NEMS is the Neural Encoding Model System. It is helpful for fitting a mathematical model to time series data, plotting the model predictions, and comparing the predictive accuracy of multiple models. We use it to develop and test computational models of how sound is encoded in the brains of behaving mammals, but it will work with many different types of timeseries data.
Full documentation can be found here.
Direct link to the some demos. We also have a Gitter chat where you can get help from other users.
If you don’t already have Python and Git installed, see the installation instructions for recommended procedures.
If you already have Python and Git, download NEMS:
git clone https://github.com/lbhb/NEMS
Add the NEMS library via pip (where ./NEMS
is the installation directory and -e
means editable mode):
pip install -e ./NEMS
NEMS libraries should now be loadable. See next section for how to try it out!
You may test if everything is working by telling NEMS to download some sample auditory stimulus-response data, use a simple linear-nonlinear model (which should taking about 2 minutes to fit), and then save the results locally:
cd NEMS/scripts ipython In [1]: run demo_script.py
Or open demo_script.py
in an editor to work through each step of
the fit.
If you have Jupyter installed:
cd NEMS/notebooks jupter notebook
Click on demo_xforms.ipynb
and give it a whirl!