def get_predictions_from_seqdict(self, seqdic, site):
""" we need to generate a huge test features object
containing all locations found in each seqdict-sequence
and each location (this is necessary to efficiently
(==fast,low memory) compute the splice outputs
"""
seqlen = self.window_right + self.window_left + 2
for s in seqdic:
position_list = DynamicIntArray()
sequence = s.seq
positions = s.preds[site].positions
for j in xrange(len(positions)):
i = positions[j] - self.offset - self.window_left
position_list.append_element(i)
t = StringCharFeatures([sequence], DNA)
t.obtain_by_position_list(seqlen, position_list)
self.wd_kernel.init(self.traindat, t)
self.wd_kernel.io.enable_progress()
l = self.svm.apply().get_labels()
self.wd_kernel.cleanup()
sys.stdout.write("\n...done...\n")
num = len(s.preds[site].positions)
scores = num * [0]
for j in xrange(num):
scores[j] = l[j]
s.preds[site].set_scores(scores)
def get_predictions_from_seqdict(self, seqdic, site):
""" we need to generate a huge test features object
containing all locations found in each seqdict-sequence
and each location (this is necessary to efficiently
(==fast,low memory) compute the splice outputs
"""
seqlen=self.window_right+self.window_left+2
for s in seqdic:
position_list=DynamicIntArray()
sequence=s.seq
positions=s.preds[site].positions
for j in xrange(len(positions)):
i=positions[j] - self.offset -self.window_left
position_list.append_element(i)
t=StringCharFeatures([sequence], DNA)
t.obtain_by_position_list(seqlen, position_list)
self.wd_kernel.init(self.traindat, t)
self.wd_kernel.io.enable_progress()
l=self.svm.apply().get_values()
self.wd_kernel.cleanup()
sys.stdout.write("\n...done...\n")
num=len(s.preds[site].positions)
scores= num * [0]
for j in xrange(num):
scores[j]=l[j]
s.preds[site].set_scores(scores)
def get_predictions(self, sequence, positions):
seqlen = self.window_right + self.window_left + 2
num = len(positions)
position_list = DynamicIntArray()
for j in xrange(num):
i = positions[j] - self.offset - self.window_left
position_list.append_element(i)
t = StringCharFeatures([sequence], DNA)
t.obtain_by_position_list(seqlen, position_list)
self.wd_kernel.init(self.traindat, t)
del t
self.wd_kernel.io.enable_progress()
l = self.svm.classify().get_labels()
self.wd_kernel.cleanup()
sys.stdout.write("\n...done...\n")
return l
def get_predictions(self, sequence, positions):
seqlen=self.window_right+self.window_left+2
num=len(positions)
position_list=DynamicIntArray()
for j in xrange(num):
i=positions[j] - self.offset - self.window_left
position_list.append_element(i)
t=StringCharFeatures([sequence], DNA)
t.obtain_by_position_list(seqlen, position_list)
self.wd_kernel.init(self.traindat, t)
del t
self.wd_kernel.io.enable_progress()
l=self.svm.apply().get_values()
self.wd_kernel.cleanup()
sys.stdout.write("\n...done...\n")
return l
def features_string_sliding_window_modular(strings):
from shogun.Features import StringCharFeatures, DNA
from shogun.Library import DynamicIntArray
f = StringCharFeatures([strings], DNA)
# slide a window of length 5 over features
# (memory efficient, does not copy strings)
f.obtain_by_sliding_window(5, 1)
#print(f.get_num_vectors())
#print(f.get_vector_length(0))
#print(f.get_vector_length(1))
#print(f.get_features())
# slide a window of length 4 over features
# (memory efficient, does not copy strings)
f.obtain_by_sliding_window(4, 1)
#print(f.get_num_vectors())
#print(f.get_vector_length(0))
#print(f.get_vector_length(1))
#print(f.get_features())
# extract string-windows at position 0,6,16,25 of window size 4
# (memory efficient, does not copy strings)
f.set_features([s])
positions = DynamicIntArray()
positions.append_element(0)
positions.append_element(6)
positions.append_element(16)
positions.append_element(25)
f.obtain_by_position_list(4, positions)
#print(f.get_features())
# now extract windows of size 8 from same positon list
f.obtain_by_position_list(8, positions)
#print(f.get_features())
return f
def features_string_sliding_window_modular(strings):
from shogun.Features import StringCharFeatures, DNA
from shogun.Library import DynamicIntArray
f = StringCharFeatures([strings], DNA)
# slide a window of length 5 over features
# (memory efficient, does not copy strings)
f.obtain_by_sliding_window(5, 1)
# print(f.get_num_vectors())
# print(f.get_vector_length(0))
# print(f.get_vector_length(1))
# print(f.get_features())
# slide a window of length 4 over features
# (memory efficient, does not copy strings)
f.obtain_by_sliding_window(4, 1)
# print(f.get_num_vectors())
# print(f.get_vector_length(0))
# print(f.get_vector_length(1))
# print(f.get_features())
# extract string-windows at position 0,6,16,25 of window size 4
# (memory efficient, does not copy strings)
f.set_features([s])
positions = DynamicIntArray()
positions.append_element(0)
positions.append_element(6)
positions.append_element(16)
positions.append_element(25)
f.obtain_by_position_list(4, positions)
# print(f.get_features())
# now extract windows of size 8 from same positon list
f.obtain_by_position_list(8, positions)
# print(f.get_features())
return f