def __init__(self,
data_path,
market_name,
tickers_fname,
parameters,
steps=1,
epochs=50,
batch_size=None,
gpu=False):
self.data_path = data_path
self.market_name = market_name
self.tickers_fname = tickers_fname
# load data
self.tickers = np.genfromtxt(os.path.join(data_path, '..',
tickers_fname),
dtype=str,
delimiter='\t',
skip_header=False)
### DEBUG
# self.tickers = self.tickers[0: 10]
print('#tickers selected:', len(self.tickers))
self.eod_data, self.mask_data, self.gt_data, self.price_data = \
load_EOD_data(data_path, market_name, self.tickers, steps)
self.parameters = copy.copy(parameters)
self.steps = steps ## depends on your strategy(default one-day)
self.epochs = epochs
if batch_size is None:
self.batch_size = len(self.tickers)
else:
self.batch_size = batch_size
self.valid_index = 756
self.test_index = 1008
self.trade_dates = self.mask_data.shape[1]
self.fea_dim = 5
self.gpu = gpu
def __init__(self,
data_path,
market_name,
tickers_fname,
relation_name,
emb_fname,
parameters,
steps=1,
epochs=50,
batch_size=None,
flat=False,
gpu=False,
in_pro=False):
seed = 123456789
random.seed(seed)
np.random.seed(seed)
tf.set_random_seed(seed)
self.data_path = data_path
self.market_name = market_name
self.tickers_fname = tickers_fname
self.relation_name = relation_name
# load data
self.tickers = np.genfromtxt(os.path.join(data_path, '..',
tickers_fname),
dtype=str,
delimiter='\t',
skip_header=False)
print('#tickers selected:', len(self.tickers))
self.eod_data, self.mask_data, self.gt_data, self.price_data = \
load_EOD_data(data_path, market_name, self.tickers, steps)
# relation data
rname_tail = {
'sector_industry': '_industry_relation.npy',
'wikidata': '_wiki_relation.npy'
}
self.rel_encoding, self.rel_mask = load_relation_data(
os.path.join(self.data_path, '..', 'relation', self.relation_name,
self.market_name + rname_tail[self.relation_name]))
print('relation encoding shape:', self.rel_encoding.shape)
print('relation mask shape:', self.rel_mask.shape)
self.embedding = np.load(
os.path.join(self.data_path, '..', 'pretrain', emb_fname))
print('embedding shape:', self.embedding.shape)
self.parameters = copy.copy(parameters)
self.steps = steps
self.epochs = epochs
self.flat = flat
self.inner_prod = in_pro
if batch_size is None:
self.batch_size = len(self.tickers)
else:
self.batch_size = batch_size
self.valid_index = 756
self.test_index = 1008
self.trade_dates = self.mask_data.shape[1]
self.fea_dim = 5
self.gpu = gpu
from load_data import load_EOD_data, load_relation_data
# params
data_path = '../data/2013-01-01'
market_name = 'NASDAQ'
tickers_fname = market_name + '_tickers_qualify_dr-0.98_min-5_smooth.csv'
steps = 1
# load stock data
tickers = np.genfromtxt(os.path.join(data_path, '..', tickers_fname),
dtype=str, delimiter='\t', skip_header=False)
print('#tickers selected:', len(tickers))
eod_data, mask_data, gt_data, price_data = \
load_EOD_data(data_path, market_name, tickers, steps)
# corr tensor
corr_size = 30
num_companies, num_timesteps = gt_data.shape
correlation_matrix_shape = (num_timesteps - corr_size, num_companies, num_companies)
corr = np.ones(correlation_matrix_shape)
print(corr.shape)
iu = np.triu_indices(num_companies,k=1)
il = (iu[1],iu[0])
for t in tqdm(range(num_timesteps - corr_size)):
for c1 in tqdm(range(num_companies)):
for c2 in range(1, num_companies - c1):
c1_movements = gt_data.T[t:t+corr_size][:,c1]
def __init__(self,
data_path,
market_name,
tickers_fname,
relation_name,
emb_fname,
parameters,
steps=1,
epochs=50,
batch_size=None,
flat=False,
gpu=False,
in_pro=False):
seed = 123456789
random.seed(seed)
np.random.seed(seed)
tf.set_random_seed(seed)
self.data_path = data_path
self.market_name = market_name
self.tickers_fname = tickers_fname
self.relation_name = relation_name
# load data
self.tickers = np.genfromtxt(os.path.join(data_path, '..',
tickers_fname),
dtype=str,
delimiter='\t',
skip_header=False)
print('#tickers selected:', len(self.tickers))
self.eod_data, self.mask_data, self.gt_data, self.price_data = \
load_EOD_data(data_path, market_name, self.tickers, steps)
# relation data
rname_tail = {
'sector_industry': '_industry_relation.npy',
'wikidata': '_wiki_relation.npy'
}
self.rel_encoding, self.rel_mask = load_relation_data(
os.path.join(self.data_path, '..', 'relation', self.relation_name,
self.market_name + rname_tail[self.relation_name]))
print('relation encoding shape:', self.rel_encoding.shape)
print('relation mask shape:', self.rel_mask.shape)
self.embedding = np.load(
os.path.join(self.data_path, '..', 'pretrain', emb_fname))
print('embedding shape:', self.embedding.shape)
self.emb_tickers = np.genfromtxt(os.path.join(
self.data_path, '..',
self.market_name + '_tickers_qualify_dr-0.98_min-5_smooth.csv'),
dtype=str,
delimiter='\t',
skip_header=False)
new_emb = []
for i, ticker in enumerate(self.tickers):
ind = np.where(self.emb_tickers == ticker)[0][0]
new_emb.append(self.embedding[ind][-len(self.eod_data[i]):])
self.embedding = np.array(new_emb)
self.parameters = copy.copy(parameters)
self.steps = steps
self.epochs = epochs
self.flat = flat
self.inner_prod = in_pro
if batch_size is None:
self.batch_size = len(self.tickers)
else:
self.batch_size = batch_size
self.valid_index = 253
self.test_index = 378
print(f"-----\n{self.mask_data.shape}\n-----")
self.trade_dates = self.mask_data.shape[1]
self.fea_dim = 5
self.gpu = gpu