z = sin(x) + 0.5*cos(y)
ds.addSample(-2.5, -1)
ds.addSample(-1.0, 3)
gp.mean = 0
# new feature "autonoise" adds uncertainty to data depending on
# it's distance to other points in the dataset. not tested much yet.
# gp.autonoise = True
gp.trainOnDataset(ds)
gp.plotCurves(showSamples=True)
# you can also test the gp on single points, but this deletes the
# original testing grid. it can be restored with a call to _buildGrid()
print(gp.testOnArray(array([[0.4]])))
# --- example on how to use the GP in 2 dimensions
ds = SupervisedDataSet(2,1)
gp = GaussianProcess(indim=2, start=0, stop=5, step=0.25)
figure()
x,y = mgrid[0:5:4j, 0:5:4j]
z = cos(x)*sin(y)
(x, y, z) = list(map(ravel, [x, y, z]))
for i,j,k in zip(x, y, z):
ds.addSample([i, j], [k])
z = sin(x) + 0.5*cos(y)
ds.addSample(-2.5, -1)
ds.addSample(-1.0, 3)
gp.mean = 0
# new feature "autonoise" adds uncertainty to data depending on
# it's distance to other points in the dataset. not tested much yet.
# gp.autonoise = True
gp.trainOnDataset(ds)
gp.plotCurves(showSamples=True)
# you can also test the gp on single points, but this deletes the
# original testing grid. it can be restored with a call to _buildGrid()
print gp.testOnArray(array([[0.4]]))
# --- example on how to use the GP in 2 dimensions
ds = SupervisedDataSet(2,1)
gp = GaussianProcess(indim=2, start=0, stop=5, step=0.25)
figure()
x,y = mgrid[0:5:4j, 0:5:4j]
z = cos(x)*sin(y)
(x, y, z) = map(ravel, [x, y, z])
for i,j,k in zip(x, y, z):
ds.addSample([i, j], [k])
z = sin(x) + 0.5*cos(y)
ds.addSample(-2.5, -1)
ds.addSample(-1.0, 3)
gp.mean = 0
# new feature "autonoise" adds uncertainty to data depending on
# it's distance to other points in the dataset. not tested much yet.
# gp.autonoise = True
gp.trainOnDataset(ds)
gp.plotCurves(showSamples=True)
# you can also test the gp on single points, but this deletes the
# original testing grid. it can be restored with a call to _buildGrid()
print(gp.testOnArray(array([[0.4]])))
# --- example on how to use the GP in 2 dimensions
ds = SupervisedDataSet(2,1)
gp = GaussianProcess(indim=2, start=0, stop=5, step=0.25)
figure()
x,y = mgrid[0:5:4j, 0:5:4j]
z = cos(x)*sin(y)
(x, y, z) = list(map(ravel, [x, y, z]))
for i,j,k in zip(x, y, z):
ds.addSample([i, j], [k])
z = sin(x) + 0.5 * cos(y)
ds.addSample(-2.5, -1)
ds.addSample(-1.0, 3)
gp.mean = 0
# new feature "autonoise" adds uncertainty to data depending on
# it's distance to other points in the dataset. not tested much yet.
# gp.autonoise = True
gp.trainOnDataset(ds)
gp.plotCurves(showSamples=True)
# you can also test the gp on single points, but this deletes the
# original testing grid. it can be restored with a call to _buildGrid()
print gp.testOnArray(array([[0.4]]))
# --- example on how to use the GP in 2 dimensions
ds = SupervisedDataSet(2, 1)
gp = GaussianProcess(indim=2, start=0, stop=5, step=0.25)
figure()
x, y = mgrid[0:5:4j, 0:5:4j]
z = cos(x) * sin(y)
(x, y, z) = map(ravel, [x, y, z])
for i, j, k in zip(x, y, z):
ds.addSample([i, j], [k])
print "preparing plots. this can take a few seconds..."
