tigerforecast.experiments.load_prob_method_to_result

tigerforecast.experiments.load_prob_method_to_result(problem_ids=['ARMA-v0', 'Crypto-v0', 'SP500-v0'], method_ids=['LastValue', 'AutoRegressor', 'RNN', 'LSTM'], problem_to_methods=None, metrics='mse')[source]

Description: Initializes the experiment instance.

Parameters:
  • problem_ids (list) – ids of problems to evaluate on
  • method_ids (list) – ids of methods to use
  • problem_to_methods (dict) – map of the form problem_id -> list of method_id. If None, then we assume that the user wants to test every method in method_to_params against every problem in problem_to_params
  • metrics – metrics to load