def correspondence(self, templates, template_name, q1=None, artifact=None, var=None):
''' Fulchignoni et al. (2000) extension used to give a correspondence to clusters'''
from itertools import imap
from gmode_module import Invert, free, hyp_test
from file_module import pickle, writedict
import cPickle as pkl
if q1 == None: q1 = self.q1
cluster_members = self.cluster_members
cluster_stats = self.cluster_stats
templ = pkl.load(open(templates,'rb'))
interpretation = dict()
for n, stat in enumerate(cluster_stats):
iS = Invert(stat[2][var, :][:, var])
f = free(stat[3][var, :][:, var])
size = len(cluster_members[n])
selected = filter(lambda x: x != None, \
imap(lambda key, y: hyp_test(size, q1, f, key, y[var], stat[0][var], iS), templ.keys(), templ.values()))
interpretation[n+1] = selected
writedict(interpretation,open(pathjoin("TESTS",self.label,'correspondence_q'+str(q1)+'_'+template_name+'.dat'), 'w'))
pickle(interpretation, self.label, "correspondence_q"+str(q1)+'_'+template_name)
def evaluate(self, q2=None):
if q2 == None: q2 = self.q1
if len(self.cluster_members) > 1:
from eval_variables import distance
from gmode_module import mad
from file_module import pickle
elems = copy(self.elems)
dev = mad(elems, median(elems, axis=0))
#errs = self.errs
self.report.append('\n############################## Part II : Verifying the variable significance ###############################\n')
self.report.append("Confidence level q2: "+str(normal.cdf(q2) - normal.cdf(-q2)))
d2, Gc, D2 = distance(self.cluster_members, self.cluster_stats, elems/dev)
j = 0
for i in range(len(elems[0])):
self.report.append('\nMatrix Gc for variable '+str(i+1)+10*" "+' Weight: '+str(d2[i].sum()/d2.sum())) #+pretty_print(Gc[i]))
if all(Gc[i] < q2):
self.report.append('\n Variable '+str(i+1)+' is statistically redundant.')
print('Variable '+str(i+1)+' is statistically redundant.')
j += 1
pickle(D2, self.label, "D2")
pickle(Gc, self.label, "Gc")
def writelog(self):
from file_module import writeit, writedict
from file_module import pickle
mypath = pathjoin("TESTS",self.label)
writeit(self.report, open(pathjoin(mypath, 'log_'+self.label+'.dat'), 'w'))
writeit(self.clusters_report, open(pathjoin(mypath, 'cluster_'+self.label+'.dat'), 'w'))
pickle(self.cluster_stats, self.label, "cluster_stats")
pickle(self.cluster_members, self.label, "cluster_members")
pickle(self.excluded, self.label, "excluded")
