def features_snp_modular (fname): from modshogun import StringByteFeatures, SNPFeatures, SNP sf=StringByteFeatures(SNP) sf.load_ascii_file(fname, False, SNP, SNP) #print(sf.get_features()) snps=SNPFeatures(sf)
def distribution_ppwm_modular(fm_dna=traindna, order=3):
from modshogun import StringByteFeatures, StringCharFeatures, DNA
from modshogun import PositionalPWM
from numpy import array, e, log, exp
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_dna)
feats = StringByteFeatures(charfeat.get_alphabet())
feats.obtain_from_char(charfeat, order - 1, order, 0, False)
L = 20
k = 3
sigma = 1
mu = 4
ppwm = PositionalPWM()
ppwm.set_sigma(sigma)
ppwm.set_mean(mu)
pwm = array([[0.0, 0.5, 0.1, 1.0], [0.0, 0.5, 0.5, 0.0],
[1.0, 0.0, 0.4, 0.0], [0.0, 0.0, 0.0, 0.0]])
pwm = array([[0.01, 0.09, 0.1], [0.09, 0.01, 0.1], [0.85, 0.4, 0.1],
[0.05, 0.5, 0.7]])
ppwm.set_pwm(log(pwm))
#print(ppwm.get_pwm())
ppwm.compute_w(L)
w = ppwm.get_w()
#print(w)
#from pylab import *
#figure(1)
#pcolor(exp(w))
#pcolor(w)
#colorbar()
#figure(2)
ppwm.compute_scoring(1)
u = ppwm.get_scoring(0)
#pcolor(exp(u))
#show()
#ppwm=PositionalPWM(feats)
#ppwm.train()
#out_likelihood = histo.get_log_likelihood()
#out_sample = histo.get_log_likelihood_sample()
return w, u
def features_string_hashed_wd_modular (A=matrix,order=3,start_order=1,hash_bits=2):
a=LongIntFeatures(A)
from numpy import array, uint8
from modshogun import HashedWDFeatures, StringByteFeatures, RAWDNA
from modshogun import MSG_DEBUG
x=[array([0,1,2,3,0,1,2,3,3,2,2,1,1],dtype=uint8)]
from_order=order
f=StringByteFeatures(RAWDNA)
#f.io.set_loglevel(MSG_DEBUG)
f.set_features(x)
y=HashedWDFeatures(f,start_order,order,from_order,hash_bits)
fm=y.get_computed_dot_feature_matrix()
return fm
def distribution_ppwm_modular(fm_dna=traindna, order=3):
from modshogun import StringByteFeatures, StringCharFeatures, DNA
from modshogun import PositionalPWM
from numpy import array, e, log, exp
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_dna)
feats = StringByteFeatures(charfeat.get_alphabet())
feats.obtain_from_char(charfeat, order - 1, order, 0, False)
L = 20
k = 3
sigma = 1
mu = 4
ppwm = PositionalPWM()
ppwm.set_sigma(sigma)
ppwm.set_mean(mu)
pwm = array([[0.0, 0.5, 0.1, 1.0], [0.0, 0.5, 0.5, 0.0], [1.0, 0.0, 0.4, 0.0], [0.0, 0.0, 0.0, 0.0]])
pwm = array([[0.01, 0.09, 0.1], [0.09, 0.01, 0.1], [0.85, 0.4, 0.1], [0.05, 0.5, 0.7]])
ppwm.set_pwm(log(pwm))
# print(ppwm.get_pwm())
ppwm.compute_w(L)
w = ppwm.get_w()
# print(w)
# from pylab import *
# figure(1)
# pcolor(exp(w))
# pcolor(w)
# colorbar()
# figure(2)
ppwm.compute_scoring(1)
u = ppwm.get_scoring(0)
# pcolor(exp(u))
# show()
# ppwm=PositionalPWM(feats)
# ppwm.train()
# out_likelihood = histo.get_log_likelihood()
# out_sample = histo.get_log_likelihood_sample()
return w, u
def features_string_hashed_wd_modular(A=matrix,
order=3,
start_order=1,
hash_bits=2):
a = LongIntFeatures(A)
from numpy import array, uint8
from modshogun import HashedWDFeatures, StringByteFeatures, RAWDNA
from modshogun import MSG_DEBUG
x = [array([0, 1, 2, 3, 0, 1, 2, 3, 3, 2, 2, 1, 1], dtype=uint8)]
from_order = order
f = StringByteFeatures(RAWDNA)
#f.io.set_loglevel(MSG_DEBUG)
f.set_features(x)
y = HashedWDFeatures(f, start_order, order, from_order, hash_bits)
fm = y.get_computed_dot_feature_matrix()
return fm
