def sdfprocess(rvdata, partidx):
os.environ["MALT_PARSER"] = "/home/cosmo/Dropbox/Purdue/nlp/maltparser-1.8"
parser = MaltParser(
mco='engmalt.poly-1.7',
working_dir='/home/cosmo/Dropbox/Purdue/nlp/maltparser-1.8',
additional_java_args=['-Xmx5000m'])
sdfdata = []
cnn = 1
# demo()
print parser.raw_parse("I am a student.")
for eg in rvdata:
if cnn % 100 == 0:
print "%f%% of document %d finished" % (cnn * 100 * 1.0 /
len(rvdata), partidx + 1)
cmt = eg[3].decode('utf-8') #3 is the idx of comment
sentences = nltk.sent_tokenize(cmt)
sdfparsed = [parser.raw_parse(sentence) for sentence in sentences]
sdfdata.append(eg[:3] + [sdfparsed])
# print cnn
print sdfparsed
# print sdfdata
cnn += 1
if cnn > 5: break
return sdfdata
def mltprocess(tp, path, filenamels, docid):
parser=MaltParser(working_dir='/home/cosmo/Dropbox/Purdue/nlp/maltparser-1.8/maltparser-1.8.jar', mco='engmalt.poly-1.7.mco', additional_java_args='-mx5000m')
sdfdata = []
for i in range(len(filenamels)):
if (i+1)%100 == 0: print "%f%% of document %d of %s finished" % ((i+1)*100*1.0/len(filenamels), docid, tp)
filename = filenamels[i]
h = open(path + filename, 'r')
lines = h.readlines()
h.close()
headraw, bodyraw = preprocess(lines[0]), preprocess(lines[1])
sentences = [headraw] + nltk.sent_tokenize(bodyraw)
sdfparsed = [parser.raw_parse(sentence) for sentence in sentences]
sdfdata.append(sdfparsed)
# print sdfparsed
# print sdfdata
# if i > 5: break
return sdfdata
#!/usr/bin/env python
from nltk.parse.malt import MaltParser
parser = MaltParser('maltparser-1.8.1','espmalt-1.0.mco')
txt="This is a test sentence"
parser.train_from_file('Tibidabo_Treebank.txt')
parser.raw_parse(txt)
