4db3da80995cfe44c3520e3581f8bf15cc64f263,cde/evaluation_runs/question2_noise_reg_y_econ_kmn/configuration.py,,,#,35

Before Change

                      ]

  // Search for pickle file in directory
  pickle_files = glob.glob("*.pickle")
  if pickle_files:
    results_pickle = pickle_files[0]
  else:
    results_pickle = None

  if run:
    observations = 100 * np.logspace(0, 4, num=5, base=2.0, dtype=np.int32) // creates a list with log scale: 100, 200, 400, 800, 1600

    conf_est, conf_sim = question1()
    conf_runner = ConfigRunner(conf_est, conf_sim, observations=observations, keys_of_interest=keys_of_interest,
                               n_mc_samples=2*10**6, n_x_cond=5, n_seeds=5, results_pickle_file=results_pickle)

    results_list, full_df = conf_runner.run_configurations(output_dir="./", prefix_filename="question2_noise_reg")

After Change

                      ]

  // Search for pickle file in directory
  results_pickle_file = glob.glob("*noise*.pickle")
  config_pickle_file = glob.glob("config*.pickle")

  if results_pickle_file:
    results_pickle = results_pickle_file[0]
  else:
    results_pickle = None

  if config_pickle_file:
    config_pickle_file = config_pickle_file[0]
  else:
    config_pickle_file = None

  if run:
    observations = 100 * np.logspace(0, 4, num=5, base=2.0, dtype=np.int32) // creates a list with log scale: 100, 200, 400, 800, 1600

    conf_est, conf_sim = question1()
    conf_runner = ConfigRunner(conf_est, conf_sim, observations=observations, keys_of_interest=keys_of_interest,
                               n_mc_samples=2*10**6, n_x_cond=5, n_seeds=5, results_pickle_file=results_pickle, config_pickle_file=config_pickle_file)

    results_list, full_df = conf_runner.run_configurations(output_dir="./", prefix_filename="question2_noise_reg")

Instances