def test_plot_voronoi():
kmeans = KMeans(n_clusters=15)
kmeans.fit([data])
ax = plot_voronoi(kmeans)
assert isinstance(ax, Subplot)
def test_plot_voronoi(self):
kmeans = KMeans(n_clusters=15)
kmeans.fit([data])
ax = plot_voronoi(kmeans, xlabel='x', ylabel='y')
assert isinstance(ax, SubplotBase)
def cluster_msm(sequences,n_states, lag_times):
for n in n_states:
states = KMeans(n_clusters=n)
states.fit(sequences)
io.dump(states,str(n)+'n_cl.pkl')
ts=np.zeros(5)
for lag_time in lag_times:
msm = MarkovStateModel(lag_time=lag_time, verbose=False,n_timescales=5)
msm.fit(states.labels_)
ts1=msm.timescales_
ts=np.vstack((ts,ts1))
io.dump(msm,str(n)+'n_'+str(lag_time)+'lt_msm.pkl')
ts=np.delete(ts, (0), axis=0)
io.dump(ts,str(n)+'n_timescales.pkl')
def cluster_project_wrapper(proj_folder,feature_dict,n_states):
if os.path.exists(proj_folder+"/assignments.pkl"):
return verboseload(proj_folder+"/cluster_mdl.pkl"),verboseload(proj_folder+"/assignments.pkl")
elif os.path.exists(proj_folder+"/cluster_mdl.pkl"):
cluster_mdl = verboseload(proj_folder+"/cluster_mdl.pkl")
else:
cluster_mdl = KMeans(n_clusters = n_states)
cluster_mdl.fit([feature_dict[i] for i in feature_dict.keys()])
assignments={}
for i in feature_dict.keys():
assignments[i] = cluster_mdl.transform([feature_dict[i]])
verbosedump(cluster_mdl,proj_folder+"/cluster_mdl.pkl")
verbosedump(assignments,proj_folder+"/assignments.pkl")
return cluster_mdl,assignments
def cluster_project_wrapper(proj_folder, feature_dict, n_states):
if os.path.exists(proj_folder + "/assignments.pkl"):
return verboseload(proj_folder +
"/cluster_mdl.pkl"), verboseload(proj_folder +
"/assignments.pkl")
elif os.path.exists(proj_folder + "/cluster_mdl.pkl"):
cluster_mdl = verboseload(proj_folder + "/cluster_mdl.pkl")
else:
cluster_mdl = KMeans(n_clusters=n_states)
cluster_mdl.fit([feature_dict[i] for i in feature_dict.keys()])
assignments = {}
for i in feature_dict.keys():
assignments[i] = cluster_mdl.transform([feature_dict[i]])
verbosedump(cluster_mdl, proj_folder + "/cluster_mdl.pkl")
verbosedump(assignments, proj_folder + "/assignments.pkl")
return cluster_mdl, assignments
def cluster():
'''
This function perfomes K-means clustering on the tICA space and saves assignsment files for each trajectory.
Cluster centers are also saved at `microstate_centers.txt` file.
'''
cluster = KMeans(n_clusters=n_states,n_jobs=-1,verbose=0, max_iter=100, tol=0.0001,)
dataset, ev0, ev1 = [], [], []
print "Loading projected data..."
for i in tqdm(range(start_traj, end_traj+1)):
a = io.loadh('%s/traj%d_%s.h5' %(proj_path,i,traj_name))['arr_0']
a = a[:,0:2]
dataset.append(a)
ev0.extend(a[:,0])
ev1.extend(a[:,1])
print "Clustering %d datapoints..." %len(ev0)
cluster.fit(dataset)
for i in range(start_traj,end_traj+1):
np.savetxt('%s/assigns_%d.txt' %(out_path,i),np.array(cluster.labels_[i-start_traj]),fmt='%d')
np.savetxt('%s/microstate_centers.txt' %out_path,np.array(cluster.cluster_centers_))
print "Saved microstate assignments and microstate centers at %s" %out_path
return cluster.cluster_centers_, np.array(ev0), np.array(ev1)
topFile='NarK-strip.pdb'
dataset = []
ls = []
for i in sorted(glob.glob('*.npy')):
a = np.load(i)
b = np.array(a)
dataset.append(b)
ls.append(i)
print(i)
np.save('list', ls)
#trajs = [np.load('data.npy')]
# make cluster of the tICs trajectories
cluster = KMeans(n_clusters=myn_clusters)
cluster.fit(dataset)
l = cluster.labels_
T = []
for trj in glob.glob('*strip.mdcrd'):
T.append(trj)
T.sort()
# Write the output file, which have the information about population of each cluster,
# trajectory name and frame number of corresponding frame
asFunctions.writeOPF(l, T, myn_clusters, n_samples)
# Based on information in output file, build the cpptraj input file
asFunctions.CpptrajInGen_commonTop(topFile)
#pickle.dump( cluster , open( "tICCluster.pkl", "wb"))
lagtime = 50
for n in n_clusters:
kmeans = KMeans(n_clusters=n, n_jobs=-1)
print "Clustering data to %d clusters..." % n
for fold in range(nFolds):
train_data = []
test_data = []
for i in range(len(tica_data)):
cv = KFold(len(tica_data[i]), n_folds=nFolds)
for current_fold, (train_index, test_index) in enumerate(cv):
if current_fold == fold:
train_data.append(tica_data[i][train_index])
test_data.append(tica_data[i][test_index])
reduced_train_data = sub_sampling_data(train_data, stride=100)
kmeans.fit(reduced_train_data)
assignments_train = kmeans.predict(train_data)
assignments_test = kmeans.predict(test_data)
msm = MarkovStateModel(lag_time=lagtime)
msm.fit(assignments_train)
train_score = msm.score_
test_score = msm.score(assignments_test)
results.append({
'train_score': train_score,
'test_score': test_score,
'n_states': n,
'fold': fold,
'timescales': msm.timescales_
})
