if daily_stock_quote:
for k in DailyStockQuote.fields.keys():
if k in OptionEffect.fields:
self.__set(k, daily_stock_quote.get(k))
def set(self, key, value):
raise RuntimeError("Should not be used")
def __set(self, key, value):
if key not in OptionEffect.fields:
raise KeyError(f"Invalid key={key}")
self._values[key] = value
if __name__ == '__main__':
metadata_dir = setup_metadata_dir()
setup_logger(__file__)
logger.setLevel(logging.DEBUG)
logging.getLogger("web_chrome_driver").setLevel(logging.DEBUG)
# test from online reading
with ChromeDriver() as browser:
option_quote = read_daily_option_quote(browser,
"AMD",
"Call",
60.0,
20220121,
use_barchart=True)
stock_quote = read_stock_quote(browser, "AMD")
option_effect = OptionEffect(daily_option_quote=option_quote,
daily_stock_quote=stock_quote)
print(json.dumps(option_effect.__dict__, indent=4))
# from scipy.misc import imresize
# from tensorboardX import SummaryWriter
# import warnings
from sklearn.metrics import roc_auc_score
from sklearn.metrics import average_precision_score
import cv2
from utils_logging import setup_logger
from models.__init__ import save_checkpoint, resume_checkpoint
from parse_inputs import parse_inputs
args = parse_inputs()
logger = setup_logger(name='first_logger',
log_dir='./logs/',
log_file=args.log_file,
log_format='%(asctime)s %(levelname)s %(message)s',
verbose=True)
def main():
# transform = _get_transform(args.input_resolution)
# Prepare data
print("Loading Data")
batch_size = args.batch_size
train_set = GazeDataset(args.train_dir, args.train_annotation, 'train')
train_data_loader = DataLoader(dataset=train_set,
batch_size=batch_size,
shuffle=False,