ManchesterBioinference / GP_Transcription_Dynamics

1 stars 1 forks source link

simulated_examples.py gives "predicted y failed, predicted f" #3

Closed jakeyeung closed 1 year ago

jakeyeung commented 1 year ago

Hi GP team,

Thanks so much for helping me out.

I managed to get the simulated_examples.py running but when trying to run trcd.model.predict_y() it is giving an error NameError: name 'F' is not defined.

In the simulation code, this happens when trying to run plot_trcd_predict().

The function still runs but gives predicted y failed, predicted f

Any reason why it is unable to predict_y() in the simulation?

Kindest regards,

Jake

YuliyaShapovalova commented 1 year ago

Hi Jake,

Currently, plot_trcd_predict() uses only the trcd.predict_f() function. The uncertainty due to the measurement noise is added in the plot_trcd_predict() function through the terms with the parameters var_m_noise and var_p_noise.

predicted y failed, predicted f is just a warning, mostly for internal use. We probably will incorporate a more elegant solution in the future. But for now, if you are interested in predictions of y (i.e., with uncertainty due to both f and the measurement noise), the function already works as intended. If you are interested in the prediction of only f, you can remove the terms with var_m_noise and var_p_noise in them from the plot_trcd_predict() function.