def run(self, generation):
runned_generation = list()
data_reader = DataReader.getInstance()
X, Y, X_test, X_output = data_reader.read_data()
#for each gene of this generation
for i in range(0, len(generation)):
this_gene = generation[i]
# runner is which algorithm will I use:
# 0 is XGBoost Classifier
# 1 is XGBoost regressor
# 2 is SVC
# 3 is DecisionTreeClassifier
# 4 is AdaBoost applied to DecisionTreeClassifier
# 5 is GradientBoosting
# 6 is KNeighbors
# 7 is RandomForest
# 8 is RandomForest but simplified (more defaults and less configuration)
runner = None
if (this_gene.way == 0):
runner = TitanicBoostClassifier()
else:
if (this_gene.way == 1):
runner = TitanicBoostRegressor()
else:
runner = VariousForests()
runner.set_datasets(X, Y, X_test, X_output)
runner.set_gene_to_model(this_gene) #here we configure the model
this_gene.set_fitness_level(runner.run())
runned_generation.append(this_gene)
return runned_generation
https://www.kaggle.com/c/titanic
'''
if __name__ == "__main__":
## the application is quite fast, because the Db is small.. so in a normal laptop we can run with
## 15-20 generations and a population of 60-100..
population = 80
n_generations = 15
# this class can create randome genes in order to initialize the genetic algoritgm
creator = GeneCreator()
# method to implement the genetic algorithm itself
breeder = Breeder()
data_reader = DataReader.getInstance()
X, Y, X_test, X_output = data_reader.read_data()
#print( X.head() )
#try regressors
print("\n\n\n########################## BEGIN! ##########################")
generation = breeder.get_first_generation(population)
generation = breeder.run(generation)
for i in range(0, n_generations):
print("\n\n\n########################## GENERATION: " + str(i) +
" ##########################")
generation = breeder.get_new_generation(generation, population)
generation = breeder.run(generation)
#print( "gen lenght: " + str(len(generation)) )
