Is it possible to specify equation bounds when learning using PC?

[maghnie]

I used PC to learn the structure and parameters of a BN (see attached screenshot).
The raw data contained time series of 4 temperature sensors in an air handling unit.

Now, I'd like to set evidence in the outdoor air temperature (ODA), which intuitively would be a temperature in Celsius degrees between -20 and 40. However, it appears that it's only possible to set evidence between -1 and 1.

So, is it possible to change the bounds? Or is there another way to set the evidence for the layperson?

Thanks for your time!

[shooltz[BayesFusion]]

The bounds can be edited after learning - simply enter -20 and 40 as lower and upper bound.

[maghnie]

Thank you for the quick answer!

My bad, I had tried setting the bounds like that last night, but thought I did something wrong when I saw overflow/underflow warning messages. 😅

I see now from this post and the Autodiscretization help page, that this is mostly normal.

[shooltz[BayesFusion]]

The default [-1, +1] bounds should be modified by the PC algorithm. It should be either an open interval (-inf,+inf), or values from the learning data, rounded or not.

I've added an item to our feature tracker, and we will make this modification before the next release.

[maghnie]

That would be yet another great feature - thank you!