Classification with Automated Semi-Supervised Algorithms (CASSA) package
Overview
CASSA is a Python package to perform unsupervised and semi-supervised machine learning (ML) classification algorithms on generic tensors of pre-processed data, such as time series, altitude profiles, images, DDMs and spectra. Mainly tested on Earth Observation (EO) satellites data, such as GNSS-RO sTEC profiles and GNSS-R DDMs. It produces a database of labeled clusters that can be used to classify new unlabeled data.
The documentation is available at https://cassa.readthedocs.io/en/latest/.
It includes the following blocks:
- Parallelized distance matrix computation using earth mover's distance (EMD, aka Wasserstein metric)
- Spetral clustering using precomputed distance matrix
- Self-tuned spectral clustering using precomputed distance matrix
- HDBSCAN clustering using precomputed distance matrix
- Classification of new data based on database of labeled clusters
Installation
pip install cassa
Authors
- Giorgio Savastano (giorgiosavastano@gmail.com)
- Karl Nordstrom (karl.am.nordstrom@gmail.com)
References
Savastano, G., K. Nordström, and M. J. Angling (2022), Semi-supervised Classification of Lower-Ionospheric Perturbations using GNSS Radio Occultation Observations from Spire’s Cubesat Constellation. Submitt. to JSWSC.
1 maintainer
Metadata
1 maintainer
Release files for cassa 2.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| cassa-2.1.1.tar.gz | 7.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| cassa-2.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 14.3 kB
Release files / cassa-2.1.1.tar.gz
| Download URL | cassa-2.1.1.tar.gz |
|---|---|
| Size | 7.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f83809163d44bf25e0c02db710a280c2c257756e75db930b2273e79dca1507e6
|
|
BLAKE2b-256 checksum How to use checksums |
78cb521f28aa54d7219f8e02ad8234002af2bdfdf3caf9868b4087e2aa3e3ca5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.1.13 CPython/3.10.2 Linux/5.13.0-1022-azure
|
Release files / cassa-2.1.1-py3-none-any.whl
| Download URL | cassa-2.1.1-py3-none-any.whl |
|---|---|
| Size | 7.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c1eedd82c1af41127067d67bb33ac3dcfe68c48cbf86505285768ee9af05fb8d
|
|
BLAKE2b-256 checksum How to use checksums |
7f4827e771aae0ff3b939d06a7d9b7acfdd4e4ba2a098495a09b5d59620513d5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.1.13 CPython/3.10.2 Linux/5.13.0-1022-azure
|
