def run_test(handler): in_data, out_data = test_utils.get_dataset() global_is_equal_flag = True global_msg = "" for test_name in in_data: hypothesis = handler(in_data[test_name], RANDOM_SEED) print(f"test name: {test_name}") is_equal_flag, msg = test_utils.compare_structs( out_data[test_name], hypothesis, ignored_keys=["id", "used_phrases"]) if msg and len(msg.split("`")) == 5: _, ground_truth_text, _, hypothesis_text, _ = msg.split("`") is_equal_flag, ratio = test_utils.compare_text( ground_truth_text, hypothesis_text, 0.80) if not is_equal_flag: msg = f"{msg} ratio = {ratio}" # assert is_equal_flag, msg if is_equal_flag: print("Success") else: print(is_equal_flag, msg) global_msg += f"\nFailed test_name: {test_name} <-> msg: {msg}" global_is_equal_flag = False assert global_is_equal_flag, global_msg
def run_test(handler): in_data, out_data = test_utils.get_dataset() for test_name in in_data: hypothesis = handler(in_data[test_name]) print(f"test name: {test_name}") is_equal_flag, msg = test_utils.compare_structs( out_data[test_name], hypothesis) assert is_equal_flag, msg print("Success")
def run_test(handler): in_data, out_data = test_utils.get_dataset() for test_name in in_data: hypothesis = handler(in_data[test_name], RANDOM_SEED) print(f"test name: {test_name}") is_equal_flag, msg = test_utils.compare_structs(out_data[test_name], hypothesis, ignored_keys=["id"]) if msg and len(msg.split("`")) == 5: _, ground_truth_text, _, hypothesis_text, _ = msg.split("`") is_equal_flag, ratio = test_utils.compare_text(ground_truth_text, hypothesis_text, 0.80) if not is_equal_flag: msg = f"{msg} ratio = {ratio}" assert is_equal_flag, msg print("Success")