def visualize_optimization():
import cPickle
results = cPickle.load(open("..\..\..\models\CANER\Flu\SD\maximintest.cPickle"))
# best_case, best_individual_score, results = results
graph_errorbars_raw(results['stats'])
graph_pop_heatmap_raw(results['raw'])
plt.show()
outcome = outcomes['deceased population region 1']
zeros = np.zeros((outcome.shape[0], 1))
zeros[outcome[:,-1]<1000000] = 1
value = np.sum(zeros)/zeros.shape[0]
return value
if __name__ == "__main__":
# ema_logging.log_to_stderr(ema_logging.INFO)
# model = FluModel(r'..\..\..\models\CANER\Flu\SD', "fluCase")
#
# ensemble = ModelEnsemble()
# ensemble.set_model_structure(model)
# ensemble.parallel = True
#
# policy_levers = {'trackperiod': (1,8),
# 'delaytime': (0.01,2)}
#
# res = ensemble.perform_robust_optimization(cases=1000,
# obj_function=obj_func,
# policy_levers = policy_levers,
# nrOfPopMembers=50,
# nrOfGenerations=50,
# crossoverRate=0.7,
# mutationRate=0.01)
# cPickle.dump(res, open(r'FLU robust optimization results.cPickle', 'w'))
res = cPickle.load(open(r'FLU robust optimization results.cPickle', 'r'))
graph_pop_heatmap_raw(res['raw'])
graph_errorbars_raw(res['stats'])
plt.show()
