Scale the data to have no mean and variance 1, then split that data into training and validation without implicit bias

standardize.py

from sklearn.preprocessing import StandardScaler

def standardize_data(data, training_validation_split=0.2):
    """
    standardize features by removing the mean and scaling to unit variance

    :param data: the data desired to be scaled
    :param training_validation_split: The percentage of data to save for validation
    :return: the standardized features and scalar in the form (training, validation, scalar)
    """
    np.random.shuffle(data)
    split = int(data.shape[0]*(1 - training_validation_split))
    training, validation = data[:split, :], data[split:, :]

    scalar = StandardScaler()
    scalar.fit(training)

    return (scalar.transform(training), scalar.transform(validation), scalar)