def mapLoadData(dataSetName, seedVal=100000):
"""This is for loading in data sets for processing using machine
learning algorithms, particularly mapping models (classification,
regression) latent variable models.
Options for dataSetName include 'spgp1d', 'gp1d' """
numpy.random.seed(seed=seedVal)
if dataSetName == 'spgp1d':
numIn = 1
N = 500
X = numpy.random.uniform(low=-1.0, high=1.0, size=(N, numIn))
X.sort(axis=0)
Xn = ndlml.matrix(X)
kern1 = ndlml.rbfKern(Xn)
kern1.setVariance(1)
kern1.setInverseWidth(20)
kern2 = ndlml.whiteKern(Xn)
kern2.setVariance(0.01)
kern = ndlml.cmpndKern(Xn)
kern.addKern(kern1)
kern.addKern(kern2)
K = ndlml.matrix(numpy.empty((N, N)))
kern.compute(K, Xn)
Kmat = K.toarray()
y = numpy.reshape(
numpy.random.multivariate_normal(numpy.zeros(N), Kmat), (N, 1))
return X, y
elif dataSetName == 'gp1d':
numIn = 1
N = 50
X = numpy.random.uniform(low=-1.0, high=1.0, size=(N, numIn))
X.sort(axis=0)
Xn = ndlml.matrix(X)
kern1 = ndlml.rbfKern(Xn)
kern1.setVariance(1)
kern1.setInverseWidth(20)
kern2 = ndlml.whiteKern(Xn)
kern2.setVariance(0.0001)
kern = ndlml.cmpndKern(Xn)
kern.addKern(kern1)
kern.addKern(kern2)
K = ndlml.matrix(numpy.empty((N, N)))
kern.compute(K, Xn)
Kmat = K.toarray()
y = numpy.reshape(
numpy.random.multivariate_normal(numpy.zeros(N), Kmat), (N, 1))
return X, y
else:
raise NameError, "Unknown data set"
def mapLoadData(dataSetName, seedVal=100000):
"""This is for loading in data sets for processing using machine
learning algorithms, particularly mapping models (classification,
regression) latent variable models.
Options for dataSetName include 'spgp1d', 'gp1d' """
numpy.random.seed(seed=seedVal)
if dataSetName == 'spgp1d':
numIn = 1
N = 500
X = numpy.random.uniform(low=-1.0, high=1.0, size=(N, numIn))
X.sort(axis=0)
Xn = ndlml.matrix(X)
kern1 = ndlml.rbfKern(Xn)
kern1.setVariance(1)
kern1.setInverseWidth(20)
kern2 = ndlml.whiteKern(Xn)
kern2.setVariance(0.01)
kern = ndlml.cmpndKern(Xn)
kern.addKern(kern1)
kern.addKern(kern2)
K = ndlml.matrix(numpy.empty((N, N)))
kern.compute(K, Xn)
Kmat = K.toarray()
y = numpy.reshape(numpy.random.multivariate_normal(numpy.zeros(N), Kmat), (N,1))
return X,y
elif dataSetName == 'gp1d':
numIn = 1
N = 50
X = numpy.random.uniform(low=-1.0, high=1.0, size=(N, numIn))
X.sort(axis=0)
Xn = ndlml.matrix(X)
kern1 = ndlml.rbfKern(Xn)
kern1.setVariance(1)
kern1.setInverseWidth(20)
kern2 = ndlml.whiteKern(Xn)
kern2.setVariance(0.0001)
kern = ndlml.cmpndKern(Xn)
kern.addKern(kern1)
kern.addKern(kern2)
K = ndlml.matrix(numpy.empty((N, N)))
kern.compute(K, Xn)
Kmat = K.toarray()
y = numpy.reshape(numpy.random.multivariate_normal(numpy.zeros(N), Kmat), (N,1))
return X,y
else:
raise NameError, "Unknown data set"
q = 2
Y, lbls = datasets.lvmLoadData('oil')
#Y = Y[0:10, :]
numData = Y.shape[0]
d = Y.shape[1]
#v, X = netlab.pca(Y.transpose(), q)
X = numpy.random.normal(0.0, 1e-1, (numData, 2))
Xstore = X;
Xstor = numpy.empty(Xstore.shape)
Ystore = Y;
Y = ndlwrap.fromarray(Y)
X = ndlwrap.fromarray(X)
# Set up kernel function
kern = nl.cmpndKern()
kern1 = nl.rbfKern(X)
kern2 = nl.biasKern(X)
kern3 = nl.whiteKern(X)
kern3.setVariance(1e-3)
kern.addKern(kern1)
kern.addKern(kern2)
kern.addKern(kern3)
noise = nl.gaussianNoise(Y)
# Create a GP model.
model = nl.gp(q, d, X, Y, kern, noise, nl.gp.DTCVAR, 100, 3)
import datasets
import matplotlib.pyplot as plt
import math
X, y = datasets.mapLoadData('spgp1d')
numActive = 9
Xstore = np.array(X)
ystore = np.array(y)
X = nl.matrix(X)
y = nl.matrix(y)
# Set up kernel function
kern = nl.cmpndKern()
kern1 = nl.rbfKern(X)
kern2 = nl.biasKern(X)
kern3 = nl.whiteKern(X)
kern3.setVariance(1e-4)
kern.addKern(kern1)
kern.addKern(kern2)
kern.addKern(kern3)
noise = nl.gaussianNoise(y)
# Create a GP model.
model = nl.gp(1, 1, X, y, kern, noise, nl.gp.DTC, numActive, 3)
model.setBetaVal(math.exp(2))
q = 2
Y, lbls = datasets.lvmLoadData('oil100')
d = Y.shape[0]
numData = Y.shape[1]
v, X = netlab.pca(Y.transpose(), q)
X = numpy.random.normal(0.0, 1e-6, (Y.shape[0], 2))
Xstore = X;
Xstor = numpy.empty(Xstore.shape)
Ystore = Y;
Y = ndlwrap.fromarray(Y)
X = ndlwrap.fromarray(X)
# Set up kernel function
kern = ndlml.cmpndKern()
kern1 = ndlml.rbfKern(X)
kern2 = ndlml.biasKern(X)
kern3 = ndlml.whiteKern(X)
kern.addKern(kern1)
kern.addKern(kern2)
kern.addKern(kern3)
noise = ndlml.gaussianNoise(Y)
# Create an GP model.
model = ndlml.gp(2, 12, X, Y, kern, noise, ndlml.gp.FTC, 100, 3)
resultsDir = os.path.join(".", dataSetName + str(experimentNo))
if not os.path.exists(resultsDir):
os.mkdir(resultsDir)
# set initial values to small random numbers.
X = np.random.normal(0.0, 1e-6, (len(tr.movieIDs()), q))
X_u = np.random.normal(0.0, 1e-6, (numActive, q))
lnsigma2 = math.log(startVar)
lnbeta = -math.log(startVar)
# Set up kernel functions
kernFtc = nl.cmpndKern(q)
kernSp = nl.cmpndKern(q)
kern1 = nl.rbfKern(q)
kern2 = nl.biasKern(q)
kern3 = nl.whiteKern(q)
kern4 = nl.whitefixedKern(q)
kern2.setVariance(0.11)
kern3.setVariance(math.exp(lnsigma2))
kern4.setVariance(1e-2)
kernFtc.addKern(kern1)
kernFtc.addKern(kern2)
kernFtc.addKern(kern3)