def get_modparse(sentence):
"""returns the modified parse tree for a sentence"""
sp_db = SentenceParse.get_sentence_parse(sentence)
try:
res = sp_db.all()[0]
parsetree = res.original_parse
modparsetree = res.modified_parse
except:
print "parse.py: 103: " + sentence
parses = parse_sentences([sentence])
if len(parses) == 0:
raise ParseError(printcolors.WARNING + ('ParseError: a sentence was empty'))
modparses = modify_parses(parses)
for i,chunk in enumerate(modparses[:]):
for j,modparse in enumerate(chunk):
if 'LANDMARK-PHRASE' in modparse:
modparses[i] = modparse
parses[i] = parses[i][j]
break
if isinstance(modparses[i],list):
modparses[i] = modparses[i][0]
parses[i] = parses[i][0]
parsetree = parses[0]
modparsetree = modparses[0]
try:
SentenceParse.add_sentence_parse(sentence, parsetree, modparsetree)
except Exception as e:
print e
if count_lmk_phrases(ParentedTree.parse(modparsetree)) < 1:
raise ParseError(printcolors.WARNING + ('ParseError: Parse contained no Landmark phrase.\nSentence: %s\nParse: %s\nModparse: %s' % (sentence,parsetree,modparsetree)))
return parsetree, modparsetree
def get_modparse(sentence):
"""returns the modified parse tree for a sentence"""
sp_db = SentenceParse.get_sentence_parse(sentence)
try:
res = sp_db.one()
modparsetree = res.modified_parse
except NoResultFound:
parsetree = parse_sentences([sentence])[0]
modparsetree = modify_parses([parsetree])[0]
SentenceParse.add_sentence_parse(sentence, parsetree, modparsetree)
return modparsetree
def get_modparse(sentence):
"""returns the modified parse tree for a sentence"""
sp_db = SentenceParse.get_sentence_parse(sentence)
try:
res = sp_db.one()
modparsetree = res.modified_parse
except NoResultFound:
parsetree = parse_sentences([sentence])[0]
modparsetree = modify_parses([parsetree])[0]
SentenceParse.add_sentence_parse(sentence, parsetree, modparsetree)
return modparsetree
print 'landmark: %s (%s)' % (lmk, lmk_id(lmk))
print 'relation: %s' % rel_type(rel)
print 'parse:'
print parse.pprint()
print 'modparse:'
print modparse.pprint()
print '-' * 70
location = Location(x=xloc, y=yloc)
save_tree(modparse, location, rel, lmk)
Bigram.make_bigrams(location.words)
Trigram.make_trigrams(location.words)
if i % 200 == 0: session.commit()
if SentenceParse.query().count() == 0:
print 'BLIND ADDING!!!!!!!!!!!'
for sentence,(parse,modparse) in unique_sentences.items():
SentenceParse.add_sentence_parse_blind(sentence, parse, modparse)
else:
print 'NOT BLIND ADDING!!!!!!!!!!!!'
for sentence,(parse,modparse) in unique_sentences.items():
SentenceParse.add_sentence_parse(sentence, parse, modparse)
session.commit()
print 'counting ...'
# count words
w1 = aliased(Word)
w2 = aliased(Word)
# print value
# exit()
# print words
# print 'Sum:',sum(words.values())
# # print typos
# print 'Typos:',len(typos)
# print 'Total:',total
# print 'Good:',len(no_bad_words)
# import IPython
# IPython.embed()
# exit()
sp_db = SentenceParse.get_sentence_parse(all_descs[0])
try:
res = sp_db.all()[0]
except IndexError:
parses = parse_sentences(all_descs,n=5,threads=8)
# temp = tempfile.NamedTemporaryFile()
# for p in parses:
# temp.write(p)
# temp.flush()
# proc = subprocess.Popen(['java -mx100m -cp stanford-tregex/stanford-tregex.jar \
# edu.stanford.nlp.trees.tregex.tsurgeon.Tsurgeon \
# -s -treeFile %s surgery/*' % temp.name],
# shell=True,
# stdout=subprocess.PIPE,
print 'relation: %s' % rel_type(rel)
print 'parse:'
print parse.pprint()
print 'modparse:'
print modparse.pprint()
print '-' * 70
location = Location(x=xloc, y=yloc)
save_tree(modparse, location, rel, lmk)
Bigram.make_bigrams(location.words)
Trigram.make_trigrams(location.words)
if i % 200 == 0: session.commit()
for sentence,(parse,modparse) in unique_sentences.items():
SentenceParse.add_sentence_parse_blind(sentence, parse, modparse)
session.commit()
# count words
parent = aliased(Production)
qry = session.query(Word.word, Word.pos,
parent.landmark, parent.landmark_class, parent.landmark_orientation_relations, parent.landmark_color,
parent.relation, parent.relation_distance_class,
parent.relation_degree_class, func.count(Word.id)).\
join(parent, Word.parent).\
group_by(Word.word, Word.pos,
parent.landmark, parent.landmark_class, parent.landmark_orientation_relations, parent.landmark_color,
parent.relation, parent.relation_distance_class,
parent.relation_degree_class)
for row in qry:
print 'relation: %s' % rel_type(rel)
print 'parse:'
print parse.pprint()
print 'modparse:'
print modparse.pprint()
print '-' * 70
location = Location(x=xloc, y=yloc)
save_tree(modparse, location, rel, lmk)
Bigram.make_bigrams(location.words)
Trigram.make_trigrams(location.words)
if i % 200 == 0: session.commit()
for sentence,(parse,modparse) in unique_sentences.items():
SentenceParse.add_sentence_parse_blind(sentence, parse, modparse)
session.commit()
print 'counting ...'
# count words
w1 = aliased(Word)
w2 = aliased(Word)
parent = aliased(Production)
qry = session.query(w1.word, w2.word, w2.pos,
parent.lhs, parent.landmark, parent.landmark_class,
parent.landmark_orientation_relations, parent.landmark_color,
parent.relation, parent.relation_distance_class,
parent.relation_degree_class, func.count(w2.id)) \
.outerjoin(w1,Bigram.w1) \
