def test_save_and_load(self):
states = "NR"
alphabet = "AGTC"
p_initial = array([1.0, 0.0])
p_transition = array([[0.75, 0.25], [0.25, 0.75]])
p_emission = array(
[[0.45, 0.36, 0.06, 0.13], [0.24, 0.18, 0.12, 0.46]])
markov_model_save = MarkovModel.MarkovModel(
states,
alphabet,
p_initial,
p_transition,
p_emission)
handle = StringIO()
MarkovModel.save(markov_model_save, handle)
handle.seek(0)
markov_model_load = MarkovModel.load(handle)
self.assertEqual(''.join(markov_model_load.states), states)
self.assertEqual(''.join(markov_model_load.alphabet), alphabet)
self.assertTrue(array_equal(markov_model_load.p_initial, p_initial))
self.assertTrue(array_equal
(markov_model_load.p_transition, p_transition))
self.assertTrue(array_equal(markov_model_load.p_emission, p_emission))
def mostLikely(self, normal, island, dnastrand):
states = "NR"
alphabet = "AGTC"
normal = [float(x)/100 for x in normal]
island = [float(x)/100 for x in island]
p_initial = [1.0, 0.0]
p_initial = asarray(p_initial)
p_transition = []
p_transition.append([1.0-normal[-1], normal[-1]])
p_transition.append([island[-1], 1.0-island[-1]])
p_transition = asarray(p_transition)
p_emission = [] # 2x4 matrix
p_emission.append(normal[:4])
p_emission.append(island[:4])
p_emission = asarray(p_emission)
mm = MarkovModel.MarkovModel(
states, alphabet, p_initial, p_transition, p_emission)
x = MarkovModel.find_states(mm, dnastrand)
states, x = x[0]
return ''.join(states)
def test_readline_and_check_start(self):
states = "NR"
alphabet = "AGTC"
markov_model = MarkovModel.MarkovModel(states, alphabet)
line = "This is a \n string with two lines \n"
handle = StringIO(line)
start = "This is a \n"
self.assertEqual(start, MarkovModel._readline_and_check_start(handle, start))
def test_topcoder5(self):
# N
states = "NR"
alphabet = "AGTC"
p_initial = array([1.0, 0.0])
p_transition = array([[0.84, 0.16], [0.25, 0.75]])
p_emission = array([[0.26, 0.37, 0.08, 0.29], [0.31, 0.13, 0.33,
0.23]])
markov_model = MarkovModel.MarkovModel(states, alphabet, p_initial,
p_transition, p_emission)
states = MarkovModel.find_states(markov_model, "T")
self.assertEqual(len(states), 1)
state_list, state_float = states[0]
self.assertEqual(state_list, ["N"])
def test_topcoder1(self):
# NNNN
states = "NR"
alphabet = "AGTC"
p_initial = array([1.0, 0.0])
p_transition = array([[0.90, 0.10], [0.20, 0.80]])
p_emission = array([[0.30, 0.20, 0.30, 0.20], [0.10, 0.40, 0.10,
0.40]])
markov_model = MarkovModel.MarkovModel(states, alphabet, p_initial,
p_transition, p_emission)
states = MarkovModel.find_states(markov_model, "TGCC")
self.assertEqual(len(states), 1)
state_list, state_float = states[0]
self.assertEqual(state_list, ["N", "N", "N", "N"])
def test_topcoder4(self):
# NRRRRRRRRRR
states = "NR"
alphabet = "AGTC"
p_initial = array([1.0, 0.0])
p_transition = array([[0.55, 0.45],
[0.15, 0.85]])
p_emission = array([[0.75, 0.03, 0.01, 0.21],
[0.34, 0.11, 0.39, 0.16]])
markov_model = MarkovModel.MarkovModel(
states, alphabet, p_initial, p_transition, p_emission)
states = MarkovModel.find_states(markov_model, "TTAGCAGTGCG")
self.assertEqual(len(states), 1)
state_list, state_float = states[0]
self.assertEqual(state_list, ['N', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R'])
def test_topcoder3(self):
# NRRRRRRRRRRRNNNNRRRRRRRRR
states = "NR"
alphabet = "AGTC"
p_initial = array([1.0, 0.0])
p_transition = array([[0.75, 0.25],
[0.25, 0.75]])
p_emission = array([[0.45, 0.36, 0.06, 0.13],
[0.24, 0.18, 0.12, 0.46]])
markov_model = MarkovModel.MarkovModel(
states, alphabet, p_initial, p_transition, p_emission)
states = MarkovModel.find_states(markov_model, "CCGTACTTACCCAGGACCGCAGTCC")
self.assertEqual(len(states), 1)
state_list, state_float = states[0]
self.assertEqual(state_list, ['N', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'N', 'N', 'N', 'N', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R', 'R'])
def test_topcoder2(self):
# NNNRRRNNRRNRRN
states = "NR"
alphabet = "AGTC"
p_initial = array([1.0, 0.0])
p_transition = array([[0.56, 0.44],
[0.25, 0.75]])
p_emission = array([[0.04, 0.14, 0.62, 0.20],
[0.39, 0.15, 0.04, 0.42]])
markov_model = MarkovModel.MarkovModel(
states, alphabet, p_initial, p_transition, p_emission)
states = MarkovModel.find_states(markov_model, "CCTGAGTTAGTCGT")
self.assertEqual(len(states), 1)
state_list, state_float = states[0]
self.assertEqual(state_list, ['N', 'N', 'N', 'R', 'R', 'R', 'N', 'N', 'R', 'R', 'N', 'R', 'R', 'N'])
def test_baum_welch(self):
states = ["CP", "IP"]
alphabet = ["cola", "ice_t", "lem"]
outputs = [
(2, 1, 0)
]
p_initial = [1.0, 0.0000001]
p_transition = [[0.7, 0.3],
[0.5, 0.5]]
p_emission = [[0.6, 0.1, 0.3],
[0.1, 0.7, 0.2]]
N, M = len(states), len(alphabet)
x = MarkovModel._baum_welch(N, M, outputs,
p_initial=p_initial,
p_transition=p_transition,
p_emission=p_emission
)
p_initial, p_transition, p_emission = x
markov_model = MarkovModel.MarkovModel(states, alphabet,
p_initial, p_transition,
p_emission)
self.assertEqual(markov_model.states, ["CP", "IP"])
self.assertEqual(markov_model.alphabet, ["cola", "ice_t", "lem"])
self.assertEqual(len(markov_model.p_initial), 2)
self.assertAlmostEqual(markov_model.p_initial[0], 1.0,
places=4)
self.assertAlmostEqual(markov_model.p_initial[1], 0.0,
places=4)
self.assertEqual(len(markov_model.p_transition), 2)
self.assertEqual(len(markov_model.p_transition[0]), 2)
self.assertEqual(len(markov_model.p_transition[1]), 2)
self.assertAlmostEqual(markov_model.p_transition[0][0], 0.02460365,
places=4)
self.assertAlmostEqual(markov_model.p_transition[0][1], 0.97539634,
places=4)
self.assertAlmostEqual(markov_model.p_transition[1][0], 1.0,
places=4)
self.assertAlmostEqual(markov_model.p_transition[1][1], 0.0,
places=4)
self.assertEqual(len(markov_model.p_emission), 2)
self.assertEqual(len(markov_model.p_emission[0]), 3)
self.assertEqual(len(markov_model.p_emission[1]), 3)
self.assertAlmostEqual(markov_model.p_emission[0][0], 0.5)
self.assertAlmostEqual(markov_model.p_emission[0][1], 0.0)
self.assertAlmostEqual(markov_model.p_emission[0][2], 0.5)
self.assertAlmostEqual(markov_model.p_emission[1][0], 0.0)
self.assertAlmostEqual(markov_model.p_emission[1][1], 1.0)
self.assertAlmostEqual(markov_model.p_emission[1][2], 0.0)
(2, 1, 0)
]
print "Training HMM"
p_initial = [1.0, 0.0000001]
p_transition = [[0.7, 0.3],
[0.5, 0.5]]
p_emission = [[0.6, 0.1, 0.3],
[0.1, 0.7, 0.2]]
N, M = len(states), len(alphabet)
x = MarkovModel._baum_welch(N, M, outputs,
p_initial=p_initial,
p_transition=p_transition,
p_emission=p_emission
)
p_initial, p_transition, p_emission = x
mm = MarkovModel.MarkovModel(states, alphabet,
p_initial, p_transition, p_emission)
print_mm(mm)
# Test Baum-Welch. This is hard because it is a non-deterministic
# algorithm. Each run will result in different states having to
# different emissions. In order to help this, we need to specify some
# initial probabilities to bias the final results. This is not
# implemented yet in the MarkovModel module.
## states = [
## "state0",
## "state1",
## "state2",
## "state3",
## ]
