def test_whitening_on_whitened(): data = np.random.normal(size=(1000, 50)) from sklearn.decomposition import PCA data = PCA(whiten=True).fit_transform(data) cov = Covariance().fit(data).fetch_model() whitened = cov.whiten(data) np.testing.assert_array_almost_equal(whitened, data)
def test_XX_weighted_meanconst(self): est = Covariance(lagtime=self.lag, compute_c0t=False, bessels_correction=False) cc = est.fit(self.data - self.mean_const, weights=self.data_weights).fetch_model() np.testing.assert_allclose(cc.mean_0, self.mx_c_wobj_lag0) np.testing.assert_allclose(cc.cov_00, self.Mxx_c_wobj_lag0) cc = est.fit(self.data - self.mean_const, weights=self.data_weights, column_selection=self.cols_2).fetch_model() np.testing.assert_allclose(cc.cov_00, self.Mxx_c_wobj_lag0[:, self.cols_2])
def test_XX_weightobj_meanfree(self): # many passes est = Covariance(lagtime=self.lag, compute_c0t=False, remove_data_mean=True, bessels_correction=False) cc = est.fit(self.data, weights=self.data_weights, n_splits=10).fetch_model() np.testing.assert_allclose(cc.mean_0, self.mx_wobj_lag0) np.testing.assert_allclose(cc.cov_00, self.Mxx0_wobj_lag0) cc = est.fit(self.data, column_selection=self.cols_2, weights=self.data_weights).fetch_model() np.testing.assert_allclose(cc.cov_00, self.Mxx0_wobj_lag0[:, self.cols_2])
def test_XX_with_mean(self): # many passes est = Covariance(lagtime=self.lag, compute_c0t=False, remove_data_mean=False, bessels_correction=False) cc = est.fit(self.data).fetch_model() np.testing.assert_allclose(cc.mean_0, self.mx_lag0) np.testing.assert_allclose(cc.cov_00, self.Mxx_lag0) cc = est.fit(self.data, column_selection=self.cols_2).fetch_model() np.testing.assert_allclose(cc.cov_00, self.Mxx_lag0[:, self.cols_2])
def test_XY_sym_meanconst(self): est = Covariance(lagtime=self.lag, compute_c0t=True, reversible=True, bessels_correction=False) cc = est.fit(self.Xc_lag0).fetch_model() np.testing.assert_allclose(cc.mean_0, self.m_c_sym) np.testing.assert_allclose(cc.cov_00, self.Mxx_c_sym) np.testing.assert_allclose(cc.cov_0t, self.Mxy_c_sym) cc = est.fit(self.Xc_lag0, column_selection=self.cols_2).fetch_model() np.testing.assert_allclose(cc.cov_00, self.Mxx_c_sym[:, self.cols_2]) np.testing.assert_allclose(cc.cov_0t, self.Mxy_c_sym[:, self.cols_2])
def test_multiple_fetch(): # checks that the model instance does not change when the estimator was not updated data = np.random.normal(size=(5000, 3)) est = Covariance(5, compute_c00=True, compute_c0t=False, compute_ctt=False) m1 = est.fit(data).model m2 = est.model m3 = est.partial_fit(np.random.normal(size=(50, 3))).model np.testing.assert_(m1 is m2) np.testing.assert_(m1 is not m3) np.testing.assert_(m2 is not m3)
def test_fit_from_cov(): data = np.random.normal(size=(500, 3)) # fitting with C0t and symmetric covariances, should pass TICA().fit(Covariance(1, compute_c0t=True, reversible=True).fit(data)) with np.testing.assert_raises(ValueError): TICA().fit(Covariance(1, compute_c0t=True, reversible=False).fit(data)) with np.testing.assert_raises(ValueError): TICA().fit(Covariance(1, compute_c0t=False, reversible=True).fit(data))
def test_XXXY_meanfree(self): # many passes est = Covariance(lagtime=self.lag, remove_data_mean=True, compute_c0t=True, bessels_correction=False) cc = est.fit(self.data).fetch_model() np.testing.assert_allclose(cc.mean_0, self.mx) np.testing.assert_allclose(cc.mean_t, self.my) np.testing.assert_allclose(cc.cov_00, self.Mxx0) np.testing.assert_allclose(cc.cov_0t, self.Mxy0) cc = est.fit(self.data, column_selection=self.cols_2).fetch_model() np.testing.assert_allclose(cc.cov_00, self.Mxx0[:, self.cols_2]) np.testing.assert_allclose(cc.cov_0t, self.Mxy0[:, self.cols_2])
def test_XXXY_sym_withmean(self): # many passes est = Covariance(lagtime=self.lag, remove_data_mean=False, compute_c0t=True, reversible=True, bessels_correction=False) cc = est.fit(self.data).fetch_model() np.testing.assert_allclose(cc.mean_0, self.m_sym) np.testing.assert_allclose(cc.cov_00, self.Mxx_sym) np.testing.assert_allclose(cc.cov_0t, self.Mxy_sym) cc = est.fit(self.data, column_selection=self.cols_2).fetch_model() np.testing.assert_allclose(cc.cov_00, self.Mxx_sym[:, self.cols_2]) np.testing.assert_allclose(cc.cov_0t, self.Mxy_sym[:, self.cols_2])
def test_weights(): weights = np.concatenate([np.ones((1001,)) * 1e-16, np.ones((3999,))]) np.testing.assert_equal(len(weights), 5000) data = np.random.normal(size=(5000, 2)) cov = Covariance(lagtime=5, compute_c00=True, compute_c0t=True, compute_ctt=False) model = cov.fit(data, weights=weights, n_splits=64).fetch_model() model2 = cov.fit(data[1002:], weights=weights[1002:], n_splits=55).fetch_model() np.testing.assert_array_almost_equal(model.cov_00, model2.cov_00, decimal=2) np.testing.assert_array_almost_equal(model.cov_0t, model2.cov_0t, decimal=2) np.testing.assert_array_almost_equal(model.mean_0, model2.mean_0, decimal=2) np.testing.assert_array_almost_equal(model.mean_t, model2.mean_t, decimal=2)
def test_XXXY_weightobj_sym_meanfree(self): # many passes est = Covariance(lagtime=self.lag, remove_data_mean=True, compute_c0t=True, reversible=True, bessels_correction=False) cc = est.fit(self.data, weights=self.data_weights).fetch_model() np.testing.assert_allclose(cc.mean_0, self.m_sym_wobj) np.testing.assert_allclose(cc.cov_00, self.Mxx0_sym_wobj) np.testing.assert_allclose(cc.cov_0t, self.Mxy0_sym_wobj) cc = est.fit(self.data, weights=self.data_weights, column_selection=self.cols_2).fetch_model() np.testing.assert_allclose(cc.cov_00, self.Mxx0_sym_wobj[:, self.cols_2]) np.testing.assert_allclose(cc.cov_0t, self.Mxy0_sym_wobj[:, self.cols_2])
def test_non_matching_length(self): n = 100 data = [np.random.random(size=(n, 2)) for n in range(3)] data = (data[:-1], data[1:]) weights = [np.random.random(n) for _ in range(3)] weights[0] = weights[0][:-3] with self.assertRaises(ValueError): Covariance(1, compute_c0t=True).fit(data, weights=weights) with self.assertRaises(ValueError): Covariance(1, compute_c0t=True).fit(data, weights=weights[:10])
def test_XXXY_withmean(self): # many passes est = Covariance(lagtime=self.lag, remove_data_mean=False, compute_c0t=True, bessels_correction=False) cc = est.fit(self.data, n_splits=1).fetch_model() assert not cc.bessels_correction np.testing.assert_allclose(cc.mean_0, self.mx) np.testing.assert_allclose(cc.mean_t, self.my) np.testing.assert_allclose(cc.cov_00, self.Mxx) np.testing.assert_allclose(cc.cov_0t, self.Mxy) cc = est.fit(self.data, n_splits=1, column_selection=self.cols_2).fetch_model() np.testing.assert_allclose(cc.cov_00, self.Mxx[:, self.cols_2]) np.testing.assert_allclose(cc.cov_0t, self.Mxy[:, self.cols_2])
def test_XXXY_weightobj_meanfree(self): for n_splits in [1, 2, 3, 4, 5, 6, 7]: est = Covariance(lagtime=self.lag, remove_data_mean=True, compute_c0t=True, bessels_correction=False) cc = est.fit(self.data, weights=self.data_weights, n_splits=n_splits).fetch_model() np.testing.assert_allclose(cc.mean_0, self.mx_wobj) np.testing.assert_allclose(cc.mean_t, self.my_wobj) np.testing.assert_allclose(cc.cov_00, self.Mxx0_wobj) np.testing.assert_allclose(cc.cov_0t, self.Mxy0_wobj) cc = est.fit(self.data, weights=self.data_weights, column_selection=self.cols_2, n_splits=n_splits).fetch_model() np.testing.assert_allclose(cc.cov_00, self.Mxx0_wobj[:, self.cols_2]) np.testing.assert_allclose(cc.cov_0t, self.Mxy0_wobj[:, self.cols_2])
def test_re_estimate_weight_types(self): # check different types are allowed and re-estimation works x = np.random.random((100, 2)) c = Covariance(lagtime=1, compute_c0t=True) c.fit(x, weights=np.ones((len(x),))).fetch_model() c.fit(x, weights=np.ones((len(x),))).fetch_model() c.fit(x, weights=None).fetch_model() c.fit(x, weights=x[:, 0]).fetch_model()
def test_eig_corr(epsilon, method, canonical_signs, return_rank, hermitian_ctt): data = np.random.normal(size=(5000, 3)) from deeptime.covariance import Covariance covariances = Covariance(lagtime=10, compute_c00=True, compute_ctt=True).fit(data).fetch_model() if not hermitian_ctt: covariances.cov_tt[0, 1] += 1e-6 assert_(not np.allclose(covariances.cov_tt, covariances.cov_tt.T)) out = eig_corr(covariances.cov_00, covariances.cov_tt, epsilon=epsilon, method=method, canonical_signs=canonical_signs, return_rank=return_rank) eigenvalues = out[0] eigenvectors = out[1] if return_rank: rank = out[2] assert_equal(rank, len(eigenvalues)) for r in range(len(out[0])): assert_array_almost_equal(covariances.cov_00 @ eigenvectors[r] * eigenvalues[r], covariances.cov_tt @ eigenvectors[r], decimal=2)
def test_weights_close_to_zero(self): n = 1000 data = [np.random.random(size=(n, 2)) for _ in range(5)] # create some artificial correlations data[0][:, 0] *= np.random.randint(n) data = np.asarray(data) weights = [np.ones(n, dtype=np.float32) for _ in range(5)] # omit the first trajectory by setting a weight close to zero. weights[0][:] = 1E-44 weights = np.asarray(weights) est = Covariance(lagtime=1, compute_c0t=True) for data_traj, weights_traj in zip(data, weights): est.partial_fit((data_traj[:-3], data_traj[3:]), weights=weights_traj[:-3]) cov = est.fetch_model() # cov = covariance_lagged(data, lag=3, weights=weights, chunksize=10) assert np.all(cov.cov_00 < 1)
def test_sanity(fixed_seed, two_state_hmm, model): traj, traj_rot, loader = two_state_hmm tae = setup_tae() if model == 'tae' else setup_tvae() tae.fit(loader, n_epochs=40) out = tae.transform(traj_rot).reshape((-1, 1)) out = Covariance().fit(out).fetch_model().whiten(out) dtraj = dt.clustering.Kmeans(2).fit(out).transform(out) msm = dt.markov.msm.MaximumLikelihoodMSM().fit_from_discrete_timeseries( dtraj, 1).fetch_model() assert_array_almost_equal(msm.transition_matrix, [[.9, .1], [.1, .9]], decimal=1)
def test_weights_incompatible(): data = np.random.normal(size=(5000, 3)) est = Covariance(5) with np.testing.assert_raises(ValueError): est.fit(data, weights=np.arange(10)) # incompatible shape with np.testing.assert_raises(ValueError): est.fit(data, weights=np.ones((len(data), 2))) # incompatible shape
def test_whitening(): data = np.random.normal(size=(5000, 50)) data = Covariance().fit(data).fetch_model().whiten(data) cov = Covariance().fit(data).fetch_model() np.testing.assert_array_almost_equal(cov.cov_00, np.eye(50), decimal=2) np.testing.assert_array_almost_equal(cov.mean_0, np.zeros_like(cov.mean_0))