date)
download_file(path, file_name, date_range, folder)
if checksum == 1:
checksum_path = "data/spot/daily/klines/{}/{}/".format(
symbol.upper(), interval)
checksum_file_name = "{}-{}-{}.zip.CHECKSUM".format(
symbol.upper(), interval, date)
download_file(checksum_path, checksum_file_name,
date_range, folder)
current += 1
if __name__ == "__main__":
parser = get_parser('klines')
args = parser.parse_args(sys.argv[1:])
if not args.symbols:
print("fetching all symbols from exchange")
symbols = get_all_symbols()
num_symbols = len(symbols)
else:
symbols = args.symbols
num_symbols = len(symbols)
if args.dates:
dates = args.dates
else:
dates = pd.date_range(end=datetime.today(),
periods=MAX_DAYS).to_pydatetime().tolist()
file_name = "{}-trades-{}.zip".format(symbol.upper(), date)
download_file(path, file_name, date_range, folder)
if checksum == 1:
checksum_path = "data/spot/daily/trades/{}/".format(
symbol.upper())
checksum_file_name = "{}-trades-{}.zip.CHECKSUM".format(
symbol.upper(), date)
download_file(checksum_path, checksum_file_name,
date_range, folder)
current += 1
if __name__ == "__main__":
parser = get_parser('trades')
args = parser.parse_args(sys.argv[1:])
if not args.symbols:
print("fetching all symbols from exchange")
symbols = get_all_symbols()
num_symbols = len(symbols)
else:
symbols = args.symbols
num_symbols = len(symbols)
print("fetching {} symbols from exchange".format(num_symbols))
if args.dates:
dates = args.dates
else:
dates = pd.date_range(end=datetime.today(),
from sklearn.cluster import MiniBatchKMeans
from skimage.io import imread
from sklearn.externals import joblib
import pickle
import utility
import numpy as np
from sklearn.utils.random import sample_without_replacement
from sklearn.model_selection import train_test_split
args = utility.get_parser().parse_args()
DATASET = args.data
NUM_PIXELS = args.num_pixels
SINGLE_CLUSTERS = args.single_clusters
DOUBLE_CLUSTERS = args.double_clusters
image_paths, _ = utility.read_data(DATASET)
image_paths, _ = train_test_split(image_paths, test_size = 1500, random_state = 42)
kmeans_single = MiniBatchKMeans(n_clusters = SINGLE_CLUSTERS)
kmeans_double = MiniBatchKMeans(n_clusters = DOUBLE_CLUSTERS)
pca = joblib.load('resources/pca.pkl')
with open('resources/bounds.pkl', 'rb') as f:
bounds = pickle.load(f)
batch = np.zeros((NUM_PIXELS, 3))
for i, img in enumerate(image_paths):
image = imread(img)
dx, dy, dz = image.shape
path = "data/spot/daily/aggTrades/{}/".format(symbol.upper())
file_name = "{}-aggTrades-{}.zip".format(symbol.upper(), date)
download_file(path, file_name)
if checksum == 1:
checksum_path = "data/spot/daily/aggTrades/{}/".format(
symbol.upper())
checksum_file_name = "{}-aggTrades-{}.zip.CHECKSUM".format(
symbol.upper(), date)
download_file(checksum_path, checksum_file_name)
current += 1
if __name__ == "__main__":
parser = get_parser('aggTrades')
args = parser.parse_args(sys.argv[1:])
if not args.symbols:
print("fetching all symbols from exchange")
symbols = get_all_symbols()
num_symbols = len(symbols)
else:
symbols = args.symbols
num_symbols = len(symbols)
print("fetching {} symbols from exchange".format(num_symbols))
if args.dates:
dates = args.dates
else:
dates = pd.date_range(end=datetime.today(),