data_extractor.py 文件源码

def metamap_wrapper(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:
       - a dictionary with key sents and values
       a list of the concepts found
    """

    # Tokenize into sentences
    sents = sent_tokenize(text)
    # Load Metamap Instance
    mm = MetaMap.get_instance(settings['load']['path']['metamap'])
    concepts, errors = mm.extract_concepts(sents, range(len(sents)))
    # Keep the sentence ids
    ids = np.array([int(concept[0]) for concept in concepts])
    sentences = []
    for i in xrange(len(sents)):
        tmp = {'sent_id': i+1, 'entities': [], 'relations': []}
        # Wanted concepts according to sentence
        wanted = np.where(ids == i)[0].tolist()
        for w_ind in wanted:
            w_conc = concepts[w_ind]
            if hasattr(w_conc, 'cui'):
                tmp_conc = {'label': w_conc.preferred_name, 'cui': w_conc.cui, 
                            'sem_types': w_conc.semtypes, 'score': w_conc.score}
                tmp['entities'].append(tmp_conc)
        sentences.append(tmp)
    if errors:
        time_log('Errors with extracting concepts!')
        time_log(errors)
    return {'sents': sentences, 'sent_text':text}