def generate_answer():
question = request.form['question']
if question == '':
return render_template('form_action.html', content='none')
a = get_answer(question)
print("FOUND: %d (<<%s>> -> %s)" % (len(a.sources), question, a.text))
higlighted_question = a.q.text
for word in a.q.not_in_kw:
higlighted_question = highlight_question_wrong(higlighted_question, word)
sources = create_sources(a)
return render_template('form_action.html', content='block', sources=sources, question=higlighted_question,
answer=a.text, query=a.q.query)
def generate_answer():
question = request.form['question']
if question == '':
return render_template('form_action.html', content='none')
a = get_answer(question)
print("FOUND: %d (<<%s>> -> %s)" % (len(a.sources), question, a.text))
higlighted_question = a.q.text
for word in a.q.not_in_kw:
higlighted_question = highlight_question_wrong(higlighted_question,
word)
sources = create_sources(a)
return render_template('form_action.html',
content='block',
sources=sources,
question=higlighted_question,
answer=a.text,
query=a.q.query)
def regenerate(splitname):
# TODO: remove irrelevant printouts, remove sentence, url, headline,.. from outfile
from argus.main_frame import get_answer
from separate_relevance import relevance_load
from argus.features import feature_list_official as flo
q_num = 0
info_files = [
open('tests/feature_prints/%s/%s.tsv' % (splitname, i_f), 'wb')
for i_f in flo
]
writers = [
csv.writer(info_file, delimiter='\t') for info_file in info_files
]
info_all = open('tests/feature_prints/%s/all_features.tsv' % (splitname, ),
'wb')
writer_all = csv.writer(info_all, delimiter='\t')
info_rel = open(
'tests/feature_prints/%s/all_features_rel.tsv' % (splitname, ), 'wb')
writer_rel = csv.writer(info_rel, delimiter='\t')
info_turk = open(
'tests/feature_prints/%s/turk_sentences.tsv' % (splitname, ), 'wb')
writer_turk = csv.writer(info_turk, delimiter=',')
first = False
r = relevance_load()
with open('tests/f%s.tsv' % (splitname, ), 'wb') as featfile:
writer = csv.writer(featfile, delimiter='\t')
with open('tests/q%s.tsv' % (splitname, )) as qfile:
i = 0
for line in csv.reader(qfile, delimiter='\t'):
qorigin, qrunid, qtopic, qtext, qgsans, qsrc = line
if i == 0:
# CSV header
i += 1
info = [
'HITID', 'Question', 'TurkAnswer', 'OurAnswer',
'OurKeywords', 'FoundSentence', 'OurHeadline',
'TurkTopic', 'TurkURL', 'OurURL', 'Source', 'info'
]
info += flo
if q_num == 0:
writer.writerow(info)
writer_turk.writerow(['question', 'sentence'])
first = True
continue
q_num += 1
# Generate answer from question; this implies generating
# various question features
ouranswer = get_answer(qtext)
# Toggle comment to keep only sources that were manually
# annotated as relevant at mturk
# filter_sources(ouranswer)
# Write details to various auxiliary csv files
url = ''
headline = ''
sentence = ''
source = ''
feat = ''
info = []
if len(ouranswer.sources) != 0:
feature_print_all(writer_all, ouranswer, first, qgsans)
feature_print_rel(writer_rel, ouranswer, r, first)
feature_print(writers, ouranswer)
turk_print(writer_turk, ouranswer)
url = ouranswer.sources[0].url
headline = ouranswer.sources[0].headline
sentence = ouranswer.sources[0].sentence
source = ouranswer.sources[0].source
for j in range(len(flo)):
for s in ouranswer.sources:
feat += str(s.features[j].get_value()) + ":"
feat = feat[:-1]
info.append(feat)
feat = ''
# Write details to the output.tsv
info = [
qrunid, qtext, qgsans, ouranswer.text,
ouranswer.q.summary(), sentence, headline, qtopic, qsrc,
url, source, ouranswer.info
] + info
info = [field.encode('utf-8') for field in info]
writer.writerow(info)
###############
if q_num % 10 == 0:
print 'answering question', splitname, q_num
for i_f in info_files:
i_f.close()
def evaluate():
# TODO: remove irrelevant printouts, remove sentence, url, headline,.. from outfile
from argus.main_frame import get_answer
from separate_relevance import relevance_load
from argus.features import feature_list_official as flo
q_num = 0
info_files = [open('tests/feature_prints/' + i_f + '.tsv', 'wb') for i_f in flo]
writers = [csv.writer(info_file, delimiter='\t') for info_file in info_files]
info_all = open('tests/feature_prints/all_features.tsv', 'wb')
writer_all = csv.writer(info_all, delimiter='\t')
info_rel = open('tests/feature_prints/all_features_rel.tsv', 'wb')
writer_rel = csv.writer(info_rel, delimiter='\t')
info_turk = open('tests/feature_prints/turk_sentences.tsv', 'wb')
writer_turk = csv.writer(info_turk, delimiter=',')
first = False
r = relevance_load()
npy_rel = []
with open(OUTFILE, 'wb') as csv_file:
writer = csv.writer(csv_file, delimiter='\t')
for csvfile in os.listdir(CSV_FOLDER):
if not csvfile.endswith(".csv"):
continue
i = 0
for line in csv.reader(open(CSV_FOLDER + '/' + csvfile), delimiter=',', skipinitialspace=True):
if i == 0:
# CSV header
i += 1
info = ['HITID', 'Question', 'TurkAnswer', 'OurAnswer',
'OurKeywords', 'FoundSentence', 'OurHeadline',
'TurkTopic', 'TurkURL', 'OurURL', 'Source', 'info']
info += flo
if q_num == 0:
writer.writerow(info)
writer_turk.writerow(['question', 'sentence'])
first = True
continue
if line[16] == 'Rejected':
continue
q_num += 1
# Generate answer from question
ouranswer = get_answer(line[30])
# Toggle comment to keep only sources that were manually
# annotated as relevant at mturk
# filter_sources(ouranswer)
# Write details to various auxiliary csv files
url = ''
headline = ''
sentence = ''
source = ''
feat = ''
info = []
turk_answer = line[28]
if len(ouranswer.sources) != 0:
feature_print_all(writer_all, ouranswer, first, turk_answer)
feature_print_rel(writer_rel, ouranswer, r, first)
feature_print(writers, ouranswer)
turk_print(writer_turk, ouranswer)
url = ouranswer.sources[0].url
headline = ouranswer.sources[0].headline
sentence = ouranswer.sources[0].sentence
source = ouranswer.sources[0].source
for j in range(len(flo)):
for s in ouranswer.sources:
feat += str(s.features[j].get_value()) + ":"
feat = feat[:-1]
info.append(feat)
feat = ''
# Write details to the output.tsv
info = [line[0], line[30], turk_answer,
ouranswer.text, ouranswer.q.query, sentence,
headline, line[31], line[29], url, source,
ouranswer.info] + info
info = [field.encode('utf-8') for field in info]
writer.writerow(info)
# Store relevance features + gs for possible separate classifier
# training
for triplet in r:
if ouranswer.q.text == triplet[0]:
for s in ouranswer.sources:
if s.sentence == triplet[1]:
fs = [f.get_value() for f in s.features if '@' in f.get_type()]
if len(npy_rel) == 0:
npy_rel = np.array(fs + [triplet[-1] / 2])
else:
npy_rel = np.vstack((npy_rel, np.array(fs + [triplet[-1] / 2])))
###############
if q_num % 10 == 0:
print 'answering question', q_num
for i_f in info_files:
i_f.close()
np.save('tests/batches/relevance/npy_rel', npy_rel)
def regenerate(splitname):
# TODO: remove irrelevant printouts, remove sentence, url, headline,.. from outfile
from argus.main_frame import get_answer
from separate_relevance import relevance_load
from argus.features import feature_list_official as flo
q_num = 0
info_files = [open('tests/feature_prints/%s/%s.tsv' % (splitname, i_f), 'wb') for i_f in flo]
writers = [csv.writer(info_file, delimiter='\t') for info_file in info_files]
info_all = open('tests/feature_prints/%s/all_features.tsv' % (splitname,), 'wb')
writer_all = csv.writer(info_all, delimiter='\t')
info_rel = open('tests/feature_prints/%s/all_features_rel.tsv' % (splitname,), 'wb')
writer_rel = csv.writer(info_rel, delimiter='\t')
info_turk = open('tests/feature_prints/%s/turk_sentences.tsv' % (splitname,), 'wb')
writer_turk = csv.writer(info_turk, delimiter=',')
first = False
r = relevance_load()
with open('tests/f%s.tsv' % (splitname,), 'wb') as featfile:
writer = csv.writer(featfile, delimiter='\t')
with open('tests/q%s.tsv' % (splitname,)) as qfile:
i = 0
for line in csv.reader(qfile, delimiter='\t'):
qorigin, qrunid, qtopic, qtext, qgsans, qsrc = line
if i == 0:
# CSV header
i += 1
info = ['HITID', 'Question', 'TurkAnswer', 'OurAnswer',
'OurKeywords', 'FoundSentence', 'OurHeadline',
'TurkTopic', 'TurkURL', 'OurURL', 'Source', 'info']
info += flo
if q_num == 0:
writer.writerow(info)
writer_turk.writerow(['question', 'sentence'])
first = True
continue
q_num += 1
# Generate answer from question; this implies generating
# various question features
ouranswer = get_answer(qtext)
# Toggle comment to keep only sources that were manually
# annotated as relevant at mturk
# filter_sources(ouranswer)
# Write details to various auxiliary csv files
url = ''
headline = ''
sentence = ''
source = ''
feat = ''
info = []
if len(ouranswer.sources) != 0:
feature_print_all(writer_all, ouranswer, first, qgsans)
feature_print_rel(writer_rel, ouranswer, r, first)
feature_print(writers, ouranswer)
turk_print(writer_turk, ouranswer)
url = ouranswer.sources[0].url
headline = ouranswer.sources[0].headline
sentence = ouranswer.sources[0].sentence
source = ouranswer.sources[0].source
for j in range(len(flo)):
for s in ouranswer.sources:
feat += str(s.features[j].get_value()) + ":"
feat = feat[:-1]
info.append(feat)
feat = ''
# Write details to the output.tsv
info = [qrunid, qtext, qgsans,
ouranswer.text, ouranswer.q.summary(), sentence,
headline, qtopic, qsrc, url, source,
ouranswer.info] + info
info = [field.encode('utf-8') for field in info]
writer.writerow(info)
###############
if q_num % 10 == 0:
print 'answering question', splitname, q_num
for i_f in info_files:
i_f.close()
def evaluate():
# TODO: remove irrelevant printouts, remove sentence, url, headline,.. from outfile
from argus.main_frame import get_answer
from separate_relevance import relevance_load
from argus.features import feature_list_official as flo
q_num = 0
info_files = [
open('tests/feature_prints/' + i_f + '.tsv', 'wb') for i_f in flo
]
writers = [
csv.writer(info_file, delimiter='\t') for info_file in info_files
]
info_all = open('tests/feature_prints/all_features.tsv', 'wb')
writer_all = csv.writer(info_all, delimiter='\t')
info_rel = open('tests/feature_prints/all_features_rel.tsv', 'wb')
writer_rel = csv.writer(info_rel, delimiter='\t')
info_turk = open('tests/feature_prints/turk_sentences.tsv', 'wb')
writer_turk = csv.writer(info_turk, delimiter=',')
first = False
r = relevance_load()
npy_rel = []
with open(OUTFILE, 'wb') as csv_file:
writer = csv.writer(csv_file, delimiter='\t')
for csvfile in os.listdir(CSV_FOLDER):
if not csvfile.endswith(".csv"):
continue
i = 0
for line in csv.reader(open(CSV_FOLDER + '/' + csvfile),
delimiter=',',
skipinitialspace=True):
if i == 0:
# CSV header
i += 1
info = [
'HITID', 'Question', 'TurkAnswer', 'OurAnswer',
'OurKeywords', 'FoundSentence', 'OurHeadline',
'TurkTopic', 'TurkURL', 'OurURL', 'Source', 'info'
]
info += flo
if q_num == 0:
writer.writerow(info)
writer_turk.writerow(['question', 'sentence'])
first = True
continue
if line[16] == 'Rejected':
continue
q_num += 1
# Generate answer from question
ouranswer = get_answer(line[30])
# Toggle comment to keep only sources that were manually
# annotated as relevant at mturk
# filter_sources(ouranswer)
# Write details to various auxiliary csv files
url = ''
headline = ''
sentence = ''
source = ''
feat = ''
info = []
turk_answer = line[28]
if len(ouranswer.sources) != 0:
feature_print_all(writer_all, ouranswer, first,
turk_answer)
feature_print_rel(writer_rel, ouranswer, r, first)
feature_print(writers, ouranswer)
turk_print(writer_turk, ouranswer)
url = ouranswer.sources[0].url
headline = ouranswer.sources[0].headline
sentence = ouranswer.sources[0].sentence
source = ouranswer.sources[0].source
for j in range(len(flo)):
for s in ouranswer.sources:
feat += str(s.features[j].get_value()) + ":"
feat = feat[:-1]
info.append(feat)
feat = ''
# Write details to the output.tsv
info = [
line[0], line[30], turk_answer, ouranswer.text,
ouranswer.q.query, sentence, headline, line[31], line[29],
url, source, ouranswer.info
] + info
info = [field.encode('utf-8') for field in info]
writer.writerow(info)
# Store relevance features + gs for possible separate classifier
# training
for triplet in r:
if ouranswer.q.text == triplet[0]:
for s in ouranswer.sources:
if s.sentence == triplet[1]:
fs = [
f.get_value() for f in s.features
if '@' in f.get_type()
]
if len(npy_rel) == 0:
npy_rel = np.array(fs + [triplet[-1] / 2])
else:
npy_rel = np.vstack(
(npy_rel,
np.array(fs + [triplet[-1] / 2])))
###############
if q_num % 10 == 0:
print 'answering question', q_num
for i_f in info_files:
i_f.close()
np.save('tests/batches/relevance/npy_rel', npy_rel)
