xkianteb / dbscan_analysis

A comparison between using kd-Tree and vp-tree for dbscan

dbscan_analysis

Software Requirements:

* Homebrew:
    - http://brew.sh
* R - statiscal computing:
    - brew update
    - brew install Caskroom/cask/xquartz
    - brew tap homebrew/science
    - brew install homebrew/science/r
    - Instruction above found at this link: https://davidsimpson.me/2013/02/26/installing-r-on-os-x/
* mlbench - Machine Learning Benchmark Problems:
    - http://cran.r-project.org/web/packages/mlbench/index.html
    - R CMD INSTALL mlbench_2r.1-1.tar

Data:

* Data will be created using mlbench
    - This stack overflow post shows the 6 different datasets that will be potentially used:
        - http://stackoverflow.com/questions/4722290/generating-synthetic-datasets
    - mlbench method docmentation can be located at the following link:
    	- http://stackoverflow.com/questions/4722290/generating-synthetic-datasets

kd-Tree:

https://sites.google.com/site/mikescoderama/Home/kd-tree-knn

DBSCAN:

https://github.com/choffstein/dbscan/tree/master/dbscan

VP-Tree:

https://github.com/huyng/algorithms/tree/master/vptree