def extractFullMIToThesaurus():
accents = Accents()
parameters = Parameters()
max_qty_terms = parameters.getMaxQtyTerms()
seeds = Seeds()
dic_seeds = seeds.getSeeds()
mi_file = Statistic(stat_temp+'IMT_FullStatisticalCorpus.txt')
try:
thesaurus_file = codecs.open('../Data/Output/T3/T3_Jaccard.xml', 'w', 'utf-8')
except IOError:
print 'ERROR: System cannot open the file ../Data/Output/T3/T3_Jaccard.xml'
sys.exit()
thesaurus_file.write('<?xml version="1.0" encoding="ISO-8859-1"?>\n<thesaurus>\n\t<ontology id="privacy">\n')
for seed in dic_seeds:
qty_terms = 0
dic_related = mi_file.getOrderedNounMIForTerm(seed)
if dic_related != False:
thesaurus_file.write('\t\t<seed term_id="" term_name="'+accents.buildAccents(seed)+'" type="">\n')
for mi_related in dic_related:
if qty_terms < max_qty_terms:
thesaurus_file.write('\t\t\t<term id="" display="ON" similarity="'+mi_related[0]+'">'+accents.buildAccents(mi_related[1])+'</term>\n')
qty_terms += 1
thesaurus_file.write('\t\t</seed>\n')
thesaurus_file.write('\t</ontology>\n</thesaurus>')
thesaurus_file.close()
