Machine learning for Project Cognoma

This repository hosts machine learning code and discussion (see Issues) for Project Cognoma.

Environment

This repository uses conda to manage its environment and install packages. If you don't have conda installed on your system, you can download it here. You can install the Python 2 or 3 version of Miniconda (or Anaconda), which determines the Python version of your root environment. Since we create a dedicated environment for this project, named cognoma-machine-learning whose explicit dependencies are specified in environment.yml, the version of your root environment will not be relevant.

With conda, you can create the cognoma-machine-learning environment by running the following from the root directory of this repository:

# Create or overwrite the cognoma-machine-learning conda environment
conda env create --quiet --force --file environment.yml

If environment.yml has changed since you created the environment, run the following update command:

conda env update --file environment.yml

Activate the environment by running source activate cognoma-machine-learning on Linux or OS X and activate cognoma-machine-learning on Windows. Once this environment is active in a terminal, run jupyter notebook to start a notebook server.

cognoml package

This repository contains a python package named cognoml. For development, the package can be installed locally. First, make sure the cognoma-machine-learning environment is activated, so the cognoml is only installed for this environment. Then install using the following command from this repository's root directory:

pip install --editable .