https://github.com/mahmoudimus/pyfastmap
A python implementation of FastMap, a fast algorithm for indexing, data-mining and visualization of traditional and multimedia datasets
https://github.com/mahmoudimus/pyfastmap
Last synced: 6 months ago
JSON representation
A python implementation of FastMap, a fast algorithm for indexing, data-mining and visualization of traditional and multimedia datasets
- Host: GitHub
- URL: https://github.com/mahmoudimus/pyfastmap
- Owner: mahmoudimus
- Created: 2010-06-07T08:00:24.000Z (almost 15 years ago)
- Default Branch: master
- Last Pushed: 2010-06-09T10:42:25.000Z (almost 15 years ago)
- Last Synced: 2024-04-14T06:25:33.088Z (about 1 year ago)
- Language: Python
- Homepage: http://blog.mahmoudimus.com/
- Size: 97.7 KB
- Stars: 14
- Watchers: 4
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README
Awesome Lists containing this project
README
FastMap originally implemented by Gunnar Aastrand Grimnes (http://gromgull.net)
StringMap and derivations are implemented by Mahmoud Abdelkader (http://blog.mahmoudimus.com)
TODO:
- StringMap unit tests
FastMap
-------
FastMap is a fast algorithm for indexing, data-mining, and visualization of traditional and multimedia datasets. It maps objects into points in some k-dimensional space (k is user-defined) such that the dis-similarities are preserved.
Two benefits from this mapping:
- efficient retrieval
- visualization and data-mining
The objects can now be plotted as points in 2-d or 3-d space, revealing potential clusters, correlations among attributes and other regularities that data-mining typically looks for.
StringMap
---------
StringMap is a modification of FastMap where the recursion is removed from the canonical `GetPivot()` implementation and the distance is measured in terms of a similarity function that returns a metric distance. It is a linear algorithm to d^2, where d is the dimensionality, or orthogonal directions, of the StringMap. See the reference paper: http://flamingo.ics.uci.edu/pub/dasfaa03.pdf