def predict(self, x, init_prob=None, method='hmmlearn', window=-1):
"""Predict result based on HMM
"""
if init_prob is None:
init_prob = np.array(
[1 / self.num_states for i in range(self.num_states)])
if method == 'hmmlearn':
model = MultinomialHMM(self.num_states, n_iter=100)
model.n_features = self.num_observations
model.startprob_ = init_prob
model.emissionprob_ = self.B
model.transmat_ = self.A
if window == -1:
result = model.predict(x)
else:
result = np.zeros(x.shape[0], dtype=np.int)
result[0:window] = model.predict(x[0:window])
for i in range(window, x.shape[0]):
result[i] = model.predict(x[i - window + 1:i + 1])[-1]
else:
if window == -1:
result = self.decode(x, init_prob)
else:
result = np.zeros(x.shape[0], dtype=np.int)
result[0:window] = self.decode(x[0:window], init_prob)
for i in range(window, x.shape[0]):
result[i] = self.decode(x[i - window + 1:i + 1],
init_prob)[-1]
return result
def get_hmm(df, n_components, n_features):
_, state_list = get_ubie_label(df["label"])
pred_list = get_pred_for_hmm(df["pred"])
clf = MultinomialHMM(n_components=n_components)
clf.n_features = n_features
clf.transmat_ = get_transmat(state_list)
clf.emissionprob_ = get_emission(pred_list, state_list)
clf.startprob_ = np.array([0.5, 0.05, 0.4, 0.05])
return clf
def predict_prob(self, x, init_prob=None, window=-1):
"""Predict the probability
"""
if init_prob is None:
init_prob = np.array(
[1 / self.num_states for i in range(self.num_states)])
model = MultinomialHMM(self.num_states)
model.n_features = self.num_observations
model.startprob_ = init_prob
model.emissionprob_ = self.B
model.transmat_ = self.A
return model.predict_proba(x)
0.0, 0.0, 0.2, 0.0, 0.3, 0.0, 0.0, 0.0, 0.0, 0.0, 0.2,
0.0, 0.3, 0.0, 0.0, 0.0
],
[
0.0, 0.0, 0.3, 0.0, 0.7, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
0.0, 0.0, 0.0, 0.0, 0.0
],
[
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
0.0, 0.6, 0.4, 0.0, 0.0
],
[
0.0, 0.0, 0.2, 0.0, 0.8, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
0.0, 0.0, 0.0, 0.0, 0.0
]])
hmmBol.n_features = 16
hmmBol.startprob_ = startprob
hmmBol.transmat_ = transmat
hmmBol.emissionprob_ = emmBol
# Position HMM
emmPos = np.array([[0.0, 0.0, 0.0, 0.0, 1.0], [0.0, 0.0, 0.0, 0.0, 1.0],
[0.0, 0.0, 0.3, 0.7, 0.0], [0.0, 0.0, 0.0, 0.0, 1.0],
[0.5, 0.5, 0.0, 0.0, 0.0], [0.5, 0.5, 0.0, 0.0, 0.0],
[0.0, 0.0, 0.8, 0.2, 0.0], [0.0, 1.0, 0.0, 0.0, 0.0]])
hmmPos.n_features = 5
hmmPos.startprob_ = startprob
hmmPos.transmat_ = transmat
hmmPos.emissionprob_ = emmPos
# Object HMM
def computeHMM(dataset, alphabet, num_matchstates=9):
num_sequences = len(dataset)
best_score = None
best_model = None
alphabet = list(alphabet)
residue_mapper = {alphabet[j]: j for j in range(0, len(alphabet))}
#one begin, one end, num_matchstates + 1 insert states, num_matchstates match states, num_matchstates deletion states.
num_states = 3 + 3 * num_matchstates
concat_dataset = np.concatenate([[[residue_mapper[x]] for x in y]
for y in dataset])
dataset_lengths = [len(x) for x in dataset]
for x in range(0, 10):
transition_matrix = np.zeros((num_states, num_states))
emission_matrix = np.zeros((num_states, len(alphabet)))
#first num_matchstates + 2 are the matchstates (including beginning and end, though those two are mute
#first do B, then M_1,...,M_m
#B goes to either I_0 or M_1.
b_row = ProfileHMM.compute_random_row(2)
transition_matrix[0][1] = b_row[0]
transition_matrix[0][2] = b_row[1]
for i in range(1, num_matchstates + 1):
#go to either match state, insertion state, or delete state.
m_row = ProfileHMM.compute_random_row(3)
#next match state
transition_matrix[i][i + 1] = m_row[0]
#insert state
transition_matrix[i][i + num_matchstates + 2] = m_row[1]
#deletion state
print('i: %d' % i)
transition_matrix[i][i + 2 * num_matchstates + 2] = m_row[2]
emission_matrix[i] = ProfileHMM.compute_random_row(
len(alphabet))
#now we do the insertion states.
for i in range(num_matchstates + 2, 2 * num_matchstates + 3):
#either go to self, or next match state.
row = ProfileHMM.compute_random_row(2)
transition_matrix[i][i] = row[0]
transition_matrix[i][i - (num_matchstates + 1)] = row[1]
emission_matrix[i] = ProfileHMM.compute_random_row(
len(alphabet))
#now do deletion states. In the loop, do all but the last one
for i in range(2 * num_matchstates + 3, 3 * num_matchstates + 2):
row = ProfileHMM.compute_random_row(2)
transition_matrix[i][i] = row[0]
transition_matrix[i][i - 2 * num_matchstates - 1] = row[1]
model = MultinomialHMM(num_states, params="ets")
model.n_features = len(alphabet)
start_prob = np.zeros(num_states)
start_prob[0] = 1.0
print('start prob array')
print(start_prob)
model.startprob_ = start_prob
model.transmat_ = transition_matrix
model.emissionprob_ = emission_matrix
try:
model.fit(concat_dataset, dataset_lengths)
except ValueError:
pdb.set_trace()
print('model')
print(model)
"""
for row in range(0, len(model.emissionprob_)):
for col in range(0, len(model.emissionprob_[row])):
count = model.emissionprob_[row][col]*num_sequences
model.emissionprob_[row][col] = (count + 0.01)/(num_sequences + len(alphabet)*0.01)
"""
print('emission probabilities')
print(model.emissionprob_)
score = model.score(concat_dataset, dataset_lengths)
if x == 0:
best_score = score
best_model = model
elif score > best_score:
best_score = score
best_model = model
return best_model
def buildHMM(num_states, n_iter=10, tol=0.01):
model = MultinomialHMM(n_components=num_states, n_iter=n_iter, tol=tol)
model.n_features = 3
return model
