def get(self, params):
if self.get_argument("fetch", True):
scope = ['https://spreadsheets.google.com/feeds']
credentials = ServiceAccountCredentials.from_json_keyfile_name('client_secret.json',scope)
word_repository = WordRepository()
dict_utils = DictUtils()
try:
gc = gspread.authorize(credentials)
sh = gc.open_by_key("1QeU3AoSghCAvYBD8kauC8oEZ0wA6j_gPj1pkvIY4MPU")
for ws_count, worksheets in enumerate(sh.worksheets()):
word_list = worksheets.col_values(1)
type_list = worksheets.col_values(2)
meaning_list = worksheets.col_values(3)
if ws_count < 26:
word_tuple_list = []
for i, (word, word_type, meaning) in enumerate(zip(word_list, type_list, meaning_list)):
if i > 0:
if word != '':
word_tuple_list.append(dict(id=str(uuid.uuid1().hex), word=word,
type=word_type,
meaning_zg=meaning,
meaning_uni=meaning))
else:
pass
word_repository.bulk_insert(word_tuple_list, dict_utils.get_model(str(worksheets.title).lower()))
else:
self.respond({}, NO_CONTENT_ERROR, code=SUCCESS)
except Exception as ex:
print ex.message
self.respond({}, ex.message, code=SERVER_ERROR)
parser.add_argument('--drop_out', type=float, default=0.5)
parser.add_argument('--m', type=float, default=0.3)
parser.add_argument('--p', type=float, default=0.55)
parser.add_argument('--flag', default="PER")
parser.add_argument('--dataset', default="conll2003")
parser.add_argument('--lr', type=float, default=1e-4)
parser.add_argument('--batch_size', type=int, default=300)
parser.add_argument('--model', default="")
parser.add_argument('--iter', type=int, default=1)
args = parser.parse_args()
dp = DataPrepare(args.dataset)
mutils = AdaptivePUUtils(dp)
dutils = DictUtils()
trainSet, validSet, testSet, prior = mutils.load_new_dataset(
args.flag, args.dataset, args.iter, args.p)
print(prior)
trainSize = len(trainSet)
validSize = len(validSet)
testSize = len(testSet)
print(("train set size: {}, valid set size: {}, test set size: {}").format(
trainSize, validSize, testSize))
charcnn = CharCNN(dp.char2Idx)
wordnet = WordNet(dp.wordEmbeddings, dp.word2Idx)
casenet = CaseNet(dp.caseEmbeddings, dp.case2Idx)
featurenet = FeatureNet()
pulstmcnn = AdaPULSTMCNN2(dp, charcnn, wordnet, casenet, featurenet, 150,