Pymc3: AttributeError: module 'pymc3.gp' has no attribut 'Marginal'

Created on 21 Sep 2017  路  4Comments  路  Source: pymc-devs/pymc3

Hi,

I was running the Gaussian process example code of pymc3 and found that many attribute are not in this module.

X = np.linspace(0, 1, 10)[:, None]

with pm.Model() as model:
# Specify the covariance function.
cov_func = pm.gp.cov.ExpQuad(1, 0.1)

# Specify the GP.  The default mean function is `Zero`.
gp = pm.gp.Marginal(cov_func=cov_func)

# Place a GP prior over the function f.
sigma = pm.HalfCauchy("sigma", beta=3)
y_ = gp.marginal_likelihood("y", X=X, y=y, noise=sigma)

AttributeError: module 'pymc3.gp' has no attribute 'Marginal'

Most helpful comment

That makes sense; gp.Marginal was introduced after the 3.1 release. Try installing the master branch instead:

pip install git+https://github.com/pymc-devs/pymc3

All 4 comments

What version of PyMC3 are you running? How did you install it?

It is version 3.1 and I installed by pip.

That makes sense; gp.Marginal was introduced after the 3.1 release. Try installing the master branch instead:

pip install git+https://github.com/pymc-devs/pymc3

It works! Thanks!

Was this page helpful?
0 / 5 - 0 ratings