BayesFusion Support Forum

Please note that cooer representing the sensitivity of the node in GeNIe's graphical view is based on the max sensitivity over all node's CPT entries. I'd go for the max as the quantitive value. A node does not have a single derivative, there's one for each probability in node's definition.

I also found that by default `model.get_rand_seed()` is 0. When it is zero, the inference result will change each time I run.
After using `model.set_rand_seed(seed)` to set a non-zero seed, the result for each run is consistent.

That is correct. Using the seed equal to zero will initialize the ...

(1) Why even though I set a specific seed, each time I print the posterior of target variable, it still has variability?

This should not happen, the pseudorandom generator is seeded from the value specified in network properties. If you can share your model, we can investigate this.

(2) During ...

GeNIe does not have the command to show all posterior probabilities. There's a Bulk Update option which iterates over rows in the datafile and outputs probabilities; the output file can be easily loaded into Excel. You can also switch node view to barchart, which gives you instant visualization of ...

To switch the inference algorithm to EPIS use set_bayesian_algorithm with pysmile.BayesianAlgorithmType.EPIS_SAMPLING:
net.set_bayesian_algorithm(pysmile.BayesianAlgorithmType.EPIS_SAMPLING)

Regarding explicit relevance targets in the network, here's the info from the wrappers manual
Network ...

The inference in fully continuous and hybrid networks works the same way. If there's no evidence for nodes with parents which do not have evidence, forward sampling is used (this includes the hybrid case).

If there's evidence in nodes which have parents without evidence, the network will be ...

Network.set_controlled_value works just like set_evidence - you specify the node and the outcome. Calling this function is the equivalent of using 'Control Value' in GeNIe - in GeNIe the Control Value submenu has the entries for all node outcomes.

Error -42 is caused by insufficient memory in exact inference algorithm. This algorithm creates temporary data structure (the join tree), which can become very large, depending on the connections in the network.

You can switch to approximate sampling inference (EPIS), or set explicit targets in the ...

BTW, if you want to move this conversation into private space, email me or send me a forum PM.

One more thing, we're now working on additional structure learning algorithms and there will be a way to calculate BIC for network+dataset directly.

Consider using Network.set_controlled_value. For more info on arc cutting/value control, please refer to GeNIe manual, chapter "Controlling values". In the PDF version of the manual, the chapter number is 6.2.8.

BTW, you can use GeNIe to calculate loglikelihood for a dataset/network without learning. This functionality is not exposed in PySMILE, however.

You can obtain the log likelihood after EM by calling the EM.get_last_score() method.

BayesianSearch.get_last_score() returns the Bayesian score after learning.

Currently there's no method to calculate BIC from the dataset and network without learning.

I confirm that SMILE does not support parameter learning in hybrid networks.

Correct, the .so file from the .tar.gz archive is for the scenario where you do not use pip.