def test_2():
n_features = 3
length = 32
for n_states in [4]:
t1 = np.random.randn(length, n_features)
means = np.random.randn(n_states, n_features)
vars = np.random.rand(n_states, n_features)
transmat = np.random.rand(n_states, n_states)
transmat = transmat / np.sum(transmat, axis=1)[:, None]
startprob = np.random.rand(n_states)
startprob = startprob / np.sum(startprob)
chmm = GaussianHMMCPUImpl(n_states, n_features)
chmm._sequences = [t1]
pyhmm = GaussianHMM(n_components=n_states,
init_params='',
params='',
covariance_type='diag')
chmm.means_ = means.astype(np.float32)
chmm.vars_ = vars.astype(np.float32)
chmm.transmat_ = transmat.astype(np.float32)
chmm.startprob_ = startprob.astype(np.float32)
clogprob, cstats = chmm.do_estep()
pyhmm.means_ = means
pyhmm.covars_ = vars
pyhmm.transmat_ = transmat
pyhmm.startprob_ = startprob
framelogprob = pyhmm._compute_log_likelihood(t1)
fwdlattice = pyhmm._do_forward_pass(framelogprob)[1]
bwdlattice = pyhmm._do_backward_pass(framelogprob)
gamma = fwdlattice + bwdlattice
posteriors = np.exp(gamma.T - logsumexp(gamma, axis=1)).T
stats = pyhmm._initialize_sufficient_statistics()
pyhmm._accumulate_sufficient_statistics(stats, t1, framelogprob,
posteriors, fwdlattice,
bwdlattice, 'stmc')
yield lambda: np.testing.assert_array_almost_equal(
stats['trans'], cstats['trans'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(
stats['post'], cstats['post'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(
stats['obs'], cstats['obs'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(
stats['obs**2'], cstats['obs**2'], decimal=3)
def test_2():
n_features = 3
length = 32
for n_states in [4]:
t1 = np.random.randn(length, n_features)
means = np.random.randn(n_states, n_features)
vars = np.random.rand(n_states, n_features)
transmat = np.random.rand(n_states, n_states)
transmat = transmat / np.sum(transmat, axis=1)[:, None]
startprob = np.random.rand(n_states)
startprob = startprob / np.sum(startprob)
chmm = GaussianHMMCPUImpl(n_states, n_features)
chmm._sequences = [t1]
pyhmm = GaussianHMM(n_components=n_states, init_params='', params='', covariance_type='diag')
chmm.means_ = means.astype(np.float32)
chmm.vars_ = vars.astype(np.float32)
chmm.transmat_ = transmat.astype(np.float32)
chmm.startprob_ = startprob.astype(np.float32)
clogprob, cstats = chmm.do_estep()
pyhmm.means_ = means
pyhmm.covars_ = vars
pyhmm.transmat_ = transmat
pyhmm.startprob_ = startprob
framelogprob = pyhmm._compute_log_likelihood(t1)
fwdlattice = pyhmm._do_forward_pass(framelogprob)[1]
bwdlattice = pyhmm._do_backward_pass(framelogprob)
gamma = fwdlattice + bwdlattice
posteriors = np.exp(gamma.T - logsumexp(gamma, axis=1)).T
stats = pyhmm._initialize_sufficient_statistics()
pyhmm._accumulate_sufficient_statistics(
stats, t1, framelogprob, posteriors, fwdlattice,
bwdlattice, 'stmc')
yield lambda: np.testing.assert_array_almost_equal(stats['trans'], cstats['trans'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(stats['post'], cstats['post'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(stats['obs'], cstats['obs'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(stats['obs**2'], cstats['obs**2'], decimal=3)
def predict(self, obs):
"""Find most likely state sequence corresponding to `obs`.
Parameters
----------
obs : np.ndarray, shape=(n_samples, n_features)
Sequence of n_features-dimensional data points. Each row
corresponds to a single point in the sequence.
Returns
-------
hidden_states : np.ndarray, shape=(n_states)
Index of the most likely states for each observation
"""
_, vl = scipy.linalg.eig(self.transmat_, left=True, right=False)
startprob = vl[:, 0] / np.sum(vl[:, 0])
model = GaussianHMM(n_components=self.n_states, covariance_type='full')
model.startprob_ = startprob
model.transmat_ = self.transmat_
model.means_ = self.means_
model.covars_ = self.covars_
return model.predict(obs)
def predict(self, obs):
"""Find most likely state sequence corresponding to `obs`.
Parameters
----------
obs : np.ndarray, shape=(n_samples, n_features)
Sequence of n_features-dimensional data points. Each row
corresponds to a single point in the sequence.
Returns
-------
hidden_states : np.ndarray, shape=(n_states)
Index of the most likely states for each observation
"""
_, vl = scipy.linalg.eig(self.transmat_, left=True, right=False)
startprob = vl[:, 0] / np.sum(vl[:, 0])
model = GaussianHMM(n_components=self.n_states, covariance_type='full')
model.startprob_ = startprob
model.transmat_ = self.transmat_
model.means_ = self.means_
model.covars_ = self.covars_
return model.predict(obs)
def test_2():
np.random.seed(42)
n_features = 32
length = 20
#for n_states in [3, 4, 5, 7, 8, 9, 15, 16, 17, 31, 32]:
for n_states in [8]:
t1 = np.random.randn(length, n_features)
means = np.random.randn(n_states, n_features)
vars = np.random.rand(n_states, n_features)
transmat = np.random.rand(n_states, n_states)
transmat = transmat / np.sum(transmat, axis=1)[:, None]
startprob = np.random.rand(n_states)
startprob = startprob / np.sum(startprob)
cuhmm = GaussianHMMCUDAImpl(n_states, n_features)
cuhmm._sequences = [t1]
pyhmm = GaussianHMM(n_components=n_states, init_params='', params='', covariance_type='diag')
cuhmm.means_ = means
cuhmm.vars_ = vars
cuhmm.transmat_ = transmat
cuhmm.startprob_ = startprob
logprob, custats = cuhmm.do_estep()
pyhmm.means_ = means
pyhmm.covars_ = vars
pyhmm.transmat_ = transmat
pyhmm.startprob_ = startprob
pyhmm._initialize_sufficient_statistics()
framelogprob = pyhmm._compute_log_likelihood(t1)
cuframelogprob = cuhmm._get_framelogprob()
yield lambda: np.testing.assert_array_almost_equal(framelogprob, cuframelogprob, decimal=3)
fwdlattice = pyhmm._do_forward_pass(framelogprob)[1]
cufwdlattice = cuhmm._get_fwdlattice()
yield lambda: np.testing.assert_array_almost_equal(fwdlattice, cufwdlattice, decimal=3)
bwdlattice = pyhmm._do_backward_pass(framelogprob)
cubwdlattice = cuhmm._get_bwdlattice()
yield lambda: np.testing.assert_array_almost_equal(bwdlattice, cubwdlattice, decimal=3)
gamma = fwdlattice + bwdlattice
posteriors = np.exp(gamma.T - logsumexp(gamma, axis=1)).T
cuposteriors = cuhmm._get_posteriors()
yield lambda: np.testing.assert_array_almost_equal(posteriors, cuposteriors, decimal=3)
stats = pyhmm._initialize_sufficient_statistics()
pyhmm._accumulate_sufficient_statistics(
stats, t1, framelogprob, posteriors, fwdlattice,
bwdlattice, 'stmc')
print 'ref transcounts'
print transitioncounts(cufwdlattice, cubwdlattice, cuframelogprob, np.log(transmat))
print 'cutranscounts'
print custats['trans']
yield lambda: np.testing.assert_array_almost_equal(stats['trans'], custats['trans'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(stats['post'], custats['post'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(stats['obs'], custats['obs'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(stats['obs**2'], custats['obs**2'], decimal=3)
idx = (viterbi_states==i)
ax.plot_date(x_ax[idx],y_train[idx],'o',label='%dth state'%i)
ax.legend()
ax.set_ylabel('Load (Mlb/Hr)')
ax.set_xlabel('Time')
ax.grid(True)
plt.show()
##############################################################################
#create a new model
modelw = GaussianHMM(n_clusters,covariance_type='diag',n_iter=1000)
modelw._means_ = model.means_[:,1:]
modelw._covars_ = [item[1:,1:] for item in model.covars_]
modelw.transmat_ = model.transmat_
modelw.n_features = model.n_features-1
modelw.startprob_ = model.startprob_
##############################################################################
#RUN ENSEMBLE
def run_ensemble(X_train,y_train,X_test,y_test):
hours = X_train.index.map(lambda x: x.hour)
test_hours = X_test.index.map(lambda x: x.hour)
y_svr = []
y_gbr = []
for i in xrange(24):
X_train_hourly = X_train[hours==i]
y_train_hourly = y_train[hours==i]
X_test_hourly = X_test[test_hours==i]
from sklearn.svm import SVR
y_svr = np.append(y_svr,run_svr(X_train_hourly,y_train_hourly,X_test_hourly))
y_gbr = np.append(y_gbr,run_gbr(X_train_hourly,y_train_hourly,X_test_hourly))
def test_2():
np.random.seed(42)
n_features = 32
length = 20
#for n_states in [3, 4, 5, 7, 8, 9, 15, 16, 17, 31, 32]:
for n_states in [8]:
t1 = np.random.randn(length, n_features)
means = np.random.randn(n_states, n_features)
vars = np.random.rand(n_states, n_features)
transmat = np.random.rand(n_states, n_states)
transmat = transmat / np.sum(transmat, axis=1)[:, None]
startprob = np.random.rand(n_states)
startprob = startprob / np.sum(startprob)
cuhmm = GaussianHMMCUDAImpl(n_states, n_features)
cuhmm._sequences = [t1]
pyhmm = GaussianHMM(n_components=n_states,
init_params='',
params='',
covariance_type='diag')
cuhmm.means_ = means
cuhmm.vars_ = vars
cuhmm.transmat_ = transmat
cuhmm.startprob_ = startprob
logprob, custats = cuhmm.do_estep()
pyhmm.means_ = means
pyhmm.covars_ = vars
pyhmm.transmat_ = transmat
pyhmm.startprob_ = startprob
pyhmm._initialize_sufficient_statistics()
framelogprob = pyhmm._compute_log_likelihood(t1)
cuframelogprob = cuhmm._get_framelogprob()
yield lambda: np.testing.assert_array_almost_equal(
framelogprob, cuframelogprob, decimal=3)
fwdlattice = pyhmm._do_forward_pass(framelogprob)[1]
cufwdlattice = cuhmm._get_fwdlattice()
yield lambda: np.testing.assert_array_almost_equal(
fwdlattice, cufwdlattice, decimal=3)
bwdlattice = pyhmm._do_backward_pass(framelogprob)
cubwdlattice = cuhmm._get_bwdlattice()
yield lambda: np.testing.assert_array_almost_equal(
bwdlattice, cubwdlattice, decimal=3)
gamma = fwdlattice + bwdlattice
posteriors = np.exp(gamma.T - logsumexp(gamma, axis=1)).T
cuposteriors = cuhmm._get_posteriors()
yield lambda: np.testing.assert_array_almost_equal(
posteriors, cuposteriors, decimal=3)
stats = pyhmm._initialize_sufficient_statistics()
pyhmm._accumulate_sufficient_statistics(stats, t1, framelogprob,
posteriors, fwdlattice,
bwdlattice, 'stmc')
print 'ref transcounts'
print transitioncounts(cufwdlattice, cubwdlattice, cuframelogprob,
np.log(transmat))
print 'cutranscounts'
print custats['trans']
yield lambda: np.testing.assert_array_almost_equal(
stats['trans'], custats['trans'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(
stats['post'], custats['post'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(
stats['obs'], custats['obs'], decimal=3)
yield lambda: np.testing.assert_array_almost_equal(
stats['obs**2'], custats['obs**2'], decimal=3)
