def som_cluster_test(data,real_labels, outputfile = None):
if outputfile != None:
f = open(outputfile,'w')
f.write(out_result_header())
start = time.time()
ks = range(6,40)
for k in ks:
print 'som clustering when k=%d' % k
predicted = Pycluster.somcluster(data,nxgrid=k,nygrid=1, niter=5, dist='u')[0]
predicted = [xy[0] for xy in predicted.tolist()]
cata = tuple(set(predicted))
for i in range(0,len(predicted)):
predicted[i]=cata.index(predicted[i])
if outputfile != None:
f.write(out_result(predicted, k, real_labels))
elasped = time.time() - start
print 'som clustering time: %.3f' % (elasped/float(len(ks)))
def self_organizing_map(flat_data, data):
""" """
# Self-organizing maps
clusterid, celldata = pc.somcluster(
data=flat_data.values(),
transpose=0,
nxgrid=5,
nygrid=5,
inittau=0.02,
niter=100,
dist='e')
# load clusters into dictionary
clusters = defaultdict(list)
for i, j in zip(clusterid, data):
clusters[tuple(i)].append(j)
make_plots('SOM (c=%s, m=%s, d=%s)' % (nclusters, method, distance),
clusters, flat_data)
def som_cluster_test(data, real_labels, outputfile=None):
if outputfile != None:
f = open(outputfile, 'w')
f.write(out_result_header())
start = time.time()
ks = range(6, 40)
for k in ks:
print 'som clustering when k=%d' % k
predicted = Pycluster.somcluster(data,
nxgrid=k,
nygrid=1,
niter=5,
dist='u')[0]
predicted = [xy[0] for xy in predicted.tolist()]
cata = tuple(set(predicted))
for i in range(0, len(predicted)):
predicted[i] = cata.index(predicted[i])
if outputfile != None:
f.write(out_result(predicted, k, real_labels))
elasped = time.time() - start
print 'som clustering time: %.3f' % (elasped / float(len(ks)))
input_vecs = utils.make_prices_diffs_vecs(data) else: input_vecs = utils.make_prices_vecs(data) # Run clustering algorithm. if algorithm_type == ClusterAlg.KMEANS: labels, wcss, n = Pycluster.kcluster(input_vecs, number_of_clusters, dist = dist_measure, npass = number_of_iters, method = dist_method) elif algorithm_type == ClusterAlg.HIERARCHICAL: tree = Pycluster.treecluster(input_vecs, method = dist_method, dist = dist_method) labels = tree.cut(number_of_clusters) elif algorithm_type == ClusterAlg.SELFORGMAPS: labels, celldata = Pycluster.somcluster(input_vecs, nxgrid = xgrid, nygrid = ygrid, niter = number_of_iters) # If algorithm is self-organizing maps each item is assigned to # a particular 2D point, so we need to create groups from 2D points. # See implementation of making groups from labels for details. if algorithm_type == ClusterAlg.SELFORGMAPS: clusters = utils.make_groups_from_labels(labels, data, True) else: clusters = utils.make_groups_from_labels(labels, data) # Check with which type of key we have to deal with. # Any better idea how to check if object is a pair? :) keys_are_2D_points = True sample_key = clusters.keys()[0]
