from collections import defaultdict
import itertools
from base import Summarizer
from log_conf import Logger
from util.tokenization import WordTokenizer, SentTokenizer
logger = Logger('.'.join(__file__.split('/')[-2:-1])).logger
class Summarizer(Summarizer):
'''
classdocs
'''
def __init__(self, args, opts):
'''
Constructor
'''
def summarize(self, extracted_refs, facet_results, max_length=250):
'''
Summarizes the extracted references based on the facet results
Chooses from facets naively
Args:
extracted_refs(list) -- results of the method.run (e.g. simple.py)
facet_results(dict) -- facets for each extracted reference
Look at data/task1b_results1.json
from _collections import defaultdict
from util.rouge.PythonROUGE.rouge_wrapper import calc_rouge
from random import randint
from copy import deepcopy
import itertools
from log_conf import Logger
from summarizer.mmr_summarizer import MMR
from util.aritmatic_operations import mean_conf
from util.tokenization import WordTokenizer
from util.common import write_json_as_csv, hash_obj, hash_dict
import gzip
w_t = WordTokenizer(stem=False)
logger = Logger(__file__.split('/')[-1]).logger
path = constants.get_path()
result_outpath = 'tmp/tmpres/'
_ANNS_DIR = path['ann']
_ANNS_PATH = path['ann_json']
CACHE = path['cache']
valid_topics = ['all']
# doc_mod = DocumentsModel(_ANNS_DIR)
CACHE_FILE = constants.join_path(
CACHE, 'umls.json')
if os.path.isfile(CACHE_FILE):
try: