# python run_evaluate.py --input=<INPUT> --cat=<CATEGORY> --filter
args = parse_args()
if args.language == 'en':
from nemo_text_processing.text_normalization.en.clean_eval_data import filter_loaded_data
file_path = args.input
normalizer = Normalizer(input_case=args.input_case, lang=args.language)
print("Loading training data: " + file_path)
training_data = load_files([file_path])
if args.filter:
training_data = filter_loaded_data(training_data)
if args.category is None:
print("Sentence level evaluation...")
sentences_un_normalized, sentences_normalized, _ = training_data_to_sentences(training_data)
print("- Data: " + str(len(sentences_normalized)) + " sentences")
sentences_prediction = normalizer.normalize_list(sentences_un_normalized)
print("- Normalized. Evaluating...")
sentences_accuracy = evaluate(
preds=sentences_prediction, labels=sentences_normalized, input=sentences_un_normalized
)
print("- Accuracy: " + str(sentences_accuracy))
print("Token level evaluation...")
tokens_per_type = training_data_to_tokens(training_data, category=args.category)
token_accuracy = {}
for token_type in tokens_per_type:
print("- Token type: " + token_type)
tokens_un_normalized, tokens_normalized = tokens_per_type[token_type]
print(" - Data: " + str(len(tokens_normalized)) + " tokens")
if fil.class_type == instance.token_type and fil.filter(instance):
instance = fil.process(instance)
updated_instance = True
if updated_instance:
if verbose:
print(instance)
updates_instances.append(instance)
return updates_instances
def parse_args():
parser = ArgumentParser()
parser.add_argument("--input",
help="input file path",
type=str,
default='./ar_with_types/output-00001-of-00100')
parser.add_argument("--verbose",
help="print filtered instances",
action='store_true')
return parser.parse_args()
if __name__ == "__main__":
args = parse_args()
file_path = args.input
print("Loading training data: " + file_path)
instance_list = load_files([file_path]) # List of instances
filtered_instance_list = filter_loaded_data(instance_list, args.verbose)
training_data_to_sentences(filtered_instance_list)
