search

RJT1990 / pyflux

Open source time series library for Python
BSD 3-Clause "New" or "Revised" License
2.1k stars 240 forks source link

model.predict give error: No latent variables estimated! #157

Closed altineel closed 2 years ago

altineel commented 4 years ago

Here is the following code that I'm trying to run but the model raise an exception of 'No latent variables estimated!'. I got the reason of error that latent variables weren't updated but if I fit the model then I can't call the method of 'predict()' on the fitted model. Could you help about it ?

dynamic_reg_model1 = pyflux.DynReg('traffic_volume ~ week_day + hour', data = train[-100:][['traffic_volume','week_day','hour']])
dynamic_reg_model1.plot_predict(10,train[0:100][['traffic_volume','week_day','hour']])