setup_variables_for_training.py

# Set constants
batch_size=16
epochs=300

# Reinitiating data here
data = fractional_diff_data

X = data[['open', 'high', 'low', 'close', 'volume', 'rsi', 'macd', 'macd_signal', 'macd_hist', 'cci', 'dx', 'volatility']].values
y = np.squeeze(data[['label_barrier']].values).astype(int)

# Split into train+val and test
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, stratify=y, random_state=69)

# Normalize input
scaler = MinMaxScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Convert to numpy arrays
X_train, y_train = np.array(X_train), np.array(y_train)
X_test, y_test = np.array(X_test), np.array(y_test)

# initialize sets and convet them to Pytorch dataloader sets
train_dataset = ClassifierDataset(torch.from_numpy(X_train).float(), torch.from_numpy(y_train.astype(int)).long())
test_dataset = ClassifierDataset(torch.from_numpy(X_test).float(), torch.from_numpy(y_test.astype(int)).long())


train_loader = DataLoader(dataset=train_dataset,
                          batch_size=batch_size
                          )

test_loader = DataLoader(dataset=test_dataset, 
                         batch_size=1)