'[%(pathname)s:%(lineno)d]: %(message)s')
ch.setFormatter(formatter)
fh.setFormatter(formatter)
# add the handlers to logger
logger.addHandler(ch)
logger.addHandler(fh)
logger.info("running %s" % ' '.join(sys.argv))
#Load Reuters-21578 dataset
if options.path is None:
logger.error("Path to Reuters-21578 dataset not set.")
sys.exit(1)
#Load feature models and extractor
#feature_extractor = LdaBowFeatureExtractor(prefix = options.prefix)
#feature_extractor = LdaFeatureExtractor(prefix = options.prefix)
feature_extractor = cEsaFeatureExtractor(prefix = options.path + '/models/cesa_on_reuters/wiki')
#Load database, training and test data
db = FileDatabase.load(options.path + '/reuters.db')
split = R8Split(db)
training_data = train_data(feature_extractor, split)
test_data = test_data(feature_extractor, split)
# store training and test data
np.save(options.path + '/training_data_cesa.npy', training_data)
np.save(options.path + '/test_data_cesa.npy', test_data)
logger.info("done.")
if config_ == None:
logger.error("No config. Exit.")
sys.exit(1)
#Connect to mongo database
connect(config_['database']['db-name'],
username= config_['database']['user'],
password= config_['database']['passwd'],
port = config_['database']['port'])
#Load feature extractor
#feature_extractor = EsaFeatureExtractor(prefix = config_['prefix'])
#feature_extractor = TfidfFeatureExtractor(prefix = config_['prefix'])
#feature_extractor = LdaFeatureExtractor(prefix = config_['prefix'])
#feature_extractor = LdaBowFeatureExtractor(prefix = config_['prefix'])
feature_extractor = cEsaFeatureExtractor(prefix = config_['prefix'])
#get user
user = User.objects(email=u"*****@*****.**").first()
ranked_article_ids = (a.article.id
for a
in RankedArticle.objects(user_id = user.id).only("article"))
all_article_ids = Set(a.id
for a
in Article.objects(id__in = ranked_article_ids).only("id"))
read_article_ids = Set(a.article.id
for a
in ReadArticleFeedback.objects(user_id = user.id).only("article"))
