e2edutch.predict.main()

Complexity

Conditions

13

Size

Total Lines	76
Code Lines	60

Duplication

Lines	0
Ratio	0 %

Importance

Changes

0

import sys
def main(args=None):

Missing function or method docstring

This function exceeds the maximum number of variables (22/15).

    parser = get_parser()
    args = parser.parse_args()
    if args.verbose:
        logger.setLevel(logging.INFO)

    # Input file in .jsonlines format or .conll.
    input_filename = args.input_filename

    ext_input = os.path.splitext(input_filename)[-1]
    if ext_input not in ['.conll', '.jsonlines', '.txt', '.naf']:
        raise Exception(
            'Input file should be .naf, .conll, .txt or .jsonlines, but is {}.'
            .format(ext_input))

    if ext_input == '.conll':
        labels = collections.defaultdict(set)
        stats = collections.defaultdict(int)
        docs = minimize.minimize_partition(
            input_filename, labels, stats, args.word_col)
    elif ext_input == '.jsonlines':
        docs = read_jsonlines(input_filename)
    elif ext_input == '.naf':
        naf_obj = naf.get_naf(input_filename)
        jsonlines_obj, term_ids, tok_ids = naf.get_jsonlines(naf_obj)

The variable tok_ids seems to be unused.

        docs = [jsonlines_obj]
    else:
        text = open(input_filename).read()
        docs = [util.create_example(text)]

    output_file = args.output_file

    config = util.initialize_from_env(cfg_file=args.cfg_file, model_cfg_file=args.config)
    predictor = Predictor(config=config)

    sentences = {}
    predictions = {}
    for example_num, example in enumerate(docs):
        example["predicted_clusters"], _ = predictor.predict(example)
        if args.format_out == 'jsonlines':
            output_file.write(json.dumps(example))
            output_file.write("\n")
        else:
            predictions[example['doc_key']] = example["predicted_clusters"]
            sentences[example['doc_key']] = example["sentences"]
        if example_num % 100 == 0:
            logger.info("Decoded {} examples.".format(example_num + 1))

Use lazy % formatting in logging functions

    if args.format_out == 'conll':
        conll.output_conll(output_file, sentences, predictions)
    elif args.format_out == 'naf':
        # Check number of docs - what to do if multiple?
        # Create naf obj if input format was not naf
        if ext_input != '.naf':
            # To do: add linguistic processing layers for terms and tokens
            logger.warn(

Use lazy % formatting in logging functions

Using deprecated method warn()

                'Outputting NAF when input was not naf,'
                + 'no dependency information available')
            for doc_key in sentences:
                naf_obj, term_ids = naf.get_naf_from_sentences(
                    sentences[doc_key])
                naf_obj = naf.create_coref_layer(
                    naf_obj, predictions[doc_key], term_ids)
                naf_obj = naf.add_linguistic_processors(naf_obj)
                buffer = io.BytesIO()
                naf_obj.dump(buffer)
                output_file.write(buffer.getvalue().decode('utf-8'))
                # To do, make sepearate outputs?
                # TO do, use dependency information from conll?
        else:
            # We only have one input doc
            naf_obj = naf.create_coref_layer(
                naf_obj, example["predicted_clusters"], term_ids)

The variable term_ids does not seem to be defined for all execution paths.

The loop variable example might not be defined here.

The variable naf_obj does not seem to be defined for all execution paths.

The variable example does not seem to be defined in case the for loop on line 145 is not entered. Are you sure this can never be the case?

            naf_obj = naf.add_linguistic_processors(naf_obj)
            buffer = io.BytesIO()
            naf_obj.dump(buffer)
            output_file.write(buffer.getvalue().decode('utf-8'))