Jinyu Xie

Hi, Sorry for the late reply. For now, you can only specify carbohydrate in the CustomScenario. To have a scenario where the patient takes carb but no insulin, you need...

Hi Kasun, 1. There is no big difference between using your own custom controller or built-in basal_bolus_controller. I was saying that if you need to keep the basal (so the...

@aacelik Thanks! I will take a look. If you want to go head and fix it, please send me a pull request :)

Hi thanks for asking. I don't think I have the bandwidth to upgrade it in the near future. Another potential blocker for this upgrade is that I don't have a...

Yes, I did not expose the meal as an action here. I treat the random meal as a challenge for the control algorithm. You might want to implement the meal...

Hi, you can only control the insulin through the action of the environment. Do you mean you want to also change CHO through the action?

BBController needs meal information (how much carb is taken by the patient currently) to determine the bolus amount, but this meal information is not necessary for a controller. You can...

Hi, Thanks for raising this. The risk index function has a horizon meaning how many samples in the past you want to average on. For example, at time = 10,...

This might be a dependency issue. Mine is good. I feel there is some updates in pandas causing this issue, but I agree the report function is written in quite...

Historical target values (e.g. y(t-1), y(t-2), are used as features to predict the future target value. For example, if you build a NARX(RandomForestRegressor(), auto_order=2, exog_order=[1], exog_delay=[0]), the predicted value y(t...