sentiment.py 文件源码

def preview(self, fraction=0.1):
        fetched = 0
        scores = []
        mod_print = int(1 / fraction)
        while fetched < self.limit:
            '''
                use search instead of scan because keeping an ordered scan cursor
                open negates the performance benefits
            '''
            resp = self.es.search(index='fcc-comments', body=self.query, size=self.limit)
            print('total=%s mod_print=%s' % (resp['hits']['total'], mod_print))
            for doc in resp['hits']['hits']:
                fetched += 1
                scores.append(doc['_score'])
                if not fetched % mod_print:
                    print('\n--- comment %s\t%s\t%s\t%s' % (fetched, doc['_id'],
                        doc['_score'], doc['_source']['text_data'][:1000]))