Looping through random variables

[junpenglao]

In your model you have a latent discrete variable, which is why sampling needs a BinaryGibbsMetropolis. In general, discrete latent variable are very difficult to inference, the general recommendation is that to treat it as a mixture model problem and rewrite it into a marginalized mixture model.

I think this post is the closest to your problem that you can start with:

Problem with hierachical occupancy model

I would do it this way: First reshape everything so within the pm.Model we are not dealing with dict: index = [] W_r = [] y_r = [] for i in range(n): index.append(np.ones((W[i].shape[0], 1))*i) W_r.append(W[i]) y_r.append(y[i][:, np.newaxis]) index = np.concatenate(index, axis=0).astype(int64) W_r = np.concatenate(W_r, axis=0) y_r = np.concatenate(y_r, axis=0) Then I will use matrix multiplication instead of nested for loops: with pm.Model() as m: beta = pm.Normal('beta', mu=…

See also:

Naive Bayes model with PyMC3

So here is how I would approach it: First, I would rewrite the explicit model, so that the observed is a flatten array - it is easier to handle shape wise: # flatten and index data data_flatten = np.reshape(data, data.shape[0]*data.shape[1]) data_index = np.repeat(np.arange(data.shape[0]), data.shape[1]) with pm.Model() as model: # Global topic distribution theta = pm.Dirichlet("theta", a=alpha) # Word distributions for K topics phi = pm.Dirichlet("phi", a=beta, shape=(K,…

It provides a way to marginalizing the latent discrete variables.