Upload new file

+#!/usr/bin/python
+#SPLIT PARTITION: Recibe un archivo con listas de número de oraciones, indicando a qué cluster pertenecen. Genera un archivo con cada uno de los clusters
+from optparse import OptionParser
+import re
+
+# Recibir input y output
+parser = OptionParser()
+parser.add_option("-i", dest="inF",help="Input text file. Clusters of sentences starting with cluster name indicated by '#'. Each sentence must be followed by _s", metavar="PATH")
+parser.add_option("-o", dest="otF",help="output directory", metavar="PATH")
+
+(options, args) = parser.parse_args()
+if len(args) > 0:
+    parser.error("Please indicate an input file")
+    sys.exit(1)
+
+# Asignar variables
+infile = options.inF
+outdir = options.otF
+
+#Separar oraciones pertenecientes a los clusters e imprimirlas en archivos separados por cluster
+with open (infile, 'r') as clusterfile, open ('/home/mrocha/storage/embeddings/gene-disease-embeddings/corpora/articles-titles.txt', 'r') as sentencefile:
+   sentences = sentencefile.readlines()
+   for line in clusterfile:
+      if (re.search('\#Cluster:\s+\d', line)):
+         cl = re.search('\#Cluster:\s+(\d)', line)
+         num = str(cl.group(1))
+         name=outdir+"/cluster"+num+".txt"
+         out = open(name, 'w')
+      elif (re.search('(\d+)_s', line)):
+         num=re.search('(\d+)_s', line)
+         out.write(sentences[int(num.group(1))-1])
+out.close()
\ No newline at end of file