lanprosForVCF.py 文件源码

def tagged_abstracts(RS_pmids_tokenizedabstracts_dict):

    """ Takes a dict of tokenized abstracts
    and tags them using the NLTK module for Natural Language Entities.
    Input dictionary: key is the RS ID, value is a dictionary where key is the pmid and value is a list of tokens"""
    RS_pmids_taggedabstracts_dict = {}
    for each_RS in RS_pmids_tokenizedabstracts_dict:
        pmids_taggedabstracts = {}
        pmids_tokenizedabstracts = RS_pmids_tokenizedabstracts_dict[each_RS]
        for pmid in pmids_tokenizedabstracts:
            taggedabstracts_list = []
            for token in pmids_tokenizedabstracts[pmid]:
                tagged = nltk.pos_tag(token)
                taggedabstracts_list.append(tagged)
            pmids_taggedabstracts[pmid] = taggedabstracts_list
        RS_pmids_taggedabstracts_dict[each_RS] = pmids_taggedabstracts
    return RS_pmids_taggedabstracts_dict