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: with codecs.open(CACHE_FILE, 'rb', 'utf-8') as mf: cachefile = json.load(mf) except: cachefile = {} else: cachefile = {} def evaluate(opts, args): def tofloat(s): return '%.3f' % s # round float representation def toCI(s): return s, s + '_cb', s + '_ce'
import codecs import os import sys from copy import deepcopy from libs.evaluate import merge_offsets from libs.supervised.prep.prepare import Prep from constants import get_path, join_path from libs.supervised.classifiers.svm_rank import Supervised from util.common import hash_obj from util.cache import simple_caching, object_hashing from importlib import import_module import constants path = get_path() STOPWORDS_PATH = path['data'] + '/stopwords.txt' CLF_PATH = join_path(path['root'], 'libs/supervised/classifiers') docs_path = join_path(path['data'], 'TAC_2014_BiomedSumm_Training_Data') json_data_path = join_path(path['data'], 'v1-2a.json') # root_proj_path = os.getcwd() # while not('.git' in os.listdir(root_proj_path)): # root_proj_path = os.path.split(root_proj_path)[0] # if not(root_proj_path in sys.path): # sys.path.append(root_proj_path) class Reranker(RerankInterface): reranker_opts = { 'cutoff': { 'type': int,
import codecs import os import sys from libs.evaluate import merge_offsets from libs.supervised.prep.prepare import Prep from constants import get_path, join_path from libs.supervised.classifiers.svm_rank import Supervised from util.common import hash_obj from util.cache import simple_caching, object_hashing from importlib import import_module import constants import operator path = get_path() STOPWORDS_PATH = path['data'] + '/stopwords.txt' CLF_PATH = join_path( path['root'], 'libs/supervised/classifiers') docs_path = join_path(path['data'], 'TAC_2014_BiomedSumm_Training_Data') json_data_path = join_path(path['data'], 'v1-2a.json') # root_proj_path = os.getcwd() # while not('.git' in os.listdir(root_proj_path)): # root_proj_path = os.path.split(root_proj_path)[0] # if not(root_proj_path in sys.path): # sys.path.append(root_proj_path) class Reranker(RerankInterface): reranker_opts = {'cutoff': {'type': int, 'default': 3}, 'lookup': {'type': int, 'default': 15}, 'relaxation': {'type': int, 'default': 0},