test_energy_krr_cmat.py 文件源码

def test_krr_cmat():

    test_dir = os.path.dirname(os.path.realpath(__file__))

    # Parse file containing PBE0/def2-TZVP heats of formation and xyz filenames
    data = get_energies(test_dir + "/data/hof_qm7.txt")

    # Generate a list of qml.Compound() objects
    mols = []

    for xyz_file in sorted(data.keys())[:1000]:

        # Initialize the qml.Compound() objects
        mol = qml.Compound(xyz=test_dir + "/qm7/" + xyz_file)

        # Associate a property (heat of formation) with the object
        mol.properties = data[xyz_file]

        # This is a Molecular Coulomb matrix sorted by row norm
        mol.generate_coulomb_matrix(size=23, sorting="row-norm")

        mols.append(mol)

    # Shuffle molecules
    np.random.seed(666)
    np.random.shuffle(mols)

    # Make training and test sets
    n_test  = 300
    n_train = 700

    training = mols[:n_train]
    test  = mols[-n_test:]

    # List of representations
    X  = np.array([mol.representation for mol in training])
    Xs = np.array([mol.representation for mol in test])

    # List of properties
    Y = np.array([mol.properties for mol in training])
    Ys = np.array([mol.properties for mol in test])

    # Set hyper-parameters
    sigma = 10**(4.2)
    llambda = 10**(-10.0)

    # Generate training Kernel
    K = laplacian_kernel(X, X, sigma)

    # Solve alpha
    K[np.diag_indices_from(K)] += llambda
    alpha = cho_solve(K,Y)

    # Calculate prediction kernel
    Ks = laplacian_kernel(X, Xs, sigma)
    Yss = np.dot(Ks.transpose(), alpha)

    mae = np.mean(np.abs(Ys - Yss))
    print(mae)