def __init__(self, tickers, start='2014-01-01', end='2018-01-01', interval='1d', n_series=20, T_pred=10, n_cols=30, n_rows=30, T_space=10, train=True):
self.folder = './' + ''.join(tickers) + '_start' + start + '_end' + end + '_int' + interval + \
'/case' + str(n_series) + '_' + str(T_pred) + '_' + str(n_cols) + '_' + str(n_rows) + '_' + str(T_space)
try:
self.original = np.load(self.folder + '/original.npy')
if train:
self.x = np.load(self.folder + '/Xtrain.npy')
self.y = np.load(self.folder + '/Ytrain.npy')
else:
self.x = np.load(self.folder + '/Xtest.npy')
self.y = np.load(self.folder + '/Ytest.npy')
except:
ld = LoadData(tickers, start, end, interval)
try:
ld.unprocessed = pd.read_csv('./' + ''.join(tickers) + '_start' + start + '_end' + end + '_int' + interval + '/UnprocessedData.csv')
except:
print('DOWNLOADING DATA')
ld.download()
print('PROCESSING DATA')
ld.process(n_series, T_pred, n_cols, n_rows, T_space, plot=True)
ld.cut_and_shuffle()
if train:
self.x = ld.Xtrain
self.y = ld.Ytrain
else:
self.x = ld.Xtest
self.y = ld.Ytest
self.original = ld.original
# Shape of X: (Number of datasamples, Number of tickers, Number of rows, Number of columns)
# Shape of Y: (Number of datasamples, Number of tickers)
self.len = self.x.shape[0]
