def test_save_and_load(): import matplotlib.pyplot as plt from expWorkbench.EMAlogging import log_to_stderr, INFO from expWorkbench.model import SimpleModelEnsemble from examples.FLUvensimExample import FluModel from analysis.graphs import lines log_to_stderr(level= INFO) model = FluModel(r'..\..\models\flu', "fluCase") ensemble = SimpleModelEnsemble() # ensemble.parallel = True ensemble.set_model_structure(model) policies = [{'name': 'no policy', 'file': r'\FLUvensimV1basecase.vpm'}, {'name': 'static policy', 'file': r'\FLUvensimV1static.vpm'}, {'name': 'adaptive policy', 'file': r'\FLUvensimV1dynamic.vpm'} ] ensemble.add_policies(policies) results = ensemble.perform_experiments(10) file = r'C:\eclipse\workspace\EMA workbench\models\results.cPickle' save_results(results, file) results = load_results(file) lines(results) plt.show()
def test_feature_selection(): from expWorkbench.model import SimpleModelEnsemble from examples.FLUvensimExample import FluModel log_to_stderr(level= INFO) model = FluModel(r'..\..\models\flu', "fluCase") ensemble = SimpleModelEnsemble() ensemble.parallel = True ensemble.set_model_structure(model) policies = [{'name': 'no policy', 'file': r'\FLUvensimV1basecase.vpm'}, {'name': 'static policy', 'file': r'\FLUvensimV1static.vpm'}, {'name': 'adaptive policy', 'file': r'\FLUvensimV1dynamic.vpm'} ] ensemble.add_policies(policies) results = ensemble.perform_experiments(5000) results = feature_selection(results, classify) for entry in results: print entry[0] +"\t" + str(entry[1])
value = temp_box.dtype.fields.get(name)[0] if value == 'object': c_b = box[name][0] values = np.asarray([cats[name].index(c) for c in c_b]) if a[i] != 1: a_i = 1/(maxima[i]-1) values = a_i*values else: values = [1/2] temp_box[name][0] = values temp_box[name][1] = values else: temp_box[name][0] = a[i]*box[name][0] + b[i] temp_box[name][1] = a[i]*box[name][1] + b[i] temp_boxes.append(temp_box) boxes= temp_boxes return boxes if __name__ == '__main__': log_to_stderr(level= INFO) model = FluModel(r'..\..\models\flu', "fluCase") results = expWorkbench.util.load_results(r'1000 flu cases.cPickle') boxes = perform_prim(results, classify=model.outcomes[1].name, threshold_type=1, threshold=0.8) write_prim_to_stdout(boxes) show_boxes_individually(boxes, results) plt.show()