def distance_hammingword_modular (fm_train_dna=traindna,fm_test_dna=testdna, fm_test_real=testdat,order=3,gap=0,reverse=False,use_sign=False): from shogun.Features import StringCharFeatures, StringWordFeatures, DNA from shogun.Preprocessor import SortWordString from shogun.Distance import HammingWordDistance charfeat=StringCharFeatures(DNA) charfeat.set_features(fm_train_dna) feats_train=StringWordFeatures(charfeat.get_alphabet()) feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse) preproc=SortWordString() preproc.init(feats_train) feats_train.add_preprocessor(preproc) feats_train.apply_preprocessor() charfeat=StringCharFeatures(DNA) charfeat.set_features(fm_test_dna) feats_test=StringWordFeatures(charfeat.get_alphabet()) feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse) feats_test.add_preprocessor(preproc) feats_test.apply_preprocessor() distance=HammingWordDistance(feats_train, feats_train, use_sign) dm_train=distance.get_distance_matrix() distance.init(feats_train, feats_test) dm_test=distance.get_distance_matrix() return distance,dm_train,dm_test
def distance_hammingword_modular(fm_train_dna=traindna,
fm_test_dna=testdna,
fm_test_real=testdat,
order=3,
gap=0,
reverse=False,
use_sign=False):
from shogun.Features import StringCharFeatures, StringWordFeatures, DNA
from shogun.Preprocessor import SortWordString
from shogun.Distance import HammingWordDistance
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_train_dna)
feats_train = StringWordFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse)
preproc = SortWordString()
preproc.init(feats_train)
feats_train.add_preprocessor(preproc)
feats_train.apply_preprocessor()
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_test_dna)
feats_test = StringWordFeatures(charfeat.get_alphabet())
feats_test.obtain_from_char(charfeat, order - 1, order, gap, reverse)
feats_test.add_preprocessor(preproc)
feats_test.apply_preprocessor()
distance = HammingWordDistance(feats_train, feats_train, use_sign)
dm_train = distance.get_distance_matrix()
distance.init(feats_train, feats_test)
dm_test = distance.get_distance_matrix()
return distance, dm_train, dm_test
def perform_clustering(mss_id):
import numpy
import expenv
mss = expenv.MultiSplitSet.get(mss_id)
from method_mhc_mkl import SequencesHandler
from shogun.Distance import EuclidianDistance, HammingWordDistance
from shogun.Features import StringCharFeatures, StringWordFeatures, PROTEIN
from shogun.Clustering import Hierarchical
from shogun.PreProc import SortWordString
order = 1
gap = 0
reverse = False
seq_handler = SequencesHandler()
data = [seq_handler.get_seq(ss.dataset.organism) for ss in mss.split_sets]
charfeat = StringCharFeatures(PROTEIN)
charfeat.set_features(data)
feats = StringWordFeatures(charfeat.get_alphabet())
feats.obtain_from_char(charfeat, order - 1, order, gap, reverse)
preproc = SortWordString()
preproc.init(feats)
feats.add_preproc(preproc)
feats.apply_preproc()
use_sign = False
distance = HammingWordDistance(feats, feats, use_sign)
#distance = EuclidianDistance()
merges = 4
hierarchical = Hierarchical(merges, distance)
hierarchical.train()
hierarchical.get_merge_distances()
hierarchical.get_cluster_pairs()
return hierarchical