def test_featureselector():
trajectories = AlanineDipeptide().get_cached().trajectories
fs = FeatureSelector(FEATS, which_feat="phi")
assert fs.which_feat == ["phi"]
y1 = fs.partial_transform(trajectories[0])
y_ref1 = FEATS[0][1].partial_transform(trajectories[0])
np.testing.assert_array_almost_equal(y_ref1, y1)
def test_featureselector():
trajectories = AlanineDipeptide().get_cached().trajectories
fs = FeatureSelector(FEATS, which_feat='phi')
assert fs.which_feat == ['phi']
y1 = fs.partial_transform(trajectories[0])
y_ref1 = FEATS[0][1].partial_transform(trajectories[0])
np.testing.assert_array_almost_equal(y_ref1, y1)
def test_variancethreshold_vs_sklearn():
trajectories = AlanineDipeptide().get_cached().trajectories
fs = FeatureSelector(FEATS)
vt = VarianceThreshold(0.1)
vtr = VarianceThresholdR(0.1)
y = fs.partial_transform(trajectories[0])
z1 = vt.fit_transform([y])[0]
z_ref1 = vtr.fit_transform(y)
np.testing.assert_array_almost_equal(z_ref1, z1)
def test_variancethreshold_vs_sklearn():
trajectories = AlanineDipeptide().get_cached().trajectories
fs = FeatureSelector(FEATS)
vt = VarianceThreshold(0.1)
vtr = VarianceThresholdR(0.1)
y = fs.partial_transform(trajectories[0])
z1 = vt.fit_transform([y])[0]
z_ref1 = vtr.fit_transform(y)
np.testing.assert_array_almost_equal(z_ref1, z1)
def test_which_feat_types():
# trajectories = AlanineDipeptide().get_cached().trajectories
fs = FeatureSelector(FEATS, which_feat=('phi', 'psi'))
assert fs.which_feat == ['phi', 'psi']
fs = FeatureSelector(FEATS, which_feat=set(('phi', 'psi')))
assert fs.which_feat == ['phi', 'psi'] or fs.which_feat == ['psi', 'phi']
try:
fs = FeatureSelector(FEATS, which_feat={'phi': 'psi'})
assert False
except TypeError:
pass
try:
fs = FeatureSelector(FEATS, which_feat=['phiii'])
assert False
except ValueError:
pass
def test_FeatureSelector_describe_features():
rnd_traj = np.random.randint(len(trajectories))
f_ca = ContactFeaturizer(scheme='CA', ignore_nonprotein=True)
f1 = f_ca.transform([trajectories[rnd_traj]])
df1 = pd.DataFrame(f_ca.describe_features(trajectories[rnd_traj]))
f_dih = DihedralFeaturizer()
f2 = f_dih.transform([trajectories[rnd_traj]])
df2 = pd.DataFrame(f_dih.describe_features(trajectories[rnd_traj]))
df_dict = {}
df_dict["ca"] = df1
df_dict["dih"] = df2
f_comb = FeatureSelector([('ca', f_ca), ('dih', f_dih)])
f3 = f_comb.transform([trajectories[rnd_traj]])
df3 = pd.DataFrame(f_comb.describe_features(trajectories[rnd_traj]))
assert len(df3) == len(df1) + len(df2)
df4 = pd.concat([df_dict[i] for i in f_comb.feat_list])
# lets randomly compare 40 features
for i in np.random.choice(range(len(df3)), 40):
for j in df3.columns:
assert eq(df3.iloc[i][j], df4.iloc[i][j])
def test_FeatureSelector_describe_features():
rnd_traj = np.random.randint(len(trajectories))
f_ca = ContactFeaturizer(scheme='CA', ignore_nonprotein=True)
f1 = f_ca.transform([trajectories[rnd_traj]])
df1 = pd.DataFrame(f_ca.describe_features(trajectories[rnd_traj]))
f_dih = DihedralFeaturizer()
f2 = f_dih.transform([trajectories[rnd_traj]])
df2 = pd.DataFrame(f_dih.describe_features(trajectories[rnd_traj]))
df_dict = {}
df_dict["ca"] = df1
df_dict["dih"] = df2
f_comb = FeatureSelector([('ca', f_ca), ('dih', f_dih)])
f3 = f_comb.transform([trajectories[rnd_traj]])
df3 = pd.DataFrame(f_comb.describe_features(trajectories[rnd_traj]))
assert len(df3) == len(df1) + len(df2)
df4 = pd.concat([df_dict[i] for i in f_comb.feat_list])
# lets randomly compare 40 features
for i in np.random.choice(range(len(df3)), 40):
for j in df3.columns:
assert eq(df3.iloc[i][j], df4.iloc[i][j])
def Get_combined_features_villin():
from msmbuilder.featurizer import DihedralFeaturizer
from msmbuilder.featurizer import ContactFeaturizer
diheds= DihedralFeaturizer()
contacts=ContactFeaturizer()
features=[("di_villin",diheds),("con_villin",contacts)]
import os
import shutil
os.chdir('/homes/anuginueni/traj_villin')
if(os.path.isdir('/homes/anuginueni/traj_villin/combined')):
shutil.rmtree('/homes/anuginueni/traj_villin/combined')
from msmbuilder.dataset import dataset
xyz = dataset( "/homes/anuginueni/traj_villin/*.xtc",topology='/homes/anuginueni/traj_villin/filtered.pdb',stride=5)
from msmbuilder.feature_selection import FeatureSelector
comb_features=FeatureSelector(features)
co=xyz.fit_transform_with(comb_features, '/homes/anuginueni/traj_villin/combined/', fmt='dir-npy')
return co
#
# TIMESCALES
#
# The data will be loaded with a stride of 10 frames. Each fame is 50ps, so the time per frame will be
# 500ps/frame or 0.5ns/frame.
# Each trajectory is 1000 frames long
# Lag time will be 40 frames (20 ns) based on a visual inspection of /Misc/MSM_lag_time.ipynb
to_ns = 0.5
msm_lag = int(40 / to_ns)
#
# FEATURE INDICES
#
all_idx = np.load('indices_all.npy')
#
# OTHER PARAMETERS
#
ref_traj = md.load('../Data/data/trajectory-1.xtc',
top='../Data/data/fs-peptide.pdb')
featurizer = FeatureSelector(features=feats)
pipe = Pipeline([('features', featurizer),
('variance_cut', VarianceThreshold()),
('scaling', RobustScaler()), ('cluster', MiniBatchKMeans()),
('msm', MarkovStateModel(lag_time=msm_lag, verbose=False))])
save_generic(pipe, 'model.pickl')
#
# TIMESCALES
#
# The data will be loaded with a stride of 10 frames. Each fame is 50ps, so the time per frame will be
# 500ps/frame or 0.5ns/frame.
# Each trajectory is 1000 frames long
# Lag time will be 40 frames (20 ns) based on a visual inspection of /Misc/MSM_lag_time.ipynb
features = tica_unstructured_features
to_ns = 0.5
msm_lag = int(40/to_ns)
#
# MODEL
#
pipe = Pipeline([('features', FeatureSelector(features=tica_unstructured_features)),
('variance_cut', VarianceThreshold()),
('scaling', RobustScaler()),
('tica', tICA(kinetic_mapping=True)),
('cluster', MiniBatchKMeans()),
('msm', MarkovStateModel(lag_time=msm_lag, verbose=False, n_timescales=2))])
#
# SAVE MODEL
#
savedir = 'rand-tica-all'
save_generic(pipe, '{}/model.pickl'.format(savedir))
print_feature_names(features, join(savedir, 'feature_list.txt'))
def test_featureselector_transform():
trajectories = AlanineDipeptide().get_cached().trajectories
fs = FeatureSelector(FEATS, which_feat='psi')
y1 = fs.transform(trajectories)
assert len(y1) == len(trajectories)
def test_featureselector_transform():
trajectories = AlanineDipeptide().get_cached().trajectories
fs = FeatureSelector(FEATS, which_feat="psi")
y1 = fs.transform(trajectories)
assert len(y1) == len(trajectories)
def test_featureselector_order():
fs1 = FeatureSelector(FEATS)
fs2 = FeatureSelector(FEATS[::-1])
assert fs1.which_feat == ['phi', 'psi']
assert fs2.which_feat == ['psi', 'phi']
