BayesFusion Support Forum

I suspect one or more nodes are based on a data column(s) with very large number of distinct values. If your data file has a unique identifier column, do not include it.

I used the new data for parameter learning, I completed the Match Network and Date steps, but the Learn Parameters with EM step did not appear? The EM options window should appear after you complete network/data matching. Did you get any error/crash message? The yellow exclamation mark icons appear...

GeNIe 4.0 is now available at https://download.bayesfusion.com. Most important new features are: discrete nodes with outcomes based on numeric intervals or point values metalog distribution, including interactive metalog builder tool geospatial processing added, Esri ASCII raster grids supported new...

To modify node's CPT, you should call set_node_definition. Refer to Tutorial 1 in SMILE Wrappers Manual - the tutorial program initializes the CPT with probabilities hardcoded into the Python source. In your case, you'll need to create an array from the CSV file, then call set_node_definition.

most sensitivity parameter for "L = good" is "I = L | D = L". That means this paramter will make the posterior probability of "L = good" change from 0.303756 to 0.314423. The output probability range from 0.303756 to 0.314423 is calculated for parameter spread=10% (the...

The most likely cause for this error message would be 32-bit Python environment and 64-bit pysmile.pyd module.

You can ignore the issue. Your model is closer to the perfect sum=1.0 distribution that our default epsilon.

Before we release new version, you can consider using the 'Complement' command in the columns with warnings to get perfect 1.0 total.

We tracked down this problem to GeNIe's algorithm for epsilon selection. If a column in the CPT has a very small non-zero probability (like 2e-25 in your example), it will be used for comparison of the total probabilities in the column with 1.0. The default epsilon is on the order of 1e-6. This algo...

I can't reproduce the problem. I have typed the numbers in your screenshots and got no warning icon with the 2e-25 value. Can you send me your xdsl file (use a forum private message if model contains confidential information). BTW: you can hover the mouse cursor over the warning icon sign and the pr...

Unfortunately, GeNIe does not support equation nodes in DBNs.

The tornado is ordered by the change in the target posterior when one of the parameters changes within the selected range. In your case the target is probability of the 'severe' outcome of the 'mental_health' node. The largest change in this probability would be caused by changing the appropriate en...

This error can be caused either by lost of arithmetic precision (for very large network), or by an inconsistent probabilities/evidence. Can you post your model so we can diagnose this? If it contains sensitive information, send me a private forum message with a download link.

For each record in the test set we set evidence if the value is present in the record and the node is not a class node. The inference is then performed and most likely outcome is selected as prediction. Prediction is compared with actual value in the test set, and the confusion matrix is updated acc...

Can you send me a link to your data file using private message on this forum?

Also, please note that GeNIe Academic is 32-bit only and its address space is limited to two gigabytes. I believe part of the problem here is dataset size.

For Maven-based Java builds it is now possible to use jSMILE from BayesFusion's Maven repository. For more details, read the "Platforms and Wrappers/Java and jSMILE/Maven" section in SMILE Wrappers manual at https://support.bayesfusion.com/docs.