Y = Y
self.R = R
self.outerIter = outerIter
self.samples = samples
self.ttss = StratifiedShuffleSplit(Y,
n_iter=samples,
test_size=testSize,
random_state=seed)
self.rawFeatures = createRawFeatures(X)
self.flatX = sptenmat.sptenmat(
X, [0]).tocsrmat() # matricize along the first mode
self.pcaModel = RandomizedPCA(n_components=R)
self.predModel = LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
self.nmfModel = NMF(n_components=R,
max_iter=self.outerIter,
nls_max_iter=self.innerIter)
def ctor(verbose):
x = numpy.array([[[0, 0, 0.9052], [0.9121, 0, 0.7363]],
[[0.1757, 0.2089, 0], [0, 0.7455, 0]],
[[0, 0, 0.6754], [0, 0, 0]]])
obj = sptenmat.sptenmat(x, [0], [1, 2], [10, 10, 10])
print obj
subs = numpy.array([[1, 3, 5], [1, 1, 0], [2, 2, 2], [3, 4, 4], [1, 1, 1],
[1, 1, 1]])
vals = numpy.array([[0.5], [1.5], [100], [3.5], [4.5], [5.5]])
siz = numpy.array([4, 5, 6])
spt = sptensor.sptensor(subs, vals, siz)
print spt
obj = sptenmat.sptenmat(spt, [0, 1], [2])
print obj
def ctor(verbose):
x = numpy.array([
[[0,0,0.9052],[0.9121,0,0.7363]],
[[0.1757,0.2089,0],[0,0.7455,0]],
[[0,0,0.6754],[0,0,0]]
])
obj = sptenmat.sptenmat(x, [0], [1,2], [10,10,10]);
print obj;
subs = numpy.array([[1, 3, 5], [1, 1, 0], [2, 2, 2], [3, 4, 4], [1, 1, 1], [1, 1, 1]]);
vals = numpy.array([[0.5], [1.5], [100], [3.5], [4.5], [5.5]]);
siz = numpy.array([4, 5, 6]);
spt = sptensor.sptensor(subs, vals, siz);
print spt;
obj = sptenmat.sptenmat(spt, [0,1], [2]);
print obj;
def tosparsematTest(verbose):
subs = numpy.array([[1, 3, 5], [1, 1, 0], [2, 2, 2], [3, 4, 4], [1, 1, 1], [1, 1, 1]]);
vals = numpy.array([[0.5], [1.5], [100], [3.5], [4.5], [5.5]]);
siz = numpy.array([4, 5, 6]);
spt = sptensor.sptensor(subs, vals, siz);
print spt;
sptm = sptenmat.sptenmat(spt,[1]);
print sptm;
print sptm.tosparsemat();
def tosparsematTest(verbose):
subs = numpy.array([[1, 3, 5], [1, 1, 0], [2, 2, 2], [3, 4, 4], [1, 1, 1],
[1, 1, 1]])
vals = numpy.array([[0.5], [1.5], [100], [3.5], [4.5], [5.5]])
siz = numpy.array([4, 5, 6])
spt = sptensor.sptensor(subs, vals, siz)
print spt
sptm = sptenmat.sptenmat(spt, [1])
print sptm
print sptm.tosparsemat()
def __init__(self, X, XAxis, Y, R, outerIter=70, testSize=0.5, samples=10, seed=10):
self.X = X
self.axisInfo = np.array(XAxis[0], dtype="int")
self.Y = Y
self.R = R
self.outerIter = outerIter
self.samples = samples
self.ttss = StratifiedShuffleSplit(Y,n_iter=samples, test_size=testSize, random_state=seed)
self.rawFeatures = createRawFeatures(X)
self.flatX = sptenmat.sptenmat(X, [0]).tocsrmat() # matricize along the first mode
self.pcaModel = RandomizedPCA(n_components=R)
self.predModel = LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
self.nmfModel = NMF(n_components=R, max_iter = self.outerIter, nls_max_iter = self.innerIter)
def DTA(Xnew, R, C=None, alpha=None):
"""DTA analysis"""
# number of dimensions of the input tensor.
N = Xnew.ndims()
# If the co-variacne matrices are not given,
# initialize all of them to be 0
if (C == None):
C = []
dv = Xnew.shape
for i in range(0, N):
C.extend([sparse.coo_matrix(([], ([], [])), [dv[i], dv[i]])])
# If the forgetting factor is not given, it is 1.
if (alpha == None):
alpha = 1
U = []
Cnew = []
for i in range(0, N):
if (Xnew.__class__ == tensor.tensor):
XM = tenmat.tenmat(Xnew, [i]).tondarray()
elif (Xnew.__class__ == sptensor.sptensor):
XM = sptenmat.sptenmat(Xnew, [i]).tosparsemat()
elif (Xnew.__class__ == ttensor.ttensor):
raise TypeError("It is not supported yet.")
else:
raise TypeError(
"1st argument must be tensor, sptensor, or ttensor")
Cnew.extend(
[numpy.array(alpha * C[i] + numpy.dot(XM, XM.transpose()))])
(w, v) = eigwrapper(Cnew[i], R[i])
U.extend([numpy.array(v)])
core = Xnew.ttm(U, None, 't')
T = ttensor.ttensor(core, U)
return (T, Cnew)
def DTA(Xnew, R, C = None, alpha = None):
"""DTA analysis"""
# number of dimensions of the input tensor.
N = Xnew.ndims();
# If the co-variacne matrices are not given,
# initialize all of them to be 0
if(C == None):
C = [];
dv = Xnew.shape;
for i in range(0, N):
C.extend([ sparse.coo_matrix(([],([],[])),[dv[i], dv[i]]) ]);
# If the forgetting factor is not given, it is 1.
if(alpha == None):
alpha = 1;
U = [];
Cnew = [];
for i in range (0,N):
if(Xnew.__class__ == tensor.tensor):
XM = tenmat.tenmat(Xnew,[i]).tondarray();
elif(Xnew.__class__ == sptensor.sptensor):
XM = sptenmat.sptenmat(Xnew,[i]).tosparsemat();
elif(Xnew.__class__ == ttensor.ttensor):
raise TypeError("It is not supported yet.");
else:
raise TypeError("1st argument must be tensor, sptensor, or ttensor");
Cnew.extend([ numpy.array(alpha*C[i] + numpy.dot(XM, XM.transpose())) ]);
(w,v) = eigwrapper(Cnew[i], R[i]);
U.extend([ numpy.array(v) ]);
core = Xnew.ttm(U, None, 't');
T = ttensor.ttensor(core, U);
return (T, Cnew);
from sklearn import preprocessing
import nimfa
import sys
sys.path.append("..")
import KLProjection
import predictionModel
import sptenmat
import tensorTools
import json
X, axisDict, classDict = tensorTools.loadSingleTensor("data/cms-tensor-{0}.dat")
Y = np.array(classDict.values(), dtype='int')
flatX = sptenmat.sptenmat(X, [0]).tocsrmat() # matricize along the first mode
testSize = 0.5
seed = 400
R = 50
ttss = StratifiedShuffleSplit(Y, n_iter=1, test_size=testSize, random_state=seed)
for train, test in ttss:
nmfModel = nimfa.mf(flatX[train,:], method="nmf", max_iter=200, rank=R)
nmfResult = nimfa.mf_run(nmfModel)
nmfBasis = nmfResult.coef().transpose()
nmfBasis = preprocessing.normalize(nmfBasis, norm="l1", axis=0)
nmfBasisA = nmfBasis.toarray()
outFile = file("results/nmf-404.dat", "wb")
np.save(outFile, nmfBasisA)
outFile.close()
compOut.append({
"expt": exptID,
"R": R,
"Outer": outerIter,
"Model": "Limestone",
"Comp": elapsed
})
klp = KLProjection.KLProjection(M.U, M.R)
ptfFeat = klp.projectSlice(X, 0)
ptfMatrix = khatrirao.khatrirao(M.U[1], M.U[2])
np.save("results/pred-metric-limestone-{0}.dat".format(exptID),
ptfMatrix)
## now we want to do PCA and NMF as well
flatX = sptenmat.sptenmat(
X, [0]).tocsrmat() # matricize along the first mode
startTime = time.time()
pcaModel = RandomizedPCA(n_components=R)
pcaModel.fit(flatX[train, :])
elapsed = time.time() - startTime
compOut.append({
"expt": exptID,
"R": R,
"Outer": outerIter,
"Model": "PCA",
"Comp": elapsed
})
pcaFeat = pcaModel.transform(flatX)
pcaBasis = pcaModel.components_
np.save("results/pred-metric-pca-{0}.dat".format(exptID), pcaBasis)
def ttm(self, mat, dims = None, option = None):
""" computes the sptensor times the given matrix.
arrs is a single 2-D matrix/array or a list of those matrices/arrays."""
if(dims == None):
dims = range(0,self.ndims());
#Handle when arrs is a list of arrays
if(mat.__class__ == list):
if(len(mat) == 0):
raise ValueError("the given list of arrays is empty!");
(dims,vidx) = tools.tt_dimscehck(dims, self.ndims(), len(mat));
Y = self.ttm(mat[vidx[0]],dims[0],option);
for i in range(1, len(dims)):
Y = Y.ttm(mat[vidx[i]],dims[i],option);
return Y;
if(mat.ndim != 2):
raise ValueError ("matrix in 2nd armuent must be a matrix!");
if(option != None):
if (option == 't'):
mat = mat.transpose();
else:
raise ValueError ("unknown option.");
if(dims.__class__ == list):
if(len(dims) != 1):
raise ValueError("Error in number of elements in dims");
else:
dims = dims[0];
if(dims < 0 or dims > self.ndims()):
raise ValueError ("Dimension N must be between 1 and num of dimensions");
#Check that sizes match
if(self.shape[dims] != mat.shape[1]):
raise ValueError ("size mismatch on V");
#Compute the new size
newsiz = list(self.shape);
newsiz[dims] = mat.shape[0];
#Compute Xn
Xnt = sptenmat.sptenmat(self,None,[dims],None,'t');
rdims = Xnt.rdims;
cdims = Xnt.cdims;
I = [];
J = [];
for i in range(0, len(Xnt.subs)):
I.extend([Xnt.subs[i][0]]);
J.extend([Xnt.subs[i][1]]);
Z = (sparse.coo_matrix((Xnt.vals.flatten(),(I,J)),
shape = (tools.getelts(Xnt.tsize, Xnt.rdims).prod(),
tools.getelts(Xnt.tsize, Xnt.cdims).prod()))
* mat.transpose());
Z = tensor.tensor(Z,newsiz).tosptensor();
if(Z.nnz() <= 0.5 * numpy.array(newsiz).prod()):
Ynt = sptenmat.sptenmat(Z, rdims, cdims);
return Ynt.tosptensor();
else:
Ynt = tenmat.tenmat(Z.totensor(), rdims, cdims);
return Ynt.totensor();
def ttm(self, mat, dims = None, option = None):
""" computes the sptensor times the given matrix.
arrs is a single 2-D matrix/array or a list of those matrices/arrays."""
if(dims == None):
dims = range(0,self.ndims());
#Handle when arrs is a list of arrays
if(mat.__class__ == list):
if(len(mat) == 0):
raise ValueError("the given list of arrays is empty!");
(dims,vidx) = tools.tt_dimscehck(dims, self.ndims(), len(mat));
Y = self.ttm(mat[vidx[0]],dims[0],option);
for i in range(1, len(dims)):
Y = Y.ttm(mat[vidx[i]],dims[i],option);
return Y;
if(mat.ndim != 2):
raise ValueError ("matrix in 2nd armuent must be a matrix!");
if(option != None):
if (option == 't'):
mat = mat.transpose();
else:
raise ValueError ("unknown option.");
if(dims.__class__ == list):
if(len(dims) != 1):
raise ValueError("Error in number of elements in dims");
else:
dims = dims[0];
if(dims < 0 or dims > self.ndims()):
raise ValueError ("Dimension N must be between 1 and num of dimensions");
#Check that sizes match
if(self.shape[dims] != mat.shape[1]):
raise ValueError ("size mismatch on V");
#Compute the new size
newsiz = list(self.shape);
newsiz[dims] = mat.shape[0];
#Compute Xn
Xnt = sptenmat.sptenmat(self,None,[dims],None,'t');
rdims = Xnt.rdims;
cdims = Xnt.cdims;
I = [];
J = [];
for i in range(0, len(Xnt.subs)):
I.extend([Xnt.subs[i][0]]);
J.extend([Xnt.subs[i][1]]);
Z = (sparse.coo_matrix((Xnt.vals.flatten(),(I,J)),
shape = (tools.getelts(Xnt.tsize, Xnt.rdims).prod(),
tools.getelts(Xnt.tsize, Xnt.cdims).prod()))
* mat.transpose());
Z = tensor.tensor(Z,newsiz).tosptensor();
if(Z.nnz() <= 0.5 * numpy.array(newsiz).prod()):
Ynt = sptenmat.sptenmat(Z, rdims, cdims);
return Ynt.tosptensor();
else:
Ynt = tenmat.tenmat(Z.totensor(), rdims, cdims);
return Ynt.totensor();
import numpy as np; import CP_APR import ktensor """ Test file associated with the CP decomposition using APR """ """ Test factorization of sparse matrix """ subs = np.array([[0,3,1], [1,0,1], [1,2,1], [1,3,1], [3,0,0]]); vals = np.array([[1],[1],[1],[1],[3]]); siz = np.array([5,5,2]) # 5x5x2 tensor X = sptensor.sptensor(subs, vals, siz) U0 = np.array([[0.7689, 0.8843, 0.7487, 0.0900], [0.1673, 0.5880, 0.8256, 0.1117], [0.8620, 0.1548, 0.7900, 0.1363], [0.9899, 0.1999, 0.3185, 0.6787], [0.5144, 0.4070, 0.5341, 0.4952]]) U1 = np.array([[0.1897, 0.5606, 0.8790, 0.9900], [0.4950, 0.9296, 0.9889, 0.5277], [0.1476, 0.6967, 0.0006, 0.4795], [0.0550, 0.5828, 0.8654, 0.8013], [0.8507, 0.8154, 0.6126, 0.2278]]) U2 = np.array([[0.4981, 0.5747, 0.7386, 0.2467], [0.9009, 0.8452, 0.5860, 0.6664]]) Minit = ktensor.ktensor(np.ones(4), [U0, U1, U2]) fms = Minit.fms(Minit) Y, cpstats, modelStats = CP_APR.cp_apr(X,4, Minit=Minit, maxiters=100); Y.normalize_sort(1) """ Test factorization of 2-mode sparse matrix """ matX = sptenmat.sptenmat(X, [0]).tosptensor() CP_APR.cp_apr(matX, 4) """ Test factorization of regular tensor """ XT = tensor.tensor(range(1,25), [3, 4, 2]) CP_APR.cp_apr(XT,4);