def build_regression_model(args): settings.NPARA = args.npara settings.PROBACUTOFF = args.probacutoff #settings.SAVEMODEL=args.savemodel settings.SAVEPRED = args.savepred #settings.MICROSPEC=args.microspec #settings.GRIDSEARCH=args.gridsearch settings.LATENT = args.latent X1, X2, Y1, Y2, O1, O2, V = load_datasets(training=settings.FIT, test=settings.PREDICT, y_name=settings.ACTIVITY) if settings.VERBOSE == 1: print( "\nTRAINING SET:\nN objects = %s\nN independent vars = %s\nN dependent vars: 1 (%s)\n\nTEST SET:\nN objects = %s\n" % (len(O1), len(X1[0]), settings.ACTIVITY, len(O2))) if settings.MODEL == "PLS": y_train_pred, y_test_pred = run_pls(X_train=X1, X_test=X2, y_train=Y1, y_test=Y2) else: Y1_pred, Y2_pred, Y1_prob, Y2_prob = modelling( X_train=X1, X_test=X2, Y_train=Y1, model_type=settings.MODEL, nondef_params=settings.NPARA, sm=settings.SAVEMODEL, mc=settings.MULTICLASS)
def build_auto(args): X1, X2, Y1, Y2, O1, O2, V = load_datasets(training=settings.FIT, test=settings.PREDICT, response=settings.RESPONSE) #settings.VAR_NAMES=V[1:-1] #settings.VARS=V run_procedure(X1=X1, X2=X2, Y1=Y1, Y2=Y2, O1=O1, O2=O2)
def build_class_regression_model(args): settings.LATENT = args.latent settings.HIGHTHRESHOLD = args.highthreshold settings.LOWTHRESHOLD = args.lowthreshold settings.SAVEPRED = args.savepred settings.VERBOSE = -1 X1, X2, Y1, Y2, O1, O2, V = load_datasets(training=settings.FIT, test=settings.PREDICT, y_name=settings.ACTIVITY) if settings.MODEL == 'PLS': run_pls(X_train=X1, X_test=X2, Y_train=Y1, Y_test=Y2, O_train=O1, O_test=O2, nlv=settings.LATENT, lt=settings.LOWTHRESHOLD, ht=settings.HIGHTHRESHOLD)
def build_classification_model(args): settings.NPARA = args.npara settings.MULTICLASS = args.multiclass settings.PROBACUTOFF = args.probacutoff settings.SAVEMODEL = args.savemodel settings.SAVEPRED = args.savepred settings.GRIDSEARCH = args.gridsearch settings.BACKFEEL = args.backfeel X1, X2, Y1, Y2, O1, O2, V = load_datasets(training=settings.FIT, test=settings.PREDICT, y_name=settings.ACTIVITY) settings.VAR_NAMES = V[1:-1] if settings.GRIDSEARCH: gridsearchcv(X1=X1, Y1=Y1, X2=X2, Y2=Y2, grid=param_grids[settings.MODEL]) else: make_one_model(X1=X1, X2=X2, Y1=Y1, Y2=Y2, O1=O1, O2=O2)
def run_dmody_regression_operations(args): settings.NPARA, variables.DMODY = False, True variables.X_tra, variables.Y_tra, variables.O_list, variables.V_list = load_datasets( training=settings.FIT, response=settings.RESPONSE) print( "\nTRAINING SET:\nN objects = %s\nN independent vars = %s\nN dependent vars: 1 (%s)" % (len(variables.O_list), len(variables.X_tra[0]), settings.RESPONSE)) df_results = pd.DataFrame({'Y_exp': variables.Y_tra}, index=variables.O_list) for a in algorithms_list: settings.MODEL = a print("\nPerforming %s+LOO..." % a) run_model_training() distances = calc_dmody() df_results['Y_pred (%s)' % settings.MODEL] = variables.Y_pred df_results['DModY (%s)' % settings.MODEL] = distances #print(df_results) df_results.to_csv("DModY.csv", sep=";")