Label and track unique geospatial features from gridded datasets
Ocetrac is a Python 3.6+ packaged designed to label and track unique geospatial features from gridded datasets. The package is designed to accept data that have already been preprocessed, meaning that the data only contain values the user is interested in tracking. Ocetrac operates lazily with Dask so that it is memory uninhibited and fast through parallelized execution. We provide examples and demonstrate best practices as developed by the Climate Data Science Lab at Columbia University / Lamont-Doherty Earth Observatory.
When using this package, please cite the original software.
To install the core package from conda-forge run:
conda install -c conda-forge ocetrac
To install the core package run:
pip install ocetrac.
- Clone ocetrac to your local machine:
git clone https://github.com/ocetrac/ocetrac.git
- Change to the parent directory of ocetrac
- Install ocetrac with
pip install -e ./ocetrac. This will allow changes you make locally, to be reflected when you import the package in Python.
How you can contribute
- You can get involved by trying ocetrac, filing issues if you find problems, and making pull requests if you make improvements.
- We rely heavily on scikit-image and its community of contributors.
- This work grew from a collabortion with NCAR during the ASP Graduate Visitor Program attended by Hillary Scannell. This project recieved continued support from the Leonardo DiCaprio Foundation, Microsoft, and the Gordon and Betty Moore Foundation.
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.