def __init__(self, preprocess_args, metric, graph_structure_type, A, B, pi,
obs_bins, win_len, thresh, min_peak_dist):
"""
Args:
preprocess_args:
metric:
graph_structure_type: "predefined", "fully", "left_to_right"
A: initial hidden states graph
B: initial hidden states distribution
pi: initial hidden states probabilities
obs_bins: bins used in the hidden states distribution
win_len: windows lengths of the sliding window offline
thresh: in the peak detection, detect peaks that are greater than
thresh
min_peak_dist: in the peak detection, detect peaks that are at
least separated by minimum peak distance
"""
self.preprocess_args = preprocess_args
self.metric = metric
self.graph_structure_type = graph_structure_type
self.A = A
self.B = B
self.pi = pi
self.obs_bins = obs_bins
self.win_len = win_len
self.thresh = thresh
self.min_peak_dist = min_peak_dist
m = len(self.B[0]) # num of symbols
self.emission_domain = ghmm.IntegerRange(0, m)
self.emission_distr = ghmm.DiscreteDistribution(self.emission_domain)
def _generate_alphabet(self, num_symbols):
"""Generate a simple integer alphabet: [0:num_symbols-1]
:param num_symbols: The number of different qsr symbols
:return: The ghmm integer range object to be used as an alphabet
"""
return gh.IntegerRange(0, num_symbols)
def decodeHMM(m, hmmStates):
''' Decode HMM. '''
print >> sys.stderr, printTime(), "Decode HMM for each chromosome."
sigma = ghmm.IntegerRange(0, 2)
for chrom in hmmStates:
print >> sys.stderr, printTime(), chrom
state, score = m.viterbi(
ghmm.EmissionSequence(sigma, hmmStates[chrom]))
hmmStates[chrom] = state
print >> sys.stderr, printTime(), "Decode HMM finished."
print >> sys.stderr
def setUp(self):
'''Create a simple dice rolling HMM'''
self.sigma = g.IntegerRange(1, 7)
self.A = [[0.9, 0.1], [0.3, 0.7]]
efair = [1.0 / 6] * 6
eloaded = [3.0 / 13, 3.0 / 13, 2.0 / 13, 2.0 / 13, 2.0 / 13, 1.0 / 13]
self.B = [efair, eloaded]
self.pi = [0.5] * 2
self.m = g.HMMFromMatrices(self.sigma,
g.DiscreteDistribution(self.sigma), self.A,
self.B, self.pi)
def trainHMM(hmmState):
''' Train HMM with the given chromosome. '''
print >> sys.stderr, printTime(), "Train HMM with one chromosome."
T = [[0.9, 0.1], [0.1, 0.9]]
e1 = [0.1, 0.9]
e0 = [0.9, 0.1]
E = [e0, e1]
pi = [0.9, 0.1] # initial 10% are peak?
sigma = ghmm.IntegerRange(0, 2) # 0, 1
m = ghmm.HMMFromMatrices(sigma, ghmm.DiscreteDistribution(sigma), T, E,
pi)
m.baumWelch(ghmm.EmissionSequence(sigma, hmmState))
print >> sys.stderr, printTime(), "Train HMM finished."
print >> sys.stderr
return m
# %%
import ghmm
# %%
sigma = ghmm.IntegerRange(1, 7)
train_seq = ghmm.SequenceSet(
sigma,
[[1, 1, 1, 1, 3, 3, 1, 1, 1, 1, 3, 3, 3, 3, 3, 3, 3, 1, 1, 1, 1, 1]])
A = [[0.99, 0.01], [0.99, 0.01]]
B = [[1.0 / 6] * 6] * 2
pi = [0.5] * 2
m = ghmm.HMMFromMatrices(sigma, ghmm.DiscreteDistribution(sigma), A, B, pi)
m.baumWelch(train_seq, 100000000, 0.000000000000001)
print(m.asMatrices())
# %%
print(map(sigma.external, m.sampleSingle(20)))
# %%
v = m.viterbi(test_seq)
print v
# %%
my_seq = ghmm.EmissionSequence(sigma, [1] * 20 + [6] * 10 + [1] * 40)
print m.viterbi(my_seq)
def generateAlphabet(self, num_symbols):
return gh.IntegerRange(0, num_symbols)
total_grams = 0
total_above_threshold = 0
total_threshold_correct = 0
for i, split in enumerate(kf.split(event_list)):
event_list = np.array(event_list)
train_data_raw = event_list[split[0]]
test_data_raw = event_list[split[1]]
train_data, train_vocab = prepare_data(train_data_raw)
test_data, test_vocab = prepare_data(test_data_raw)
# Create and train model
vocab_len = max(train_vocab) + 1
sigma = ghmm.IntegerRange(0, vocab_len) # Emission range
# Transition Matrix
A = calculate_transition_probabilities(n_components)
# Emission Probabilities
B = calculate_emission_probabilities(train_data, n_components,
vocab_len)
# Initial State Distribution
pi = [
1.0 / n_components
] * n_components # Equally distribute the starting probabilities
m = ghmm.HMMFromMatrices(sigma,
ghmm.DiscreteDistribution(sigma), A,