def test_accumulative(self):
hmm = HMM.from_file(self._model_filename)
for i in xrange(self._num_hidden):
self.assertAlmostEqual(1.0, hmm._accumulative_transition_matrix[-1, i],
delta=1e-6)
self.assertAlmostEqual(1.0, hmm._accumulative_observation_matrix[-1, i],
delta=1e-6)
def test_slfit(self):
sequences = io.load_sequences(self._train_filename)
hmm = HMM.from_file(self._model_filename)
learner = SLHMM(self._num_hidden, self._num_observ)
learner.fit(sequences, verbose=True)
for sequence in sequences:
pprint("True probability: %f" % hmm.predict(sequence))
pprint("Infered probability: %f" % learner.predict(sequence))
def test_slfit(self):
sequences = io.load_sequences(self._train_filename)
hmm = HMM.from_file(self._model_filename)
learner = SLHMM(self._num_hidden, self._num_observ)
learner.fit(sequences, verbose=True)
for sequence in sequences:
pprint("True probability: %f" % hmm.predict(sequence))
pprint("Infered probability: %f" % learner.predict(sequence))
def test_accumulative(self):
hmm = HMM.from_file(self._model_filename)
for i in xrange(self._num_hidden):
self.assertAlmostEqual(1.0,
hmm._accumulative_transition_matrix[-1, i],
delta=1e-6)
self.assertAlmostEqual(1.0,
hmm._accumulative_observation_matrix[-1, i],
delta=1e-6)
def test_predict(self):
sequences = io.load_sequences(self._train_filename)
hmm = HMM.from_file(self._model_filename)
for sequence in sequences:
self.assertEqual(hmm.predict(sequence), hmm.predict(sequence),
"HMM.prediction Error")
sequences = [[0, 1], [1, 2, 3, 0], [0, 0, 0, 1]]
for sequence in sequences:
self.assertEqual(hmm.predict(sequence), hmm.predict(sequence),
"HMM.prediction Error")
def test_predict(self):
sequences = io.load_sequences(self._train_filename)
hmm = HMM.from_file(self._model_filename)
for sequence in sequences:
self.assertEqual(hmm.predict(sequence), hmm.predict(sequence),
"HMM.prediction Error")
sequences = [[0,1], [1,2,3,0], [0,0,0,1]]
for sequence in sequences:
self.assertEqual(hmm.predict(sequence), hmm.predict(sequence),
"HMM.prediction Error")
def __init__(self, training_filename, test_filename, model_filename, num_hidden,
num_observ, num_em_restarts=20):
self._training_data = [np.loadtxt(training_filename, dtype=np.int, delimiter=",")]
# self._test_data = np.loadtxt(test_filename, dtype=np.int, delimiter=",")
self._test_data = []
with file(test_filename, "rb") as fin:
reader = csv.reader(fin)
for line in reader:
self._test_data.append(np.asarray(map(int, line)))
self._model = HMM.from_file(model_filename)
self._num_hidden = num_hidden
self._num_observ = num_observ
self._num_em_restarts = num_em_restarts
def test_decode(self):
sequences = io.load_sequences(self._train_filename)
hmm = HMM.from_file(self._model_filename)
for sequence in sequences:
decoded_sequence = hmm.decode(sequence)
self.assertEqual(len(sequence), len(decoded_sequence), "HMM.decode Error")
for i in xrange(len(sequence)):
self.assertEqual(sequence[i], sequence[i], "HMM.decode Error")
sequences = [[0, 1], [1, 2], [0, 1, 2, 0]]
for sequence in sequences:
decoded_sequence = hmm.decode(sequence)
self.assertEqual(len(sequence), len(decoded_sequence), "HMM.decode Error")
for i in xrange(len(sequence)):
self.assertEqual(decoded_sequence[i], decoded_sequence[i],
"HMM.decode Error")
def test_decode(self):
sequences = io.load_sequences(self._train_filename)
hmm = HMM.from_file(self._model_filename)
for sequence in sequences:
decoded_sequence = hmm.decode(sequence)
self.assertEqual(len(sequence), len(decoded_sequence),
"HMM.decode Error")
for i in xrange(len(sequence)):
self.assertEqual(sequence[i], sequence[i], "HMM.decode Error")
sequences = [[0, 1], [1, 2], [0, 1, 2, 0]]
for sequence in sequences:
decoded_sequence = hmm.decode(sequence)
self.assertEqual(len(sequence), len(decoded_sequence),
"HMM.decode Error")
for i in xrange(len(sequence)):
self.assertEqual(decoded_sequence[i], decoded_sequence[i],
"HMM.decode Error")
def __init__(self,
training_filename,
test_filename,
model_filename,
num_hidden,
num_observ,
num_em_restarts=20):
self._training_data = [
np.loadtxt(training_filename, dtype=np.int, delimiter=",")
]
# self._test_data = np.loadtxt(test_filename, dtype=np.int, delimiter=",")
self._test_data = []
with file(test_filename, "rb") as fin:
reader = csv.reader(fin)
for line in reader:
self._test_data.append(np.asarray(map(int, line)))
self._model = HMM.from_file(model_filename)
self._num_hidden = num_hidden
self._num_observ = num_observ
self._num_em_restarts = num_em_restarts
def test_emfit(self):
sequences = io.load_sequences(self._train_filename)
hmm = HMM.from_file(self._model_filename)
learner = EMHMM(self._num_hidden, self._num_observ)
learner.fit(sequences, verbose=True, repeats=1)
for sequence in sequences:
pprint("True probability: %f" % hmm.predict(sequence))
pprint("Infered probability: %f" % learner.predict(sequence))
pprint("Learned parameter using EM algorithm:")
pprint("Transition matrix: ")
pprint(learner.transition_matrix)
pprint("Observation matrix: ")
pprint(learner.observation_matrix)
pprint("Initial distribution: ")
pprint(learner.initial_dist)
pprint("*" * 50)
pprint("True Transition matrix: ")
pprint(hmm.transition_matrix)
pprint("True Observation matrix: ")
pprint(hmm.observation_matrix)
pprint("True initial distribution: ")
pprint(hmm.initial_dist)
def test_emfit(self):
sequences = io.load_sequences(self._train_filename)
hmm = HMM.from_file(self._model_filename)
learner = EMHMM(self._num_hidden, self._num_observ)
learner.fit(sequences, verbose=True, repeats=1)
for sequence in sequences:
pprint("True probability: %f" % hmm.predict(sequence))
pprint("Infered probability: %f" % learner.predict(sequence))
pprint("Learned parameter using EM algorithm:")
pprint("Transition matrix: ")
pprint(learner.transition_matrix)
pprint("Observation matrix: ")
pprint(learner.observation_matrix)
pprint("Initial distribution: ")
pprint(learner.initial_dist)
pprint("*" * 50)
pprint("True Transition matrix: ")
pprint(hmm.transition_matrix)
pprint("True Observation matrix: ")
pprint(hmm.observation_matrix)
pprint("True initial distribution: ")
pprint(hmm.initial_dist)
def model_selection(trainfile, testfile, modelpath, log_filename):
training_data = np.loadtxt(trainfile, dtype=np.int, delimiter=",")
test_data = []
with file(testfile, "rb") as fin:
reader = csv.reader(fin)
for line in reader:
test_data.append(np.asarray(map(int, line)))
model = HMM.from_file(modelpath)
num_hidden = model.m
num_observ = model.n
variation_measure = np.zeros(num_observ, dtype=np.float)
neg_num_measure = np.zeros(num_observ, dtype=np.int)
neg_proportion_measure = np.zeros(num_observ, dtype=np.float)
for m in xrange(1, num_observ + 1):
slearner = SpectralLearner()
slearner.train(training_data, m, num_observ)
true_probs = np.zeros(len(test_data))
sl_probs = np.zeros(len(test_data))
for i, seq in enumerate(test_data):
true_probs[i] = model.probability(seq)
sl_probs[i] = slearner.predict(seq)
# pprint("%e %e" % (true_probs[i], sl_probs[i]))
neg_num_measure[m - 1] = np.sum(sl_probs < 0, dtype=np.float)
neg_proportion_measure[m - 1] = neg_num_measure[m - 1] / float(
len(test_data))
partition_function = np.sum(true_probs)
#Normalizing joint probability distribution to get conditional distribution
true_probs /= partition_function
sl_probs /= partition_function
variation_measure[m - 1] = np.sum(np.abs(sl_probs - true_probs))
pprint("Model Rank Hyperparameter: %d" % m)
pprint("Sum of all true probabilities: %f" % np.sum(true_probs))
pprint("Sum of all estimated probabilities: %f" % np.sum(sl_probs))
pprint("*" * 50)
statistics = np.array(
[variation_measure, neg_num_measure, neg_proportion_measure])
statistics = statistics.T
np.savetxt(log_filename, statistics, delimiter=",", fmt="%e")
def model_selection(trainfile, testfile, modelpath, log_filename):
training_data = np.loadtxt(trainfile, dtype=np.int, delimiter=",")
test_data = []
with file(testfile, "rb") as fin:
reader = csv.reader(fin)
for line in reader:
test_data.append(np.asarray(map(int, line)))
model = HMM.from_file(modelpath)
num_hidden = model.m
num_observ = model.n
variation_measure = np.zeros(num_observ, dtype=np.float)
neg_num_measure = np.zeros(num_observ, dtype=np.int)
neg_proportion_measure = np.zeros(num_observ, dtype=np.float)
for m in xrange(1, num_observ + 1):
slearner = SpectralLearner()
slearner.train(training_data, m, num_observ)
true_probs = np.zeros(len(test_data))
sl_probs = np.zeros(len(test_data))
for i, seq in enumerate(test_data):
true_probs[i] = model.probability(seq)
sl_probs[i] = slearner.predict(seq)
# pprint("%e %e" % (true_probs[i], sl_probs[i]))
neg_num_measure[m - 1] = np.sum(sl_probs < 0, dtype=np.float)
neg_proportion_measure[m - 1] = neg_num_measure[m - 1] / float(len(test_data))
partition_function = np.sum(true_probs)
#Normalizing joint probability distribution to get conditional distribution
true_probs /= partition_function
sl_probs /= partition_function
variation_measure[m - 1] = np.sum(np.abs(sl_probs - true_probs))
pprint("Model Rank Hyperparameter: %d" % m)
pprint("Sum of all true probabilities: %f" % np.sum(true_probs))
pprint("Sum of all estimated probabilities: %f" % np.sum(sl_probs))
pprint("*" * 50)
statistics = np.array([variation_measure, neg_num_measure, neg_proportion_measure])
statistics = statistics.T
np.savetxt(log_filename, statistics, delimiter=",", fmt="%e")
def test_loading(self):
sequences = io.load_sequences(self._train_filename)
hmm = HMM.from_file(self._model_filename)
for sequence in sequences:
self.assertEqual(hmm.predict(sequence), hmm.predict(sequence),
"Inferred probability is wrong")
def regenerate_training(hmm, training_filename, dsize):
training_seq = hmm.generate_train_data(dsize)
np.savetxt(training_filename, [training_seq], delimiter=",", fmt="%d")
def regenerate_test(hmm, test_filename, dsize, max_length=50):
test_seqs = hmm.generate_test_data(tsize, min_seq_len=50, max_seq_len=51)
with file(test_filename, "wb") as fout:
writer = csv.writer(fout)
for seq in test_seqs:
writer.writerow(seq)
if __name__ == '__main__':
usage = '''./generator.py file m n test_set_size
file is the filepath to store the data
m is the size of states in HMM
n is the size of observations in HMM
test_set_size is the size of test_set
'''
if len(sys.argv) < 5:
sys.stderr.write(usage)
exit()
m = int(sys.argv[2])
n = int(sys.argv[3])
dsizes = [10000, 50000, 100000, 500000, 1000000, 5000000]
tsize = int(sys.argv[4])
file_tager = sys.argv[1]
#generate(m, n, dsizes, tsize, file_tager)
hmm = HMM.from_file(sys.argv[1])
#regenerate_training(hmm, sys.argv[2], int(sys.argv[3]))
regenerate_test(hmm, "m4n8_50_len_test.data", tsize)
def test_loading(self):
sequences = io.load_sequences(self._train_filename)
hmm = HMM.from_file(self._model_filename)
for sequence in sequences:
self.assertEqual(hmm.predict(sequence), hmm.predict(sequence),
"Inferred probability is wrong")
np.savetxt(training_filename, [training_seq], delimiter=",", fmt="%d")
def regenerate_test(hmm, test_filename, dsize, max_length=50):
test_seqs = hmm.generate_test_data(tsize, min_seq_len=50, max_seq_len=51)
with file(test_filename, "wb") as fout:
writer = csv.writer(fout)
for seq in test_seqs:
writer.writerow(seq)
if __name__ == '__main__':
usage = '''./generator.py file m n test_set_size
file is the filepath to store the data
m is the size of states in HMM
n is the size of observations in HMM
test_set_size is the size of test_set
'''
if len(sys.argv) < 5:
sys.stderr.write(usage)
exit()
m = int(sys.argv[2])
n = int(sys.argv[3])
dsizes = [10000, 50000, 100000, 500000, 1000000, 5000000]
tsize = int(sys.argv[4])
file_tager = sys.argv[1]
#generate(m, n, dsizes, tsize, file_tager)
hmm = HMM.from_file(sys.argv[1])
#regenerate_training(hmm, sys.argv[2], int(sys.argv[3]))
regenerate_test(hmm, "m4n8_50_len_test.data", tsize)