How-To Guide

Familiarize with NeMoS modules and learn how to take advantage of the pynapple and scikit-learn compatibility.

Additional requirements

To run the tutorials, you may need to install some additional packages used for plotting and data fetching. You can install all of the required packages with the following command:

pip install nemos[examples]

• GLM Demo: Toy Model Examples
  • Introduction
  • The Feed-Forward GLM
  • K-fold Cross Validation with sklearn
  • Simulate Spikes
  • Simulate a Recurrently Coupled Network
  • References

• Population GLM
  • Fitting a Population GLM
  • Neuron-specific features
  • FeaturePytree

• Batching example
  • Simulate data
  • Model configuration
  • Basis instantiation
  • Batch definition
  • Solver initialization
  • Batch learning
  • Model comparison

• Using bases as scikit-learn transformers
  • scikit-learn Transformers and NeMoS Basis
  • From Basis to TransformerBasis
  • Setting up the TransformerBasis

• Selecting basis by cross-validation with scikit-learn
  • What is a scikit-learn pipeline
  • Why pipelines are useful
  • Combining basis transformations and GLM in a pipeline
  • Create a custom scorer

• FeaturePytree example
  • FeaturePytrees
  • FeaturePytrees and GLM

• Construct Design Matrices for Categorical Features
  • Design Matrix with patsy
  • Categorical Predictors and Basis Functions

• Precomputed Features
  • Incorporating Precomputed Features into GLM Design

• Fit GLMs For Neural Coupling
  • Setting up a Fully Coupled GLM
  • Interpreting the coefficients
  • Selecting The Connectivity Map