def test_1():
#Compare msmbuilder.pca with sklearn.decomposition
pcar = PCAr()
pcar.fit(np.concatenate(trajs))
pca = PCA()
pca.fit(trajs)
y_ref1 = pcar.transform(trajs[0])
y1 = pca.transform(trajs)[0]
np.testing.assert_array_almost_equal(y_ref1, y1)
np.testing.assert_array_almost_equal(pca.components_, pcar.components_)
np.testing.assert_array_almost_equal(pca.explained_variance_,
pcar.explained_variance_)
np.testing.assert_array_almost_equal(pca.mean_, pcar.mean_)
np.testing.assert_array_almost_equal(pca.n_components_, pcar.n_components_)
np.testing.assert_array_almost_equal(pca.noise_variance_,
pcar.noise_variance_)
def test_1():
#Compare msmbuilder.pca with sklearn.decomposition
pcar = PCAr()
pcar.fit(np.concatenate(trajs))
pca = PCA()
pca.fit(trajs)
y_ref1 = pcar.transform(trajs[0])
y1 = pca.transform(trajs)[0]
np.testing.assert_array_almost_equal(y_ref1, y1)
np.testing.assert_array_almost_equal(pca.components_, pcar.components_)
np.testing.assert_array_almost_equal(pca.explained_variance_,
pcar.explained_variance_)
np.testing.assert_array_almost_equal(pca.mean_, pcar.mean_)
np.testing.assert_array_almost_equal(pca.n_components_, pcar.n_components_)
np.testing.assert_array_almost_equal(pca.noise_variance_,
pcar.noise_variance_)
def test_generator():
# Check to see if it works with a generator
traj_dict = dict((i, t) for i, t in enumerate(trajs))
pcar = PCAr()
pcar.fit(np.concatenate(trajs))
pca = PCA()
# on python 3, dict.values() returns a generator
pca.fit(traj_dict.values())
y_ref1 = pcar.transform(trajs[0])
y1 = pca.transform(trajs)[0]
np.testing.assert_array_almost_equal(y_ref1, y1)
np.testing.assert_array_almost_equal(pca.components_, pcar.components_)
np.testing.assert_array_almost_equal(pca.explained_variance_,
pcar.explained_variance_)
np.testing.assert_array_almost_equal(pca.mean_, pcar.mean_)
np.testing.assert_array_almost_equal(pca.n_components_, pcar.n_components_)
np.testing.assert_array_almost_equal(pca.noise_variance_,
pcar.noise_variance_)
def test_generator():
# Check to see if it works with a generator
traj_dict = dict((i, t) for i, t in enumerate(trajs))
pcar = PCAr()
pcar.fit(np.concatenate(trajs))
pca = PCA()
# on python 3, dict.values() returns a generator
pca.fit(traj_dict.values())
y_ref1 = pcar.transform(trajs[0])
y1 = pca.transform(trajs)[0]
np.testing.assert_array_almost_equal(y_ref1, y1)
np.testing.assert_array_almost_equal(pca.components_, pcar.components_)
np.testing.assert_array_almost_equal(pca.explained_variance_,
pcar.explained_variance_)
np.testing.assert_array_almost_equal(pca.mean_, pcar.mean_)
np.testing.assert_array_almost_equal(pca.n_components_, pcar.n_components_)
np.testing.assert_array_almost_equal(pca.noise_variance_,
pcar.noise_variance_)
class SolventShellsAnalysis():
"""Do analysis on solvent shell results.
The protocol is as follows:
1. Normalize by shell volume
2. Flatten to 2d (for compatibility with tICA, et. al.)
3. Remove zero-variance features
:param seqs: Sequences of counts. List of shape
(n_frames, n_solute, n_shells) arrays
:param shell_w: Shell width (nm)
"""
def __init__(self, seqs, shell_w):
self._seqs3d_unnormed = seqs
self._seqs3d = None
self._seqs2d_unpruned = None
self._seqs2d = None
self._deleted = None
self.shell_w = shell_w
self.tica = None
self.pca = None
self.ticax = None
self.pcax = None
@property
def seqs3d_unnormed(self):
"""Unnormalized (input) sequences"""
return self._seqs3d_unnormed
@property
def seqs3d(self):
"""Normalized 3d sequences."""
if self._seqs3d is None:
self._seqs3d = [normalize(fp3d, self.shell_w) for fp3d in
self.seqs3d_unnormed]
return self._seqs3d
@property
def seqs2d_unpruned(self):
"""Reshaped (2D) sequences."""
if self._seqs2d_unpruned is None:
self._seqs2d_unpruned = [reshape(fp3d) for fp3d in self.seqs3d]
return self._seqs2d_unpruned
@property
def seqs2d(self):
"""Reshaped with zero-variance features removed.
Input this to tICA, MSM, etc.
"""
if self._seqs2d is None:
self._seqs2d, self._deleted = prune_all(self.seqs2d_unpruned)
return self._seqs2d
@property
def deleted(self):
"""Which features (2d-indexing) we deleted."""
if self._deleted is None:
self._seqs2d, self._deleted = prune_all(self.seqs2d_unpruned)
return self._deleted
def fit_tica(self, lag_time):
self.tica = tICA(n_components=10, lag_time=lag_time,
weighted_transform=True)
self.tica.fit(self.seqs2d)
self.ticax = self.tica.transform(self.seqs2d)
def fit_pca(self):
self.pca = PCA(n_components=10)
self.pca.fit(self.seqs2d)
self.pcax = self.pca.transform(self.seqs2d)
class SolventShellsAnalysis():
"""Do analysis on solvent shell results.
The protocol is as follows:
1. Normalize by shell volume
2. Flatten to 2d (for compatibility with tICA, et. al.)
3. Remove zero-variance features
:param seqs: Sequences of counts. List of shape
(n_frames, n_solute, n_shells) arrays
:param shell_w: Shell width (nm)
"""
def __init__(self, seqs, shell_w):
self._seqs3d_unnormed = seqs
self._seqs3d = None
self._seqs2d_unpruned = None
self._seqs2d = None
self._deleted = None
self.shell_w = shell_w
self.tica = None
self.pca = None
self.ticax = None
self.pcax = None
@property
def seqs3d_unnormed(self):
"""Unnormalized (input) sequences"""
return self._seqs3d_unnormed
@property
def seqs3d(self):
"""Normalized 3d sequences."""
if self._seqs3d is None:
self._seqs3d = [
normalize(fp3d, self.shell_w) for fp3d in self.seqs3d_unnormed
]
return self._seqs3d
@property
def seqs2d_unpruned(self):
"""Reshaped (2D) sequences."""
if self._seqs2d_unpruned is None:
self._seqs2d_unpruned = [reshape(fp3d) for fp3d in self.seqs3d]
return self._seqs2d_unpruned
@property
def seqs2d(self):
"""Reshaped with zero-variance features removed.
Input this to tICA, MSM, etc.
"""
if self._seqs2d is None:
self._seqs2d, self._deleted = prune_all(self.seqs2d_unpruned)
return self._seqs2d
@property
def deleted(self):
"""Which features (2d-indexing) we deleted."""
if self._deleted is None:
self._seqs2d, self._deleted = prune_all(self.seqs2d_unpruned)
return self._deleted
def fit_tica(self, lag_time):
self.tica = tICA(n_components=10,
lag_time=lag_time,
weighted_transform=True)
self.tica.fit(self.seqs2d)
self.ticax = self.tica.transform(self.seqs2d)
def fit_pca(self):
self.pca = PCA(n_components=10)
self.pca.fit(self.seqs2d)
self.pcax = self.pca.transform(self.seqs2d)
