BayesFusion Support Forum

You are trying to run modified Tutorial1 code - in that code self refers to object of Tutorial1 class. Try to remove all self calls from your code and move create_cpt_node fuction definition before calling it.

You can learn more about self from here: https://www.w3schools.com/python/gloss_python ...

All available functions could be listed by Python help command e.g. help(pysmile.Network) in Python Interpreter command line.

Below is output of this command for Network Class:


class Network(pybind11_builtins.pybind11_object)
| Method resolution order:
| Network
| pybind11_builtins.pybind11 ...

To access Diagnostic Values you have to create DiagNetwork object based on existing Network object.


Network net = new Network();
// do some stuff or load network from file
DiagNetwork diagNetwork = new DiagNetwork(network);


To create a DiagNetwork object, the Network must meet several ...

You don't need to unpack the .zip archive. Besides, if you have files locally, you need to set the repo parameter to NULL and specify the library type - win.library.

The full command for installation will look like this:

install.packages("path_to_zip_archive", repos = NULL, type = "win.binary ...

Could you try to use PySMILE outside a venv? For testing purposes only - to check if it is really a problem of the virtual environment. I wasn't able to recreate an error (both inside and outside venv) so any additional information will be helpful.

PySMILE 1.6.2 should contain learning fix.

Have you tried to run PySMILE without using venv? Also - could you check if "home" variable in pyenv.cfg file (top of venv folder structure) points to directory which contains python39.dll file?

At first, you have to unistall pysmile version 0.2

pip uninstall pysmile

Second - to get the correct version from our index, use the command below:

pip install --no-cache-dir --index-url https://support.bayesfusion.com/pysmile-B/ pysmile

Note that PySMILE may not be fully compatible with the ...

You can use PySMILE code with Python multiprocessing package, like below:


import pysmile
import pysmile_license
import multiprocessing
import time

ds = pysmile.learning.DataSet()
ds.read_file("[path_to_dataset_file]")

def learn_net_from_dataset(ds):
bs = pysmile.learning.BayesianSearch()
bs ...

Pip installs PySMILE from local cache. You have to uninstall PySMILE again (pip uninstall pysmile) and install with command: "pip install --no-cache-dir --index-url https://support.bayesfusion.com/pysmile-A/ pysmile"

It seems you installed Pysmile package from official pip repository - it is package unrelated with our PySMILE.
First - you have to uninstall this package with command:
pip uninstall pysmile
Next - remove pysmile.so file from your directory and install from our index by typing:
pip install ...

It is probably a mismatch between the PySMILE and Python version installed.

Remove pysmile.so and pysmile.pyd from directory you are trying to run program, then uninstall locally cached PySMILE package by typing:
python -m pip uninstall pysmile
in your terminal.

Next, download recent version of ...

Ad 1:
There could be mismatch between DataSet and Network. If your network contains deterministic nodes and dataset contains informations conflicting with network EM Algorithm will not work.

You can attach DataSet and XDSL to next message - this will allow us to check what is wrong.


Ad 2:

There ...

a=net.get_node_value(net.get_node_id(h),i)


get_node_value method call is invalid - it takes only one argument (node ID or handle). I am not sure if this loop is necessary

while i<=len(v):
a=net.get_node_value(net.get_node_id(h),i)
res.append(a)
i=i+1

Because you already have node value ...

I assume you managed to create a network in GeNIe.

Do I understand correctly that you want to connect all nodes from one layer with all nodes of another layer including time steps?

Package installed by pip is not BayesFusion's PySMILE. To use PySMILE, you need to uninstall pysmile installed by pip.
pip uninstall pysmile
Download PySMILE from our website - https://download.bayesfusion.com/ and uncompress archive in your project directory.

Note that PySMILE works with ...