Understanding the kmersvm

kmersvm.py

from modshogun import StringCharFeatures,DNA
from modshogun import StringWordFeatures

#training set
train_dna=['ACGTGT',
            'ACGGTT',
            'AGTGTT',
        'ACCGGT',
        'TGTGTA',
        'TTGGGT']


train_features=StringCharFeatures(train_dna, DNA)
#desired kmerlength
kmerlen=6
word_features=StringWordFeatures(DNA) 
word_features.obtain_from_char(train_features,kmerlen-1,kmerlen,0,False)

From the shogun toolbox documentation:

void obtain_from_char ( char * str, uint64_t len)

convert string of length len into bit sequence
Parameters:
str string
len length of string in bits