Thanks Julia, great work

Hi Julia. Thank you for the PR. We should have discussed about the changes before you worked on it. I found an issue about the DatasetEphy that I first need to solve before Neo support. And its probably to change the form of the PR. I'll let you know once I found a solution.

@EtienneCmb No worry, you can first improve DatasetEphy and then we can adjust this PR. Any idea why the installation of the the neo does not seem to work for the CI? Is it caching the environment somehow?

I guess neo have to be installed also for github action (workflow)

@EtienneCmb Any progress on the restructuring of the DatasetEphy, so I can adjust this PR accordingly?

Hi @JuliaSprenger

I'm currently testing the new implementation on the develop branch. We should take a coffee and discuss about the best way to integrate neo inside Frites.

Hi @EtienneCmb I am not sure I understand your concept behind the sim_mi.py module. To me it looks like in many places the suj_ephy functionality could be used there for converting the data, but probably you had something else in mind.

Hi @EtienneCmb I am not sure I understand your concept behind the sim_mi.py module. To me it looks like in many places the suj_ephy functionality could be used there for converting the data, but probably you had something else in mind.

@EtienneCmb Any opinion on this?

Hi @JuliaSprenger, the sim_mi.py file contains functions to simulate data with statistical dependencies. This is mainly used for illustrating Frites' functions. You're right, it could use internally the suj_ephy to return an object "ready to use" in other functions. However, since not every users are familiar with xarray, I thought that returning standard NumPy arrays and then performing the conversion manually was probably clearer

@EtienneCmb So does it make sense to you to also add Neo support in the sim_mi module or is this rather minimal code for demonstration purposes that should not be cluttered with additional data format cases?

I would keep it simple, using NumPy. If you want to illustrate the functionalities with Neo, I would just add an example here.

For illustrating input types like MNE / NumPy / Xarray, I usually generate random data with NumPy and then convert them to MNE or Xarray for example. Could we do the same with neo?

Instead of having many :

try:
 import neo
 HAVE_NEO = True
except ModuleNotFoundError:
 HAVE_NEO = False

Could you make a is_neo_installed function in io_dependencies.py for testing if neo is installed?