append_timestamp = False save_best_model = True if use_saved_model: n_reps = 1 acc_train_vect = {} acc_test_vect = {} output_filename = "naive_bayes_1" prep = Preprocessing() if config["one_hot_encoding"]: prep.create_encoder( prep.adapt_input(generator.generate_binary(config["n_valves"]))) if config["run_clean"] and not use_saved_model: loader.clean(root_crt_model_folder) def init_vect(vect): for key in vect["data"]: # print(key) vect["data"][key].append(None) vect["count"].append(None) vect["files"].append(None) def update_vect(vect, index, acc, count, dt, fsize, file1):
use_randomforest = True prep = Preprocessing() if use_randomforest: root_crt_model_folder = config["root_model_container"] + "/dtree_multi" output_filename = "dtree_2_multioutput" else: root_crt_model_folder = config["root_model_container"] + "/dtree" output_filename = "dtree_1" # output_filename = "eval_deep_3_rnn_random_" # output_filename = "eval_deep_5_rnn_random_" if config["one_hot_encoding"]: binv = generator.generate_binary(config["n_valves"]) print("binv:") print(binv) binv = prep.adapt_input(binv) print("adapted:") print(binv) # print("to list") # print(prep.str_to_list(binv)) prep.create_encoder(binv) # quit() use_random_exp = True use_matching_random_model = False from_file = True