data_extractor.py 文件源码

def extract_entities(text, json_={}):
    """
    Extract entities from a given text using metamap and
    generate a json, preserving infro regarding the sentence
    of each entity that was found. For the time being, we preserve
    both concepts and the entities related to them
    Input:
         - text: str,
        a piece of text or sentence
        - json_: dic,
        sometimes the json to be returned is given to us to be enriched
        Defaults to an empty json_
    Output:
        - json_: dic,
        json with fields text, sents, concepts and entities
        containg the final results
    """
    json_['text'] = text
    # Tokenize the text
    sents = sent_tokenize(text)
    json_['sents'] = [{'sent_id': i, 'sent_text': sent} for i, sent in enumerate(sents)]
    json_['concepts'], _ = mmap_extract(text)
    json_['entities'] = {}
    for i, sent in enumerate(json_['sents']):
        ents = metamap_ents(sent)
        json_['entities'][sent['sent_id']] = ents
    return json_