zStupan

@GregaVrbancic I'm struggling to even get pipenv working on Ubuntu 22.04, It throws errors when trying to run pip install. I get the error `AttributeError: module 'collections' has no attribute...

I've made an attempt: ```python import numpy as np from niapy.algorithms import Algorithm from niapy.util.random import levy_flight from niapy.task import Task class SquirrelSearchAlgorithm(Algorithm): Name = ['SquirrelSearchAlgorithm', 'SSA'] def __init__(self, population_size=50,...

In terms of performance and speed numpy.ndarray is the clear winner. A numpy array of objects is insanely slow especially if you have to call the methods of those objects....

Algorithms using the `Individual` class: - ABC - CA - DE - ES - FSS - GA - MKE - HDE - jDE I suggest we refactor these to use...

@firefly-cpp Constraint handling can probably already be done by some sort of penalty method if you extend the Problem class, and something like ranking the solutions by degree of feasibility...

`run_iteration` is the main loop of the algorithm. Internally the run method looks something like this: ```python def run(self, task): population, fitness, params = self.init_population(task) best_individual, best_fitness = self.get_best(population, fitness)...

No problem. Yes, the run method is implemented in the [Algorithm base class](https://github.com/NiaOrg/NiaPy/blob/master/niapy/algorithms/algorithm.py). There is no need to change it. You only need to override `run_iteration` and `init_population`, if there's...

Problems with flake are fixed by #395. This PR can be closed.

@BrandonDuncan13 yes the results are different each time, but I would expect that the average fitness over 30 runs would be of similar magnitude as the results in the paper.