# In this example the Histogram algorithm object computes a histogram over all
# 16bit unsigned integers in the features.
from tools.load import LoadMatrix
from sg import sg
lm=LoadMatrix()
traindna=lm.load_dna('../data/fm_train_dna.dat')
cubedna=lm.load_cubes('../data/fm_train_cube.dat')
parameter_list=[[traindna,cubedna,3,0,'n'],[traindna,cubedna,4,0,'n']]
def distribution_histogram(fm_train=traindna,fm_cube=cubedna,order=3,
gap=0,reverse='n'):
# sg('new_distribution', 'HISTOGRAM')
sg('add_preproc', 'SORTWORDSTRING')
sg('set_features', 'TRAIN', fm_train, 'DNA')
sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse)
sg('attach_preproc', 'TRAIN')
# sg('train_distribution')
# histo=sg('get_histogram')
# num_examples=11
# num_param=sg('get_histogram_num_model_parameters')
# for i in xrange(num_examples):
# for j in xrange(num_param):
# sg('get_log_derivative %d %d' % (j, i))
# sg('get_log_likelihood')
# return sg('get_log_likelihood_sample')
#!/usr/bin/env python
from tools.load import LoadMatrix
lm = LoadMatrix()
data = lm.load_cubes('../data/fm_train_cube.dat')
parameter_list = [[data, 1, 64, 1e-5, 2, 0, False, 5],
[data, 3, 6, 1e-1, 1, 0, False, 2]]
def distribution_hmm(fm_cube, N, M, pseudo, order, gap, reverse, num_examples):
from shogun import StringWordFeatures, StringCharFeatures, CUBE
from shogun import HMM, BW_NORMAL
charfeat = StringCharFeatures(CUBE)
charfeat.set_features(fm_cube)
feats = StringWordFeatures(charfeat.get_alphabet())
feats.obtain_from_char(charfeat, order - 1, order, gap, reverse)
hmm = HMM(feats, N, M, pseudo)
hmm.train()
hmm.baum_welch_viterbi_train(BW_NORMAL)
num_examples = feats.get_num_vectors()
num_param = hmm.get_num_model_parameters()
for i in range(num_examples):
for j in range(num_param):
hmm.get_log_derivative(j, i)
best_path = 0
best_path_state = 0
for i in range(num_examples):
# In this example the Histogram algorithm object computes a histogram over all
# 16bit unsigned integers in the features.
from tools.load import LoadMatrix
from sg import sg
lm = LoadMatrix()
traindna = lm.load_dna("../data/fm_train_dna.dat")
cubedna = lm.load_cubes("../data/fm_train_cube.dat")
parameter_list = [[traindna, cubedna, 3, 0, "n"], [traindna, cubedna, 4, 0, "n"]]
def distribution_histogram(fm_train=traindna, fm_cube=cubedna, order=3, gap=0, reverse="n"):
# sg('new_distribution', 'HISTOGRAM')
sg("add_preproc", "SORTWORDSTRING")
sg("set_features", "TRAIN", fm_train, "DNA")
sg("convert", "TRAIN", "STRING", "CHAR", "STRING", "WORD", order, order - 1, gap, reverse)
sg("attach_preproc", "TRAIN")
# sg('train_distribution')
# histo=sg('get_histogram')
# num_examples=11
# num_param=sg('get_histogram_num_model_parameters')
# for i in xrange(num_examples):
# for j in xrange(num_param):
# sg('get_log_derivative %d %d' % (j, i))
