def splitTrainSet():
path = './resource/tagged_headers_everyline.txt'
lines = open(path).readlines()
nl = []
tmp = []
for line in lines:
if line.strip().endswith('::line_number::0'):
tmp.append('\n')
nl.append(tmp)
tmp = [line]
else:
tmp.append(line)
if len(tmp)>0:
tmp.append('\n')
nl.append(tmp)
print 'len(nl) = ',len(nl)
open('./py_scikit/tmp/train.in','w').writelines(Tools.flatList(nl[:600]))
open('./py_scikit/tmp/testa.in','w').writelines(Tools.flatList(nl[600:750]))
open('./py_scikit/tmp/testb.in','w').writelines(Tools.flatList(nl[750:]))
