from Header import Header
header = Header()
SUFF = ('eas', 'is', 'ais', 'as', 'eamar', 'amar', 'eabhair', 'abhair',
'ead ar', 'adar')
books = False
sentences = True
print "Loading Corpora..."
if books:
print "\tloading munster"
M = CorpusReader('munster')
print "\tloading connacht"
C = CorpusReader('connacht', M.countBooks())
C.truncateBooks(M.countBooks())
print "\tloading ulster"
U = CorpusReader('ulster', M.countBooks())
U.truncateBooks(M.countBooks())
l = [U, M, C]
#print "Done."
if sentences:
print "Creating Balanced Set of sentences"
M = CorpusReader('munster')
C = CorpusReader('connacht')
U = CorpusReader('ulster')
l = [U, M, C]
MIN_LENG = min([x.countSentences() for x in l])
for x in l:
x.truncateSentences(MIN_LENG)
print "Done!"
from pdb import set_trace
from Header import Header
header = Header()
SUFF = ('eas', 'is', 'ais', 'as', 'eamar', 'amar', 'eabhair', 'abhair', 'ead ar', 'adar')
books = False
sentences = True
print "Loading Corpora..."
if books:
print "\tloading munster"
M = CorpusReader('munster')
print "\tloading connacht"
C = CorpusReader('connacht',M.countBooks())
C.truncateBooks(M.countBooks())
print "\tloading ulster"
U = CorpusReader('ulster', M.countBooks())
U.truncateBooks(M.countBooks())
l = [U,M,C]
#print "Done."
if sentences:
print "Creating Balanced Set of sentences"
M = CorpusReader('munster')
C = CorpusReader('connacht')
U = CorpusReader('ulster')
l = [U,M,C]
MIN_LENG = min([x.countSentences() for x in l])
for x in l:
x.truncateSentences(MIN_LENG)
print "Done!"
