y=list(y.queue),
z=list(z.queue),
besties=list(besties.queue),
names=list(names.queue),
iters=list(iters.queue),
metric=metric,
path=self.path2,
n_gen=n_gen - 1,
self=self)
if __name__ == '__main__':
createDummies = False
normalize = False
name = 'madelon'
var = 'Class'
d = data.Data(name, var, [], [])
d2, target, copy, copy2, copy3, copy4, dummiesLst, ratio, chi2, anova2, originLst =\
d.ready(deleteCols=True, dropna=True, thresholdDrop=70, createDummies=True, normalize=False)
pso = PSO(d2, d, ['lr'], target, originLst, name)
pop = 5
gen = 5
w = 0.5
c1 = 0.5
c2 = 0.5
g1, g2, g3, g4, g5 = pso.init(pop, gen, w, c1, c2, copy2, dummiesLst,
createDummies, normalize, 'accuracy')
import machineLearning.config as cfg
from machineLearning import data, genetic, differential, swarm, hill, tabu, simulated, vns, iterated
if __name__ == '__main__':
d = data.Data(name=cfg.general['dataset'],
target=cfg.general['target'],
dropColsList=cfg.general['dropcol'],
dropClassList=cfg.general['dropclass'])
d2, target, copy, copy2, copy3, copy4, dummiesLst, ratio, chi2, anova, origin =\
d.ready(deleteCols=cfg.general['deletecol'], dropna=cfg.general['dropna'],
thresholdDrop=cfg.general['thresholddrop'], createDummies=cfg.general['createdummies'],
normalize=cfg.general['normalize'])
methods = cfg.general['method']
name = cfg.general['dataset']
createDummies = cfg.general['createdummies']
normalize = cfg.general['normalize']
metric = cfg.general['metric']
if cfg.general['heuristic'] == 'genetic':
heuristic = genetic.Genetic(d2, d, methods, target, origin, name)
g1, g2, g3, g4, g5 = heuristic.init(n_pop=cfg.genetic['pop'],
n_gen=cfg.genetic['gen'],
n_mut=cfg.genetic['mut'],
data=copy2,
dummiesList=d.dummiesList,
createDummies=createDummies,
normalize=normalize,
metric=metric)
elif cfg.general['heuristic'] == 'differential':
heuristic = differential.Differential(d2, d, methods, target, origin,
name)