load_parse.py 文件源码

def mmap_extract(text):
    """
    Function-wrapper for metamap binary. Extracts concepts
    found in text.

    !!!! REMEMBER TO START THE METAMAP TAGGER AND
        WordSense DISAMBIGUATION SERVER !!!!

    Input:
        - text: str,
        a piece of text or sentence
    Output:
        - concepts: list,
        list of metamap concepts extracted
    """

    # Tokenize into sentences
    sents = sent_tokenize(text)
    mm = MetaMap.get_instance(settings['load']['path']['metamap'])
    concepts, errors = mm.extract_concepts(sents, range(len(sents)), 
                                         word_sense_disambiguation=True)
    if errors:
        print 'Errors with extracting concepts!'
        print errors
    return concepts