Skip to content

Latest commit

 

History

History
65 lines (51 loc) · 2.63 KB

README.md

File metadata and controls

65 lines (51 loc) · 2.63 KB
Raw

Build Status

ACO-GRAANK

A Python implementation of the ACO-GRAANK algorithm. The algorithm utilizes a pheromone-based (or probabilistic) strategy to optimize the GRAANK algorithm. The algorithm converges as the pheromone matrix values approach saturation. The research paper is available via this link:

Requirements:

You will be required to install the following python dependencies before using ACO-GRAANK algorithm:

                   install python (version => 3.6)


                    $ pip3 install numpy pandas ypstruct~=0.0.2 sortedcontainers~=2.4.0 scikit-fuzzy~=0.4.0 python-dateutil~=2.8.2 matplotlib~=3.4.2

Usage:

Use it a command line program with the local package to mine gradual patterns:

For example we executed the ACO-GRAANK algorithm on a sample data-set

$python3 src/main.py -a 'aco' -f data/DATASET.csv

where you specify the input parameters as follows:

  • filename.csv - [required] a file in csv format
  • minSup - [optional] minimum support default = 0.5

Output

1. Age
2. Salary
3. Cars
4. Expenses

File: ../data/DATASET.csv

Pattern : Support
[('2', '+'), ('4', '-')] : 0.6
[('1', '-'), ('2', '-')] : 0.6
[('1', '-'), ('4', '+')] : 1.0
[('1', '+'), ('2', '+'), ('4', '-')] : 0.6
[('1', '+'), ('4', '-')] : 1.0
[('2', '-'), ('4', '+')] : 0.6
[('1', '+'), ('2', '+')] : 0.6
[('1', '-'), ('2', '-'), ('4', '+')] : 0.6

Pheromone Matrix
[[4 4 3]
 [4 4 3]
 [1 1 9]
 [4 4 3]]
0.08473014831542969 seconds

License:

  • MIT

References

  • Dickson Owuor, Anne Laurent, and Joseph Orero (2019). Mining Fuzzy-temporal Gradual Patterns. In the proceedings of the 2019 IEEE International Conference on Fuzzy Systems (FuzzIEEE). IEEE. https://doi.org/10.1109/FUZZ-IEEE.2019.8858883.
  • Runkler, T. A. (2005), Ant colony optimization of clustering models. Int. J. Intell. Syst., 20: 1233-1251. https://doi.org/10.1002/int.20111
  • Anne Laurent, Marie-Jeanne Lesot, and Maria Rifqi. 2009. GRAANK: Exploiting Rank Correlations for Extracting Gradual Itemsets. In Proceedings of the 8th International Conference on Flexible Query Answering Systems (FQAS '09). Springer-Verlag, Berlin, Heidelberg, 382-393.