Metadata-Version: 2.4
Name: frosted_tracks
Version: 1.1.0
Summary: Behavioral segmentation and clustering of trajectory data.
License-Expression: BSD-3-Clause
License-File: LICENSE
Keywords: clustering,ticc,dbscan,trajectories,tracktable
Author: Andy Wilson
Author-email: atwilso@sandia.gov 
Maintainer: Andy Wilson
Maintainer-email: atwilso@sandia.gov 
Requires-Python: >=3.9
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: BSD License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Requires-Dist: fast_ticc (>=1.0.1)
Requires-Dist: metric_dbscan (>=1.0.0)
Requires-Dist: numba (>=0.53.0)
Requires-Dist: numpy (>=1.22)
Requires-Dist: pandas (>=2.2.0)
Requires-Dist: pillow (>=12.2.0)
Requires-Dist: requests (>=2.33.0)
Requires-Dist: scikit-learn (>=1.0.0)
Requires-Dist: scipy (>=1.10.0)
Requires-Dist: tqdm (>4.60)
Requires-Dist: tracktable (>=1.7.0)
Project-URL: Homepage, https://github.com/sandialabs/frosted_tracks
Project-URL: Issues, https://github.com/sandialabs/frosted_tracks/issues
Description-Content-Type: text/markdown

# Frosted Tracks

Analysis of trajectory behavior using TICC and DBSCAN

## Repository Structure

- `src/`: Source code

Best practice: prototype code in a notebook, then move it into
src/frosted_tracks with proper docstrings and test cases when it's
ready to share.  Open a pull request to our GitHub repository if
you'd like to integrate your work into the main trunk!

## Python Environment

We recommend that you use Anaconda (https://www.anaconda.com) for your
Python environment.  If you do, there's an `environment.yml` file in this
repository that you can use to set up your dependencies as follows:

```bash
conda env create -f environment.yml
```

## License

See the file LICENSE in the root directory of the repository for
details.  We release this work under a 3-clause BSD license.


## Changes

Version 1.0: Initial release.  Not distributed to PyPI.

Version 1.1: Experimental cluster predictor disconnected.  It was causing 
    build errors when we tried to construct wheels.  You must now supply
    the desired number of clusters when you call cluster_trajectories.

