viniciusarruda / ga-pso-fuzzy-classifier

Classifing the iris dataset with fuzzy logic, genetic algorithm and particle swarm optimization.

This was an assignment of the subject Natural Computing, described in the file NC-TAREFACOMPUTACIONAL2-2019-2.pdf(in portuguese).

Run

Using python 3:

pip install -r requirements.txt

then:

python main.py

The code will run GA and PSO* for 30 times each and show the boxplot for the accuracies found for the iris dataset.

*The PSO implementation is from https://github.com/nathanrooy/particle-swarm-optimization

How the classifier works

The file RelatorioComputacaoNatural2.pdf reports how it was built (in portuguese).

This work was based on the paper Implementing a Fuzzy Classifier and Improving its Accuracy using Genetic Algorithms with the same settings for the classifier, changing only the evolutionary algorithms.