Train an IOHMM with independent chains

[aminzadenoori]

I want to train an IOHMM with different independent sequences and I don't know how to specify them on the only one input panda data frame. Can you explain to me the fields corr and prev briefly and how to use them, please?

[BSharmi]

I have similar question. Would really appreciate on more description on usage of the model with multiple sequences and how to specify covariates_initial, covariates_transition. Thank you

[Mogeng]

Can you explain what do you mean by "different independent sequences"? Are they supposed to share the same initial / transition / emission model? If no, you should just train each sequence individually. If yes, you can do the following:

In the example notebook, when we set the data, we use SHMM.set_data([speed]). This model can take a list of data frames with each data frame representing a sequence. So you will end up with having something like: SHMM.set_data([df1, df2, df3]).

Since these sequence should share the same initial / transition / emission model, you will specify them as if there were just one sequence.