def get_dependency(self, row_file, target):
stanford_parser = parser.Parser()
row_str = ''
f = open(row_file, 'rb')
for row in f:
row_str += row
soup = BeautifulSoup(row_str)
self.soup = soup
sentences = soup.find_all('sentence')
all_sentences = list()
for block in sentences:
text = block.text.strip()
all_sentences.append(text)
#end for
temp_csv = csv.writer(open('dependency_%s' % target, 'wb'))
for sentence in all_sentences:
temp_list = stanford_parser.parseToStanfordDependencies(sentence)
for item in temp_list:
temp_csv.writerow(item)
temp_csv.writerow([])
return
def get_whole(self, sentence):
opinion_dict = dict()
pos_f = open('../opinion-lexicon-English/positive-words.txt', 'rb')
neg_f = open('../opinion-lexicon-English/negative-words.txt', 'rb')
for _ in xrange(35):
pos_f.readline()
neg_f.readline()
for word in pos_f:
opinion_dict[word.strip()] = True
for word in neg_f:
opinion_dict[word.strip()] = False
pos_f.close()
neg_f.close()
stemmer = PorterStemmer()
stanford_parser = parser.Parser()
stanford_tagger = \
POSTagger('../stanford-postagger-full-2015-01-30/models/english-bidirectional-distsim.tagger','../stanford-postagger-full-2015-01-30/stanford-postagger.jar')
w = open('sentence_test', 'wb')
text_token = self.tf.stanford_tokenize(sentence)
text_pos = stanford_tagger.tag(text_token)
print text_pos
text_dependency = stanford_parser.parseToStanfordDependencies(sentence)
temp_list = ['none'] * len(text_token)
for dep in text_dependency:
if dep[0] == 'amod':
temp_list[int(dep[1])] = '%s_1' % dep[0]
temp_list[int(dep[2])] = '%s_2' % dep[0]
#end for
for num, item in enumerate(text_pos[0]):
temp_str = 'order'
if opinion_dict.has_key(item[0]):
temp_str = 'opion'
featrue_list=[item[0],item[1],stemmer.stem(item[0]),item[0].lower(),\
temp_str,temp_list[num],'O']
w.write(' '.join(featrue_list) + '\n')
pass
#-*-coding:utf-8-*-
import pandas as pd
from stanford_parser import parser
from nltk.tree import Tree
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import warnings
warnings.filterwarnings(action='ignore')
path = './data/'
out_path = './train_data/'
standford_parser = parser.Parser()
#get features from the structure of the deptree
def getDepTree(x):
# 构建语法分析工具
tokens, tree = standford_parser.parse(unicode(x))
posTag = standford_parser.getPosTag(tree)
return str(tree), posTag
def getDepTreeHeight(x):
#_, ret = standford_parser.parse(unicode(x))
t = Tree.fromstring(str(x))
return t.height()
(distance, sent_str))
except JavaException:
# print "Failure: sentence is too long (len = %i)" % len(sent)
pass
except AssertionError:
# print "Failure: could not find root"
pass
#best summary sentences is the one with closest feature/opinion
summary_sents_with_feature_opinion_dist.sort()
if len(summary_sents_with_feature_opinion_dist) > 0:
return summary_sents_with_feature_opinion_dist[0][1]
else:
return None
#To summarize movie review(s) not included in the NLTK:
# $ python summarizer.py filename1.txt filename2.txt ... etc.
if __name__ == '__main__':
parser = sp.Parser()
if len(sys.argv) > 1:
for fname in sys.argv[1:]:
print "\nReview: %s" % fname
print "Summary: %s\n" % find_summary_sentence(parser,
localfile=fname)
else:
for fileid in movie_reviews.fileids():
print "\nReview:", fileid
print "Summary:\n", find_summary_sentence(parser, fileid=fileid)
def __init__(self):
self.__parser_ = parser.Parser()
def setUpClass(cls):
jarPathName = normpath(join(parser.MODULE_PATH, "./CoreNLP"))
cls._parser = parser.Parser(jarPathName, 'edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz')
__author__ = 'simon.hughes'
from stanford_parser import parser
txt = "Pick up the tire pallet."
p = parser.Parser()
dependencies = p.parseToStanfordDependencies(txt)
tupleResult = [(rel, (gov.text, gov.start, gov.end), (dep.text, dep.start,
dep.end))
for rel, gov, dep in dependencies.dependencies]
tokens, tree = p.parse(txt)
kids = tree.children
for tuple in tupleResult:
print tuple
print ""
print "\n".join(map(str, dependencies.dependencies[0]))
def extract_dependencies(txt):
dependencies = p.parseToStanfordDependencies(txt)
return [(rel, (gov.text, gov.start, gov.end), (dep.text, dep.start,
dep.end))
for rel, gov, dep in dependencies.dependencies]
deps = extract_dependencies(txt)