Petrônio Cândido de Lima e Silva

Hi @ramdhan1989 Thanks for your interest in our tool, and forgive-me for the long delay. First of all, before hyperparameter optimization (hereafter called hyperopt), you should perform the time series...

Hi @ramdhan1989 Using this dictionary you can build a model with this code: ``` from pyFTS.hyperparam import Evolutionary model = Evolutionary.phenotype( dictionary, #the result of the hyperparameter method train, #The...

Hi! Unfortunately the FCMpartitioner is not yet adapted to work with multivariate data. I will research an alternative solution for this problem and give you a feedback as soon as...

Can you share the data and code you already tried?

We started to develop Fuzzy Cognitive Maps for FTS. Do you want to contribute to us?

Hi! I will look your question in detail and the code in detail, but a priori the model evaluation use rmse(dataum[model.order:], forecast[:-1]) [for Chen.ConventionalFTS the model.order = 1). If this...

Hi @smejiame ! Sorry for the long delay. Well... Order 12? Are you sure that this is really needed? The training process will be very long and the final model...

Hi @kdal1210 !! Sorry for the long delay! I hope are you enjoying the pyFTS! :-) Can you share the data and code that you are working with? Best regards

Hi George, I think you are talking about many steps ahead forecast. For this kind of forecasts just inform the parameter steps_ahead=k (where k is the forecasting horizon) in the...

George, How did you analyze this time series? Did you check the ACF and the PACF? How long is its memory? Why did you decide to use 190 partitions? Did...