#if problem.id != 'D0704': continue
sys.stderr.write(
"%s %d\n" %
(problem.id,
sum([len(doc.sentences) for doc in problem.new_docs])))
acronyms = framework.removeAcronymsFromProblem(problem)
mapper = concept_mapper.HeuristicMapperExp(problem, "n2", None)
mapper.map_concepts()
mapper.choose_sents()
concept_weight = mapper.concept_weight_sets[0]
#print concept_weight.keys()
#program = framework.build_program(problem, concept_weight, length=task.length_limit, sentences=mapper.relevant_sent_sets[0])
program = framework.build_alternative_program(
problem,
concept_weight,
length=task.length_limit,
sentences=mapper.relevant_sent_sets[0],
longuest_candidate_only=False,
providedAcronyms=acronyms)
# run the program and get the output
program.debug = 0
program.run()
#selection = framework.get_program_result(program)
selection = []
for variable in program.output:
if re.match(r'^s\d+$',
variable) and program.output[variable] == 1:
selection.append(program.binary[variable])
if len(selection) == 0:
sys.stderr.write(
'ERROR: empty summary, check the output of the solver\n')
for sentence in problem.get_new_sentences():
sentence.set_text(sentence.original)
# sentence.stemmed = sentence.no_stop
problem.query.set_text(problem.query.original)
#problem.query.stemmed = problem.query.no_stop
#if problem.id != 'D0704': continue
sys.stderr.write("%s %d\n" % (problem.id, sum([len(doc.sentences) for doc in problem.new_docs])))
acronyms = framework.removeAcronymsFromProblem(problem)
mapper = concept_mapper.HeuristicMapperExp(problem, "n2", None)
mapper.map_concepts()
mapper.choose_sents()
concept_weight = mapper.concept_weight_sets[0]
#print concept_weight.keys()
#program = framework.build_program(problem, concept_weight, length=task.length_limit, sentences=mapper.relevant_sent_sets[0])
program = framework.build_alternative_program(problem, concept_weight, length=task.length_limit, sentences=mapper.relevant_sent_sets[0], longuest_candidate_only=False, providedAcronyms=acronyms)
# run the program and get the output
program.debug = 0
program.run()
#selection = framework.get_program_result(program)
selection = []
for variable in program.output:
if re.match(r'^s\d+$', variable) and program.output[variable] == 1:
selection.append(program.binary[variable])
if len(selection) == 0:
sys.stderr.write('ERROR: empty summary, check the output of the solver\n')
sys.exit(1)
#selection = ordering.by_date(selection)
selection = ordering.by_dendrogram(selection, concept_weight, problem)
summary = "\n".join(sentence.original for sentence in selection)
summary = compression.addAcronymDefinitionsToSummary(summary, program.acronyms)
def run_standard(options, max_sents=10000):
## create output directory
try:
os.popen('rm -rf %s' % options.output)
except:
pass
try:
os.popen('mkdir -p %s' % options.output)
except:
sys.stderr.write('Error: could not create output directory [%s]\n')
sys.exit()
## summarize!
sys.stderr.write('generating summaries for task [%s]\n' % options.task)
sys.stderr.write('length limit [%d]\n' % task.length_limit)
sys.stderr.write('writing output to [%s]\n' % options.output)
map_times, run_times = {}, {}
## sentence compression
if options.compress:
for problem in task.problems:
if not '-A' in problem.id: continue
sys.stderr.write(
"%s %d\n" %
(problem.id,
sum([len(doc.sentences) for doc in problem.new_docs])))
#mapper = concept_mapper.HeuristicMapper(problem, "n2")
mapper = concept_mapper.CheatingMapper(problem, "n2")
mapper.map_concepts()
mapper.choose_sents()
concept_weights = mapper.concept_weights
#print concept_weight
#program = framework.build_program(problem, concept_weight, length=task.length_limit, sentences=mapper.relevant_sent_sets[0])
program = framework.build_alternative_program(
problem,
concept_weights,
length=task.length_limit,
sentences=mapper.relevant_sents,
longuest_candidate_only=False)
# run the program and get the output
program.debug = 0
program.run()
#selection = framework.get_program_result(program)
selection = []
for variable in program.output:
if re.match(r'^s\d+$',
variable) and program.output[variable] == 1:
selection.append(program.binary[variable])
selection = ordering.by_date(selection)
summary = "\n".join(sentence.original for sentence in selection)
#summary = compression.addAcronymDefinitionsToSummary(summary, program.acronyms)
## TAC id convention is annoying
output_id = problem.id
if options.task in ['u09', 'u08']:
output_id = problem.id[:5] + problem.id[6:]
output_file = open('%s/%s' % (options.output, output_id), 'w')
output_file.write(summary)
output_file.close()
elif options.mcd:
for problem in task.problems:
num_problem_sentences = len(problem.get_new_sentences())
if num_problem_sentences < 500: continue
used_sent_count = 0
for sentence in problem.get_new_sentences():
used_sent_count += 1
sentence.set_text(sentence.original)
if used_sent_count < max_sents: sentence.used = True
else: sentence.used = False
problem.query.set_text(problem.query.original)
sys.stdout.write(
"%s %d\n" %
(problem.id,
sum([len(doc.sentences) for doc in problem.new_docs])))
# compute idf values
word_idf = {}
for doc in problem.new_docs:
seen_words = {}
for sentence in doc.sentences:
if not sentence.used: continue
for word in sentence.no_stop_freq:
if word not in seen_words: seen_words[word] = 1
for word in seen_words:
if word not in word_idf: word_idf[word] = 1
else: word_idf[word] += 1
for word in word_idf:
word_idf[word] = 1.0 / word_idf[word]
# compare sentences to centroid and derive McDonald's relevance score
sentences = []
index = 0
for doc in problem.new_docs:
doc_text = " ".join([
sentence.original for sentence in doc.sentences
if sentence.used
])
centroid = text.Sentence(doc_text)
centroid.compute_norm()
problem.query.compute_norm()
for sentence in doc.sentences:
if not sentence.used: continue
sentence.compute_norm()
sentence.rel_score = sentence.sim_cosine(
centroid, word_idf) + 1 / (sentence.order + 1)
#sentence.rel_score = sentence.sim_cosine(centroid, word_idf) + sentence.sim_cosine(problem.query, word_idf)
sentences.append(sentence)
sentence.index = index
index += 1
# apply cutoff
sentences.sort(lambda x, y: 1 if x.rel_score < y.rel_score else -1)
if options.cutoff > 0 and len(sentences) > options.cutoff:
sentences = sentences[0:options.cutoff]
# construct ILP
program = ilp.IntegerLinearProgram(debug=0)
objective = []
length_constraint = []
for sentence in sentences:
objective.append("%+g s%d" %
(sentence.rel_score, sentence.index))
program.binary["s%d" % sentence.index] = sentence
length_constraint.append("%+g s%d" %
(sentence.length, sentence.index))
for peer in sentences:
if sentence == peer: continue
score = sentence.sim_cosine(peer, word_idf)
if score > 0:
objective.append("%+g s%d_%d" %
(-score, sentence.index, peer.index))
program.binary["s%d_%d" %
(sentence.index, peer.index)] = [
sentence, peer
]
program.constraints["c1_%d_%d" % (sentence.index, peer.index)] = \
"s%d_%d - s%d <= 0" % (sentence.index, peer.index, sentence.index)
program.constraints["c2_%d_%d" % (sentence.index, peer.index)] = \
"s%d_%d - s%d <= 0" % (sentence.index, peer.index, peer.index)
program.constraints["c3_%d_%d" % (sentence.index, peer.index)] = \
"s%d + s%d - s%d_%d <= 1" % (sentence.index, peer.index, sentence.index, peer.index)
program.objective["score"] = " ".join(objective)
program.constraints["length"] = " ".join(
length_constraint) + " <= %g" % task.length_limit
run_times[problem.id] = time.time()
program.run()
run_times[problem.id] = time.time() - run_times[problem.id]
selection = []
score = 0
# get solution and check consistency
for variable in program.binary:
if variable in program.output and program.output[variable] == 1:
if type(program.binary[variable]) == type(sentences[0]):
selection.append(program.binary[variable])
score += program.binary[variable].rel_score
for peer in program.output:
if program.output[
peer] == 0 or peer == variable or type(
program.binary[peer]) != type(
sentences[0]):
continue
if program.binary[variable].sim_cosine(
program.binary[peer], word_idf) == 0:
continue
quadratic = "s%d_%d" % (
program.binary[variable].index,
program.binary[peer].index)
if quadratic not in program.output or program.output[
quadratic] != 1:
print "WARNING: %s selected but %s not selected" % (
variable, quadratic)
else:
score -= program.binary[variable][0].sim_cosine(
program.binary[variable][1], word_idf)
if program.output[
"s%d" %
program.binary[variable][0].index] != 1:
print "WARNING: %s selected while s%d not selected" % (
variable, program.binary[variable][0].index)
if program.output[
"s%d" %
program.binary[variable][1].index] != 1:
print "WARNING: %s selected while s%d not selected" % (
variable, program.binary[variable][1].index)
#if math.fabs(program.result["score"] - score) > .1:
# print "WARNING: difference between score = %g and expected = %g" % (program.result["score"], score)
selection = ordering.by_date(selection)
new_id = re.sub(r'.-(.)$', r'-\1', problem.id)
output_file = open("%s/%s" % (options.output, new_id), "w")
for sentence in selection:
output_file.write(sentence.original + "\n")
output_file.close()
else:
hist = prob_util.Counter()
input_sents = []
for problem in task.problems:
num_problem_sentences = len(problem.get_new_sentences())
#if num_problem_sentences < 300: continue
if not '-A' in problem.id: continue
if options.ir:
#docs = [doc for doc, val in problem.ir_docs]
#for doc in docs: doc.get_sentences()
num_overlap = len(
set([d.id for d in problem.ir_docs
]).intersection(set([d.id
for d in problem.new_docs])))
print '%s overlap: %d' % (problem.id, num_overlap)
info_fh.write('%s overlap [%d]\n' % (problem.id, num_overlap))
sys.stderr.write('problem [%s] input sentences [%d]' %
(problem.id, num_problem_sentences))
input_sents.append(num_problem_sentences)
## select a concept mapper
map_times[problem.id] = time.time()
if options.cheat:
mapper = concept_mapper.CheatingMapper(problem, options.units)
else:
mapper = concept_mapper.HeuristicMapperExp(
problem, options.units)
## timing test
mapper.max_sents = max_sents
## map input concepts to weights
success = mapper.map_concepts()
if not success: sys.exit()
## choose a subset of the input sentences based on the mapping
success = mapper.choose_sents()
if not success: sys.exit()
map_times[problem.id] = time.time() - map_times[problem.id]
## testing
#fh = open('concept_matrix', 'w')
for sent in mapper.relevant_sent_concepts:
hist[len(sent)] += 1
#fh.write(''.join(['%d, ' %concept for concept in sent[:-1]]))
#fh.write('%d\n' %sent[-1])
hist[0] += (num_problem_sentences -
len(mapper.relevant_sent_concepts))
#hist.displaySorted(N=100)
#sys.exit()
## end testing
## setup and run the ILP
run_times[problem.id] = time.time()
selection = mapper.run(task.length_limit)
selection = ordering.by_date(selection)
run_times[problem.id] = time.time() - run_times[problem.id]
## TAC id convention is annoying
output_id = problem.id
if options.task in ['u09', 'u08']:
output_id = problem.id[:5] + problem.id[6:]
output_file = open('%s/%s' % (options.output, output_id), 'w')
word_count = 0
for sentence in selection:
output_file.write(sentence.original + '\n')
word_count += len(sentence.original.split())
output_file.close()
curr_time = map_times[problem.id] + run_times[problem.id]
sys.stderr.write(' word count [%d] time [%1.2fs]\n' %
(word_count, curr_time))
def run_standard(options, max_sents=10000):
## create output directory
try: os.popen('rm -rf %s' %options.output)
except: pass
try: os.popen('mkdir -p %s' %options.output)
except:
sys.stderr.write('Error: could not create output directory [%s]\n')
sys.exit()
## summarize!
sys.stderr.write('generating summaries for task [%s]\n' %options.task)
sys.stderr.write('length limit [%d]\n' %task.length_limit)
sys.stderr.write('writing output to [%s]\n' %options.output)
map_times, run_times = {}, {}
## sentence compression
if options.compress:
for problem in task.problems:
if not '-A' in problem.id: continue
sys.stderr.write("%s %d\n" % (problem.id, sum([len(doc.sentences) for doc in problem.new_docs])))
#mapper = concept_mapper.HeuristicMapper(problem, "n2")
mapper = concept_mapper.CheatingMapper(problem, "n2")
mapper.map_concepts()
mapper.choose_sents()
concept_weights = mapper.concept_weights
#print concept_weight
#program = framework.build_program(problem, concept_weight, length=task.length_limit, sentences=mapper.relevant_sent_sets[0])
program = framework.build_alternative_program(problem, concept_weights, length=task.length_limit, sentences=mapper.relevant_sents, longuest_candidate_only=False)
# run the program and get the output
program.debug = 0
program.run()
#selection = framework.get_program_result(program)
selection = []
for variable in program.output:
if re.match(r'^s\d+$', variable) and program.output[variable] == 1:
selection.append(program.binary[variable])
selection = ordering.by_date(selection)
summary = "\n".join(sentence.original for sentence in selection)
#summary = compression.addAcronymDefinitionsToSummary(summary, program.acronyms)
## TAC id convention is annoying
output_id = problem.id
if options.task in ['u09', 'u08']: output_id = problem.id[:5]+problem.id[6:]
output_file = open('%s/%s' % (options.output, output_id), 'w')
output_file.write(summary)
output_file.close()
elif options.mcd:
for problem in task.problems:
num_problem_sentences = len(problem.get_new_sentences())
if num_problem_sentences < 500: continue
used_sent_count = 0
for sentence in problem.get_new_sentences():
used_sent_count += 1
sentence.set_text(sentence.original)
if used_sent_count < max_sents: sentence.used = True
else: sentence.used = False
problem.query.set_text(problem.query.original)
sys.stdout.write("%s %d\n" % (problem.id, sum([len(doc.sentences) for doc in problem.new_docs])))
# compute idf values
word_idf = {}
for doc in problem.new_docs:
seen_words = {}
for sentence in doc.sentences:
if not sentence.used: continue
for word in sentence.no_stop_freq:
if word not in seen_words: seen_words[word] = 1
for word in seen_words:
if word not in word_idf: word_idf[word] = 1
else: word_idf[word] += 1
for word in word_idf:
word_idf[word] = 1.0 / word_idf[word]
# compare sentences to centroid and derive McDonald's relevance score
sentences = []
index = 0
for doc in problem.new_docs:
doc_text = " ".join([sentence.original for sentence in doc.sentences if sentence.used])
centroid = text.Sentence(doc_text)
centroid.compute_norm()
problem.query.compute_norm()
for sentence in doc.sentences:
if not sentence.used: continue
sentence.compute_norm()
sentence.rel_score = sentence.sim_cosine(centroid, word_idf) + 1 / (sentence.order + 1)
#sentence.rel_score = sentence.sim_cosine(centroid, word_idf) + sentence.sim_cosine(problem.query, word_idf)
sentences.append(sentence)
sentence.index = index
index += 1
# apply cutoff
sentences.sort(lambda x, y: 1 if x.rel_score < y.rel_score else -1)
if options.cutoff > 0 and len(sentences) > options.cutoff:
sentences = sentences[0:options.cutoff]
# construct ILP
program = ilp.IntegerLinearProgram(debug=0)
objective = []
length_constraint = []
for sentence in sentences:
objective.append("%+g s%d" % (sentence.rel_score, sentence.index))
program.binary["s%d" % sentence.index] = sentence
length_constraint.append("%+g s%d" % (sentence.length, sentence.index))
for peer in sentences:
if sentence == peer: continue
score = sentence.sim_cosine(peer, word_idf)
if score > 0:
objective.append("%+g s%d_%d" % (-score, sentence.index, peer.index))
program.binary["s%d_%d" % (sentence.index, peer.index)] = [sentence, peer]
program.constraints["c1_%d_%d" % (sentence.index, peer.index)] = \
"s%d_%d - s%d <= 0" % (sentence.index, peer.index, sentence.index)
program.constraints["c2_%d_%d" % (sentence.index, peer.index)] = \
"s%d_%d - s%d <= 0" % (sentence.index, peer.index, peer.index)
program.constraints["c3_%d_%d" % (sentence.index, peer.index)] = \
"s%d + s%d - s%d_%d <= 1" % (sentence.index, peer.index, sentence.index, peer.index)
program.objective["score"] = " ".join(objective)
program.constraints["length"] = " ".join(length_constraint) + " <= %g" % task.length_limit
run_times[problem.id] = time.time()
program.run()
run_times[problem.id] = time.time() - run_times[problem.id]
selection = []
score = 0
# get solution and check consistency
for variable in program.binary:
if variable in program.output and program.output[variable] == 1:
if type(program.binary[variable]) == type(sentences[0]):
selection.append(program.binary[variable])
score += program.binary[variable].rel_score
for peer in program.output:
if program.output[peer] == 0 or peer == variable or type(program.binary[peer]) != type(sentences[0]):
continue
if program.binary[variable].sim_cosine(program.binary[peer], word_idf) == 0:
continue
quadratic = "s%d_%d" % (program.binary[variable].index, program.binary[peer].index)
if quadratic not in program.output or program.output[quadratic] != 1:
print "WARNING: %s selected but %s not selected" % (variable, quadratic)
else:
score -= program.binary[variable][0].sim_cosine(program.binary[variable][1], word_idf)
if program.output["s%d" % program.binary[variable][0].index] != 1:
print "WARNING: %s selected while s%d not selected" % (variable, program.binary[variable][0].index)
if program.output["s%d" % program.binary[variable][1].index] != 1:
print "WARNING: %s selected while s%d not selected" % (variable, program.binary[variable][1].index)
#if math.fabs(program.result["score"] - score) > .1:
# print "WARNING: difference between score = %g and expected = %g" % (program.result["score"], score)
selection = ordering.by_date(selection)
new_id = re.sub(r'.-(.)$', r'-\1', problem.id)
output_file = open("%s/%s" % (options.output, new_id), "w")
for sentence in selection:
output_file.write(sentence.original + "\n")
output_file.close()
else:
hist = prob_util.Counter()
input_sents = []
for problem in task.problems:
num_problem_sentences = len(problem.get_new_sentences())
#if num_problem_sentences < 300: continue
if not '-A' in problem.id: continue
if options.ir:
#docs = [doc for doc, val in problem.ir_docs]
#for doc in docs: doc.get_sentences()
num_overlap = len(set([d.id for d in problem.ir_docs]).intersection(set([d.id for d in problem.new_docs])))
print '%s overlap: %d' %(problem.id, num_overlap)
info_fh.write('%s overlap [%d]\n' %(problem.id, num_overlap))
sys.stderr.write('problem [%s] input sentences [%d]' %(problem.id, num_problem_sentences))
input_sents.append(num_problem_sentences)
## select a concept mapper
map_times[problem.id] = time.time()
if options.cheat:
mapper = concept_mapper.CheatingMapper(problem, options.units)
else:
mapper = concept_mapper.HeuristicMapperExp(problem, options.units)
## timing test
mapper.max_sents = max_sents
## map input concepts to weights
success = mapper.map_concepts()
if not success: sys.exit()
## choose a subset of the input sentences based on the mapping
success = mapper.choose_sents()
if not success: sys.exit()
map_times[problem.id] = time.time() - map_times[problem.id]
## testing
#fh = open('concept_matrix', 'w')
for sent in mapper.relevant_sent_concepts:
hist[len(sent)] += 1
#fh.write(''.join(['%d, ' %concept for concept in sent[:-1]]))
#fh.write('%d\n' %sent[-1])
hist[0] += (num_problem_sentences-len(mapper.relevant_sent_concepts))
#hist.displaySorted(N=100)
#sys.exit()
## end testing
## setup and run the ILP
run_times[problem.id] = time.time()
selection = mapper.run(task.length_limit)
selection = ordering.by_date(selection)
run_times[problem.id] = time.time() - run_times[problem.id]
## TAC id convention is annoying
output_id = problem.id
if options.task in ['u09', 'u08']: output_id = problem.id[:5]+problem.id[6:]
output_file = open('%s/%s' % (options.output, output_id), 'w')
word_count = 0
for sentence in selection:
output_file.write(sentence.original + '\n')
word_count += len(sentence.original.split())
output_file.close()
curr_time = map_times[problem.id] + run_times[problem.id]
sys.stderr.write(' word count [%d] time [%1.2fs]\n' %(word_count, curr_time))