def main():
"""
First ARG: list of training files
Second ARG: save name for model
"""
file1 = sys.argv[1]
outname = sys.argv[2]
file_list = [f[0:-1] for f in open(file1, 'r')]
models, transitions, priors = calc_transmat(file_list)
hmm = GaussianHMM(
transitions.shape[0],
"full",
#startprob=priors,
n_iter=500,
transmat=transitions,
init_params='mcs',
params='mcs',
)
feats, _ = load_feats_labels(file_list)
feat, lab = load_feats_labels(file_list)
#hmm.means_ = np.transpose(models['mean'])
#hmm.covars_ = models['sigma']
print 'Fitting'
start = timeit.default_timer()
hmm.fit([np.transpose(feat)])
stop = timeit.default_timer()
print 'Training Time: ' + str(stop - start)
features, labels = load_feats_labels(['audio.arff'])
_, seq = hmm.decode(np.transpose(features))
#print filter(lambda(x,y): x==y, zip(labels, map(int2label, seq)))
print len(filter(lambda (x, y): x == y, zip(labels, map(int2label, seq))))
pickle.dump(hmm, open(outname, "wb"))
plt.imshow(transitions, interpolation='nearest')
plt.show()
def main():
"""
First ARG: list of training files
Second ARG: save name for model
"""
file1 = sys.argv[1]
outname = sys.argv[2]
file_list = [f[0:-1] for f in open(file1,'r')]
models, transitions, priors = calc_transmat(file_list)
hmm = GaussianHMM(
transitions.shape[0],
"full",
#startprob=priors,
n_iter=500,
transmat=transitions,
init_params='mcs',
params='mcs',
)
feats, _ = load_feats_labels(file_list)
feat, lab = load_feats_labels(file_list)
#hmm.means_ = np.transpose(models['mean'])
#hmm.covars_ = models['sigma']
print 'Fitting'
start = timeit.default_timer()
hmm.fit([np.transpose(feat)])
stop = timeit.default_timer()
print 'Training Time: ' + str(stop - start)
features, labels = load_feats_labels(['audio.arff'])
_, seq = hmm.decode(np.transpose(features))
#print filter(lambda(x,y): x==y, zip(labels, map(int2label, seq)))
print len(filter(lambda(x,y): x==y, zip(labels, map(int2label, seq))))
pickle.dump(hmm, open(outname, "wb"))
plt.imshow(transitions, interpolation='nearest')
plt.show()
for i in range(n_states):
print 'checking if initial covs are pos-definite'
np.linalg.cholesky(covs[i])
print np.linalg.eigvals(covs[i])
tmat, smat = get_tmat_and_smat(pre_states, end=False, start=False)
print tmat, smat
model = GaussianHMM(n_components=n_states, n_iter=n_iter, covariance_type=cov_type, startprob=smat, transmat=tmat, init_params='mc')
model.means_ = means
model.covars_ = covs
sum_inital_ll = 0.0
sum_initial_score = 0.0
sum_initial_map = 0.0
remove_idx = []
for idx, feat_from_list in enumerate(feats_as_list):
if np.shape(feat_from_list)[0] > n_states:
initial_ll, initial_best_seq = model.decode(feat_from_list)
initial_map, initial_best_sep_map = model.decode(feat_from_list, algorithm='map')
sum_initial_score += model.score(feat_from_list)
sum_inital_ll += initial_ll
sum_initial_map += initial_map
else:
remove_idx.append(idx)
print 'too few samples in file', list_of_patient_file_paths[idx], np.shape(feat_from_list)
print 'initial viterbi log-likelihood,', sum_inital_ll
print 'initial score log-likelihood,', sum_initial_score
print 'initial map log-likelihood', sum_initial_map
remove_idx.sort()
remove_idx.reverse()
print 'removing...', remove_idx
for r in remove_idx:
del feats_as_list[r]
t, last_index = overlapped_samples(file_path, incident_reported_time=int(incident_time), overlap=5, window=10, with_end=2)
if t is None:
print file_path, 'is bad'
else:
model.means_ = means
model.covars_ = covs
print 'shape intial', np.shape(covs)
'''
best_seq = model.decode(t)
print 'intial,', best_seq
print 'final means', model.means_
print 'initial trans', tmat
print 'initial startprobs', smat, sum(smat)
'''
model.fit([t])
best_seq = model.decode(t)
print 'file', file_path
print 'final,', best_seq
#print 'final means', model.means_
#print 'final trans', model.transmat_
#print 'final startprob', model.startprob_
if np.isnan(model.means_).any() == False and np.isnan(model.covars_).any() == False:
means = model.means_
covs = np.array([np.diag(model.covars_[0])])
for i in range(1, model.n_components):
covs = np.vstack((covs, [np.diag(model.covars_[i])]))
print 'shape after', np.shape(covs)
tmat = model.transmat_
covars[covars==0] = 1e-5
model = GaussianHMM(numState, covariance_type="tied", n_iter=1000, init_params='abdefghijklnopqrstuvwxyzABDEFGHIJKLNOPQRSTUVWXYZ')
model.means_ = means
model.covars_ = covars
print("Fitting model...")
sys.stdout.flush()
model.fit(data)
print("Decoding states...")
sys.stdout.flush()
# do a loop over everything and record in one long array
states = np.array([])
score = 0
for i in range(0, len(data)):
hidden_states = model.decode(data[i])
states = np.append(states, hidden_states[1])
score = score + model.score(data[i])
print("Saving data...")
sys.stdout.flush()
# save the states and LLH
np.savetxt("data/substates/%s%d/%d/rep_%d_states.txt" % (basepath,stateNum,numState,repInx), states, fmt="%d")
with open("data/substates/%s%d/%d/rep_%d_LLH.txt" % (basepath,stateNum,numState,repInx), 'w') as f:
f.write(str(score))
saveobject(model, "data/substates/%s%d/%d/rep_%d.pk" % (basepath,stateNum,numState,repInx))
means = np.array([[0.0, 0.0], [np.log1p(args.coverage), 0.0],
[0.0, np.log1p(args.coverage)],
[np.log1p(args.coverage / 2),
np.log1p(args.coverage / 2)],
[np.log1p(args.coverage),
np.log1p(args.coverage)]])
cv = 1.0
covars = np.array([[0.01, 0.01], [cv, 0.01], [0.01, cv], [cv / 2, cv / 2],
[cv, cv]])
hidden = ["private"] + ref_samples + ["heterozygous", "pseudohet"]
hmm = GaussianHMM(n_components=len(means), random_state=rs)
hmm._set_means(means)
hmm._set_covars(covars)
## filter sites; compute observation sequence as log(1+count)
keep = np.logical_and((counts.max(1) < args.X_max * args.coverage),
(counts.sum(1) > -1.0))
counts = counts[keep, :]
obs = np.log1p(counts)
starts = np.array([start for start, end in ivls]).reshape((len(ivls), 1))
starts = starts[keep, :]
## run hmm
states = hmm.decode(obs)
## print result to stdout
for i in range(0, counts.shape[0]):
print starts[i, 0], obs[i, 0], obs[i, 1], hidden[states[1][i]]
ax.set_xticks(range(start,end+1),minor=True)
ax.legend()
ax.grid(True,which='both')
plt.show()
##############################################################################
# Run HMM
X_hmm = np.column_stack((y_train,X_train[['hour_of_day','weather','day_of_week']]))
#X_hmm = np.column_stack((y_train,X_train[['hour_of_day','weather']]))
#X_hmm = y_train
from sklearn.hmm import GaussianHMM
n_clusters = 9
#n_clusters = 17
model = GaussianHMM(n_clusters,covariance_type='diag',n_iter=1000)
model.fit([X_hmm])
hidden_states = model.predict(X_hmm)
viterbi_states = model.decode(X_hmm)
x_ax = np.asarray(range(len(X_hmm)))
x_ax = X_train['hour_of_day'] + X_train['day_of_week']*24
#x_ax = X_train['hour_of_day']
x_ax = np.asarray([item.to_datetime() for item in X_train.index])
def plot_HMM(n_clusters,hidden_states,x_ax,y_ax):
#PLOT HIDDEN STATES
fig = plt.figure()
ax = fig.add_subplot(111)
for i in xrange(n_clusters):
print i
idx = (hidden_states==i)
if i<7:
ax.plot(x_ax[idx],y_ax[idx],'o',label='%dth state'%i)
elif i<14:
ax.plot(x_ax[idx],y_ax[idx],'x',label='%dth state'%i)
means = np.array([ [ 0.0, 0.0 ], [ np.log1p(args.coverage), 0.0 ], [ 0.0, np.log1p(args.coverage) ], [ np.log1p(args.coverage/2), np.log1p(args.coverage/2) ], [ np.log1p(args.coverage), np.log1p(args.coverage) ] ]) cv = 1.0 covars = np.array([ [ 0.01, 0.01 ], [ cv, 0.01 ], [ 0.01, cv ], [ cv/2, cv/2 ], [ cv, cv ] ]) hidden = [ "private" ] + ref_samples + [ "heterozygous","pseudohet" ] hmm = GaussianHMM(n_components = len(means), random_state = rs) hmm._set_means(means) hmm._set_covars(covars) ## filter sites; compute observation sequence as log(1+count) keep = np.logical_and((counts.max(1) < args.X_max*args.coverage), (counts.sum(1) > -1.0)) counts = counts[ keep,: ] obs = np.log1p(counts) starts = np.array([ start for start,end in ivls ]).reshape( (len(ivls), 1) ) starts = starts[ keep,: ] ## run hmm states = hmm.decode(obs) ## print result to stdout for i in range(0, counts.shape[0]): print starts[i,0], obs[i,0], obs[i,1], hidden[ states[1][i] ]
