Python msm.ContinuousTimeMSM类代码示例

def test_uncertainties_backward():
    n = 4
    grid = NDGrid(n_bins_per_feature=n, min=-np.pi, max=np.pi)
    seqs = grid.fit_transform(load_doublewell(random_state=0)['trajectories'])

    model = ContinuousTimeMSM(verbose=False).fit(seqs)
    sigma_ts = model.uncertainty_timescales()
    sigma_lambda = model.uncertainty_eigenvalues()
    sigma_pi = model.uncertainty_pi()
    sigma_K = model.uncertainty_K()

    yield lambda: np.testing.assert_array_almost_equal(
        sigma_ts, [9.13698928, 0.12415533, 0.11713719])
    yield lambda: np.testing.assert_array_almost_equal(
        sigma_lambda, [1.76569687e-19, 7.14216858e-05, 3.31210649e-04, 3.55556718e-04])
    yield lambda: np.testing.assert_array_almost_equal(
        sigma_pi, [0.00741467, 0.00647945, 0.00626743, 0.00777847])
    yield lambda: np.testing.assert_array_almost_equal(
        sigma_K,
        [[  3.39252419e-04, 3.39246173e-04, 0.00000000e+00, 1.62090239e-06],
         [  3.52062861e-04, 3.73305510e-04, 1.24093936e-04, 0.00000000e+00],
         [  0.00000000e+00, 1.04708186e-04, 3.45098923e-04, 3.28820213e-04],
         [  1.25455972e-06, 0.00000000e+00, 2.90118599e-04, 2.90122944e-04]])
    yield lambda: np.testing.assert_array_almost_equal(
        model.ratemat_,
        [[ -2.54439564e-02, 2.54431791e-02,  0.00000000e+00,  7.77248586e-07],
         [  2.64044208e-02,-2.97630373e-02,  3.35861646e-03,  0.00000000e+00],
         [  0.00000000e+00, 2.83988103e-03, -3.01998380e-02,  2.73599570e-02],
         [  6.01581838e-07, 0.00000000e+00,  2.41326592e-02, -2.41332608e-02]])

def test_uncertainties_backward():
    n = 4
    grid = NDGrid(n_bins_per_feature=n, min=-np.pi, max=np.pi)
    trajs = DoubleWell(random_state=0).get_cached().trajectories
    seqs = grid.fit_transform(trajs)

    model = ContinuousTimeMSM(verbose=False).fit(seqs)
    sigma_ts = model.uncertainty_timescales()
    sigma_lambda = model.uncertainty_eigenvalues()
    sigma_pi = model.uncertainty_pi()
    sigma_K = model.uncertainty_K()

    yield lambda: np.testing.assert_array_almost_equal(
        sigma_ts, [9.508936, 0.124428, 0.117638])
    yield lambda: np.testing.assert_array_almost_equal(
        sigma_lambda,
        [1.76569687e-19, 7.14216858e-05, 3.31210649e-04, 3.55556718e-04])
    yield lambda: np.testing.assert_array_almost_equal(
        sigma_pi, [0.007496, 0.006564, 0.006348, 0.007863])
    yield lambda: np.testing.assert_array_almost_equal(
        sigma_K,
        [[0.000339, 0.000339, 0., 0.],
         [0.000352, 0.000372, 0.000122, 0.],
         [0., 0.000103, 0.000344, 0.000329],
         [0., 0., 0.00029, 0.00029]])
    yield lambda: np.testing.assert_array_almost_equal(
        model.ratemat_,
        [[-0.0254, 0.0254, 0., 0.],
         [0.02636, -0.029629, 0.003269, 0.],
         [0., 0.002764, -0.030085, 0.027321],
         [0., 0., 0.024098, -0.024098]])

def test_doublewell():
    trjs = load_doublewell(random_state=0)['trajectories']
    for n_states in [10, 50]:
        clusterer = NDGrid(n_bins_per_feature=n_states)
        assignments = clusterer.fit_transform(trjs)

        for sliding_window in [True, False]:
            model = ContinuousTimeMSM(lag_time=100, sliding_window=sliding_window)
            model.fit(assignments)
            assert model.optimizer_state_.success

def test_fit_1():
    # call fit, compare to MSM
    sequence = [0, 0, 0, 1, 1, 1, 0, 0, 2, 2, 0, 1, 1, 1, 2, 2, 2, 2, 2]
    model = ContinuousTimeMSM(verbose=False)
    model.fit([sequence])

    msm = MarkovStateModel(verbose=False)
    msm.fit([sequence])

    # they shouldn't be equal in general, but for this input they seem to be
    np.testing.assert_array_almost_equal(model.transmat_, msm.transmat_)

def test_doublewell():
    X = load_doublewell(random_state=0)['trajectories']
    for i in range(3):
        Y = NDGrid(n_bins_per_feature=10).fit_transform([X[i]])
        model1 = MarkovStateModel(verbose=False).fit(Y)
        model2 = ContinuousTimeMSM().fit(Y)

        print('MSM uncertainty timescales:')
        print(model1.uncertainty_timescales())
        print('ContinuousTimeMSM uncertainty timescales:')
        print(model2.uncertainty_timescales())
        print()

def test_dump():
    # gh-713
    sequence = [0, 0, 0, 1, 1, 1, 0, 0, 2, 2, 0, 1, 1, 1, 2, 2, 2, 2, 2]
    model = ContinuousTimeMSM(verbose=False)
    model.fit([sequence])

    d = tempfile.mkdtemp()
    try:
        utils.dump(model, '{}/cmodel'.format(d))
        m2 = utils.load('{}/cmodel'.format(d))
        np.testing.assert_array_almost_equal(model.transmat_, m2.transmat_)
    finally:
        shutil.rmtree(d)

def test_score_2():
    ds = MullerPotential(random_state=0).get_cached().trajectories
    cluster = NDGrid(n_bins_per_feature=6,
                     min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
                     max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])
    assignments = cluster.fit_transform(ds)
    test_indices = [5, 0, 4, 1, 2]
    train_indices = [3, 6, 7, 8, 9]

    model = ContinuousTimeMSM(lag_time=3, n_timescales=1)
    model.fit([assignments[i] for i in train_indices])
    test = model.score([assignments[i] for i in test_indices])
    train = model.score_
    print('train', train, 'test', test)
    assert 1 <= test < 2
    assert 1 <= train < 2

def test_hessian_2():
    n = 3
    seqs = [
        [1, 1, 1, 1, 1, 2, 2, 2, 2, 1, 1, 1, 1, 2, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2,
         2, 1, 1, 1, 1, 2, 3, 3, 3, 3]]

    model = ContinuousTimeMSM().fit(seqs)
    print(model.timescales_)
    print(model.uncertainty_timescales())
    theta = model.theta_
    C = model.countsmat_
    print(C)

    C_flat = (C + C.T)[np.triu_indices_from(C, k=1)]
    print(C_flat)
    print('theta', theta, '\n')
    inds = np.where(theta != 0)[0]

    hessian1 = _ratematrix.hessian(theta, C, inds=inds)
    hessian2 = nd.Jacobian(lambda x: _ratematrix.loglikelihood(x, C)[1])(theta)
    hessian3 = nd.Hessian(lambda x: _ratematrix.loglikelihood(x, C)[0])(theta)

    np.set_printoptions(precision=3)

    # H1 = hessian1[np.ix_(active, active)]
    # H2 = hessian2[np.ix_(active, active)]
    # H3 = hessian2[np.ix_(active, active)]

    print(hessian1, '\n')
    print(hessian2, '\n')
    # print(hessian3)
    print('\n')

    info1 = np.zeros((len(theta), len(theta)))
    info2 = np.zeros((len(theta), len(theta)))
    info1[np.ix_(inds, inds)] = scipy.linalg.pinv(-hessian1)
    info2[np.ix_(inds, inds)] = scipy.linalg.pinv(-hessian2[np.ix_(inds, inds)])

    print('Inverse Hessian')
    print(info1)
    print(info2)
    # print(scipy.linalg.pinv(hessian2))
    # print(scipy.linalg.pinv(hessian1)[np.ix_(last, last)])
    # print(scipy.linalg.pinv(hessian2)[np.ix_(last, last)])

    print(_ratematrix.sigma_pi(info1, theta, n))
    print(_ratematrix.sigma_pi(info2, theta, n))

def test_score_2():
    from msmbuilder.example_datasets.muller import MULLER_PARAMETERS as PARAMS
    ds = MullerPotential(random_state=0).get()['trajectories']
    cluster = NDGrid(n_bins_per_feature=6,
          min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
          max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])
    assignments = cluster.fit_transform(ds)
    test_indices = [5, 0, 4, 1, 2]
    train_indices = [3, 6, 7, 8, 9]

    model = ContinuousTimeMSM(lag_time=3, n_timescales=1)
    model.fit([assignments[i] for i in train_indices])
    test = model.score([assignments[i] for i in test_indices])
    train = model.score_
    print('train', train, 'test', test)
    assert 1 <= test < 2
    assert 1 <= train < 2

def test_score_3():
    ds = MullerPotential(random_state=0).get_cached().trajectories
    cluster = NDGrid(n_bins_per_feature=6,
                     min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
                     max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])

    assignments = cluster.fit_transform(ds)

    train_indices = [9, 4, 3, 6, 2]
    test_indices = [8, 0, 5, 7, 1]

    model = ContinuousTimeMSM(lag_time=3, n_timescales=1, sliding_window=False,
                              ergodic_cutoff=1)
    train_data = [assignments[i] for i in train_indices]
    test_data = [assignments[i] for i in test_indices]

    model.fit(train_data)
    train = model.score_
    test = model.score(test_data)
    print(train, test)

def test_score_3():
    from msmbuilder.example_datasets.muller import MULLER_PARAMETERS as PARAMS

    cluster = NDGrid(n_bins_per_feature=6,
          min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
          max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])

    ds = MullerPotential(random_state=0).get()['trajectories']
    assignments = cluster.fit_transform(ds)

    train_indices = [9, 4, 3, 6, 2]
    test_indices = [8, 0, 5, 7, 1]

    model = ContinuousTimeMSM(lag_time=3, n_timescales=1, sliding_window=False, ergodic_cutoff=1)
    train_data = [assignments[i] for i in train_indices]
    test_data = [assignments[i] for i in test_indices]

    model.fit(train_data)
    train = model.score_
    test = model.score(test_data)
    print(train, test)

def test_hessian():
    grid = NDGrid(n_bins_per_feature=10, min=-np.pi, max=np.pi)
    seqs = grid.fit_transform(load_doublewell(random_state=0)['trajectories'])
    seqs = [seqs[i] for i in range(10)]

    lag_time = 10
    model = ContinuousTimeMSM(verbose=True, lag_time=lag_time)
    model.fit(seqs)
    msm = MarkovStateModel(verbose=False, lag_time=lag_time)
    print(model.summarize())
    print('MSM timescales\n', msm.fit(seqs).timescales_)
    print('Uncertainty K\n', model.uncertainty_K())
    print('Uncertainty pi\n', model.uncertainty_pi())

def test_hessian_3():
    grid = NDGrid(n_bins_per_feature=4, min=-np.pi, max=np.pi)
    trajs = DoubleWell(random_state=0).get_cached().trajectories
    seqs = grid.fit_transform(trajs)
    seqs = [seqs[i] for i in range(10)]

    lag_time = 10
    model = ContinuousTimeMSM(verbose=False, lag_time=lag_time)
    model.fit(seqs)
    msm = MarkovStateModel(verbose=False, lag_time=lag_time)
    print(model.summarize())
    # print('MSM timescales\n', msm.fit(seqs).timescales_)
    print('Uncertainty K\n', model.uncertainty_K())
    print('Uncertainty eigs\n', model.uncertainty_eigenvalues())

def test_fit_2():
    grid = NDGrid(n_bins_per_feature=5, min=-np.pi, max=np.pi)
    seqs = grid.fit_transform(load_doublewell(random_state=0)['trajectories'])

    model = ContinuousTimeMSM(verbose=True, lag_time=10)
    model.fit(seqs)
    t1 = np.sort(model.timescales_)
    t2 = -1/np.sort(np.log(np.linalg.eigvals(model.transmat_))[1:])

    model = MarkovStateModel(verbose=False, lag_time=10)
    model.fit(seqs)
    t3 = np.sort(model.timescales_)

    np.testing.assert_array_almost_equal(t1, t2)
    # timescales should be similar to MSM (withing 50%)
    assert abs(t1[-1] - t3[-1]) / t1[-1] < 0.50

def test_guess():
    ds = MullerPotential(random_state=0).get_cached().trajectories
    cluster = NDGrid(n_bins_per_feature=5,
                     min=[PARAMS['MIN_X'], PARAMS['MIN_Y']],
                     max=[PARAMS['MAX_X'], PARAMS['MAX_Y']])
    assignments = cluster.fit_transform(ds)

    model1 = ContinuousTimeMSM(guess='log')
    model1.fit(assignments)

    model2 = ContinuousTimeMSM(guess='pseudo')
    model2.fit(assignments)

    diff = model1.loglikelihoods_[-1] - model2.loglikelihoods_[-1]
    assert np.abs(diff) < 1e-3
    assert np.max(np.abs(model1.ratemat_ - model2.ratemat_)) < 1e-1