def clustering_hierarchical_modular(fm_train=traindat, merges=3):
from shogun.Distance import EuclidianDistance
from shogun.Features import RealFeatures
from shogun.Clustering import Hierarchical
feats_train = RealFeatures(fm_train)
distance = EuclidianDistance(feats_train, feats_train)
hierarchical = Hierarchical(merges, distance)
hierarchical.train()
out_distance = hierarchical.get_merge_distances()
out_cluster = hierarchical.get_cluster_pairs()
return hierarchical, out_distance, out_cluster
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
