mirtext_corpus.py 文件源码

def load_corpus(self, corenlpserver, process=True):
        # self.path is the base directory of the files of this corpus
        trainfiles = [self.path + '/' + f for f in os.listdir(self.path) if f.endswith('.txt')]
        total = len(trainfiles)
        widgets = [pb.Percentage(), ' ', pb.Bar(), ' ', pb.AdaptiveETA(), ' ', pb.Timer()]
        pbar = pb.ProgressBar(widgets=widgets, maxval=total, redirect_stdout=True).start()
        time_per_abs = []
        for current, f in enumerate(trainfiles):
            #logging.debug('%s:%s/%s', f, current + 1, total)
            print '{}:{}/{}'.format(f, current + 1, total)
            did = f.split(".")[0]
            t = time.time()
            with io.open(f, 'r', encoding='utf8') as txt:
                doctext = txt.read()
            newdoc = Document(doctext, process=False, did=did)
            newdoc.sentence_tokenize("biomedical")
            if process:
                newdoc.process_document(corenlpserver, "biomedical")
            self.documents[newdoc.did] = newdoc
            abs_time = time.time() - t
            time_per_abs.append(abs_time)
            #logging.info("%s sentences, %ss processing time" % (len(newdoc.sentences), abs_time))
            pbar.update(current+1)
        pbar.finish()
        abs_avg = sum(time_per_abs)*1.0/len(time_per_abs)
        logging.info("average time per abstract: %ss" % abs_avg)