def generateTestFeatures(client_socket, infile, featurefile):
#------------------------------------------------
doc = Document(infile)
#------------------------------------------------
# Load pickle for label
picklefile = DIR['DATA'] + 'test-labels-pickle'
global test_labels
with open(picklefile, 'rb') as pfile:
test_labels = pickle.load(pfile)
#------------------------------------------------
# For display and analysis
dir, filename = os.path.split(infile)
fcode = re.match(r'(.+)-parscit-section\.xml', filename).group(1)
#------------------------------------------------
test_sents, sent_indices = getRankedSent(doc, fcode)
#-----------------------------------------
# Sectional Ranker
sections = []
for sec, block in doc.document.items():
sentences = ''
for key in sorted(block.keys()):
sentences += (str(block[key]))
sections.append(sentences)
sec_ranker = Ranker(sections)
sec_indices = sent2Section(doc, sent_indices)
#-----------------------------------------
for sentence, sent_idx, sec_idx in zip(test_sents, sent_indices,
sec_indices):
key = fcode + '-' + str(sent_idx)
feature_string = test_data[key]['reallbl']
tree = parseTrees(getDepParse(client_socket, sentence))
feature_string += processTree(tree, sec_ranker, sec_idx, False)
test_data[key]['depparse'] = getTree(tree)
test_data[key]['features'] = feature_string
writeToFile(featurefile, feature_string + '\n', 'a')
def processTree(outfile, root, ranker, idx, label, sourcefile=None, real_sidx=None):
trees.append(root)
verb_val = ranker.tfidf_value(idx, root.word)
#-------------------------------------
# For display
root.value += '----' + str(round(verb_val, 4))
#-------------------------------------
#verb_val = ranker.total_count(root.word)
# Look for subject
subj = findNode(root, 'subj')
subj_val = getValue(subj, ranker, idx)
#-------------------------------------
# For display
if subj is not None:
subj.value += '----' + str(round(subj_val, 4))
#-------------------------------------
obj = findNode(root, 'obj')
obj_val = getValue(obj, ranker, idx)
#-------------------------------------
# For display
if obj is not None:
obj.value += '----' + str(round(obj_val, 4))
#-------------------------------------
# Adding the tree for pickling
if sourcefile is not None:
sfile = re.match(r'/home/ankur/devbench/scientific/scisumm/demo/(.+)-parscit-section\.xml', sourcefile).group(1)
key = sfile + "-" + str(real_sidx)
test_data[key]['depparse'] = getTree(root)
#-------------------------------------
writeToFile(outfile, label + " 1:" + str(verb_val) + " 2:" +
str(subj_val) + " 3:" + str(obj_val) + '\n', 'a')
def generateTrainFeatures(client_socket, infile, featurefile):
#------------------------------------------------
doc = Document(infile)
all_sentences, all_offset = doc.all_sentences()
#------------------------------------------------
# Positive sentences
pos_sents, offset = doc.section_sentences('abstract')
sent_indices = range(offset, offset + len(pos_sents))
#-----------------------------------------
# Sectional Ranker
sections = []
for sec, block in doc.document.items():
sentences = ''
for key in sorted(block.keys()):
sentences += (str(block[key]))
sections.append(sentences)
sec_ranker = Ranker(sections)
sec_indices = sent2Section(doc, sent_indices)
#-----------------------------------------
# Count ranker
#count_ranker = Ranker(all_sentences, tfidf=False)
#-----------------------------------------
for sentence, sent_idx, sec_idx in zip(pos_sents, sent_indices,
sec_indices):
feature_string = '+1'
tree = parseTrees(getDepParse(client_socket, sentence))
feature_string += processTree(tree, sec_ranker, sec_idx, False)
#feature_string += processTree(tree, count_ranker, sent_idx, True)
writeToFile(featurefile, feature_string + '\n', 'a')
#------------------------------------------------
# Negative sentences
neg_ranker = TextRank(all_sentences)
neg_ranker.rank()
num = 5
x = -1
neg_sents = []
sent_indices = []
while num > 0:
idx = neg_ranker.scores[x][0] + all_offset
x -= 1
if not validSentence(doc[idx]):
continue
else:
sent_indices.append(idx)
neg_sents.append(doc[idx].sentence.encode('utf-8'))
num -= 1
sec_indices = sent2Section(doc, sent_indices)
#------------------------------------------------
for sentence, sent_idx, sec_idx in zip(neg_sents, sent_indices,
sec_indices):
feature_string = '-1'
tree = parseTrees(getDepParse(client_socket, sentence))
feature_string += processTree(tree, sec_ranker, sec_idx, False)
#feature_string += processTree(tree, count_ranker, sent_idx, True)
writeToFile(featurefile, feature_string + '\n', 'a')
#------------------------------------------------
print "All input files processed to create feature vectors for training."
def classifyDoc(document):
featurefile = DIR['DATA'] + 'features_svm.txt'
classify = DIR['BASE'] + "lib/svm-light/svm_classify"
model = DIR['DATA'] + "sec-tfidf-model.txt"
outfile = DIR['DATA'] + "svm-out-sent.txt"
#sumlength = 5
client_socket = getConnection()
doc = Document(document)
#-----------------------------------------
# Clubbing sentences in sections and passing to the ranker
sections = []
for sec, block in doc.document.items():
sentences = ''
for key in sorted(block.keys()):
sentences += (str(block[key]))
sections.append(sentences)
sec_ranker = Ranker(sections)
sents, offset = doc.all_sentences()
ranker = TextRank(sents)
ranker.rank()
#-----------------------------------------
sents, sent_indices = getSecRankedSent(doc)
#-----------------------------------------
# The sent_idx needs to be converted to reflect the corresponding
# section index
sec_indices = sent2Section(doc, sent_indices)
summary = []
classified = []
sum_len = 0
for sent, sec_idx in zip(sents, sec_indices):
#-----------------------------------------
# dependency parse
tree = parseTrees(getDepParse(client_socket, sent))
#-----------------------------------------
deleteFiles([featurefile])
feature_string = "+1"
feature_string += processTree(tree, sec_ranker, sec_idx, False)
writeToFile(featurefile, feature_string + '\n', 'a')
deleteFiles([outfile])
subprocess.call([classify, featurefile, model, outfile])
with open(outfile, 'r') as ofile:
sent_val = float(ofile.read().strip())
classified.append((sent, sent_val))
for sent, val in sorted(classified, key=itemgetter(1)):
summary.append(sent)
sum_len += len(sent.split(' '))
if sum_len > 130:
break
writeToFile(DIR['DATA'] + "svm_summary.txt", '\n'.join(summary), 'w')
print '\n'.join(summary)
def get_pos_sentences(infile, outfile, backup=False):
doc = Document(infile)
#sentences, o = doc.all_sentences()
#ranker = Ranker(sentences, tfidf=False)
#-----------------------------------------
# Instead of the above, now sentences will be clubbed into sections and
# passed to the ranker, which is to be returned
sections = []
for sec, block in doc.document.items():
sentences = ''
for key in sorted(block.keys()):
sentences += (str(block[key]))
sections.append(sentences)
ranker = Ranker(sections)
#-----------------------------------------
sent, offset = doc.section_sentences('abstract')
sent_idx = range(offset, offset + len(sent))
samples = '\n'.join(sent)
writeToFile(outfile, samples, 'w')
#return ranker, sent_idx
# The sent_idx needs to be converted to reflect the corresponding section
# index
section_idx = sent2Section(doc, sent_idx)
if backup:
backupfile = DIR['BASE'] + "data/backup.txt"
writeToFile(backupfile, "\n---------Positive---------\n", 'a')
writeToFile(backupfile, samples, 'a')
return ranker, section_idx
def get_test_sentences(infile, outfile, backup=False):
doc = Document(infile)
sentences, offset = doc.all_sentences()
ranker = TextRank(sentences)
ranker.rank()
num = 7
x = 0
samples = ''
sent_idx = []
while num > 0:
idx = ranker.scores[x][0] + offset
x += 1
#if not validSentence(doc[idx]):
# continue
#else:
# sent_idx.append(idx)
# samples += doc[idx].sentence.encode('utf-8') + '\n'
# num -= 1
sent_idx.append(idx)
samples += doc[idx].sentence.encode('utf-8') + '\n'
num -= 1
#---------------------------------------------------
# Storing the sentence in the dictionary for pickling for display
infi = re.match(r'/home/ankur/devbench/scientific/scisumm/demo/(.+)-parscit-section\.xml', infile).group(1)
key = infi + "-" + str(idx)
test_data[key] = {'sentence': doc[idx].sentence.encode('utf-8'),
'textrank': ranker.scores[x - 1][1],
'contextpre': getContext(doc, idx, -2),
'contextpos': getContext(doc, idx, 2)}
writeToFile(outfile, samples, 'w')
#ranker = Ranker(sentences, tfidf=False)
#return ranker, sent_idx
#-----------------------------------------
# Calculating the sectional TF-IDF
sections = []
for sec, block in doc.document.items():
sentences = ''
for key in sorted(block.keys()):
sentences += (str(block[key]))
sections.append(sentences)
ranker = Ranker(sections)
#-----------------------------------------
# The sent_idx needs to be converted to reflect the corresponding section
# index
section_idx = sent2Section(doc, sent_idx)
if backup:
backupfile = DIR['BASE'] + "data/backup.txt"
writeToFile(backupfile, "\n---------" + str(doc) + "---------\n", 'a')
writeToFile(backupfile, samples, 'a')
return ranker, section_idx, sent_idx
def get_neg_sentences(infile, outfile, backup=False):
doc = Document(infile)
sentences, offset = doc.all_sentences()
ranker = TextRank(sentences)
ranker.rank()
num = 5
x = -1
samples = ''
sent_idx = []
while num > 0:
idx = ranker.scores[x][0] + offset
x -= 1
if not validSentence(doc[idx]):
continue
else:
sent_idx.append(idx)
samples += doc[idx].sentence.encode('utf-8') + '\n'
num -= 1
writeToFile(outfile, samples, 'w')
#ranker = Ranker(sentences, tfidf=False)
#return ranker, sent_idx
#-----------------------------------------
# Calculating the sectional TF-IDF
sections = []
for sec, block in doc.document.items():
sentences = ''
for key in sorted(block.keys()):
sentences += (str(block[key]))
sections.append(sentences)
ranker = Ranker(sections)
#-----------------------------------------
# The sent_idx needs to be converted to reflect the corresponding section
# index
section_idx = sent2Section(doc, sent_idx)
if backup:
backupfile = DIR['BASE'] + "data/backup.txt"
writeToFile(backupfile, "\n---------Negative---------\n", 'a')
writeToFile(backupfile, samples, 'a')
return ranker, section_idx
def classifyDoc(document):
featurefile = DIR['DATA'] + 'features_svm.txt'
classify = DIR['BASE'] + "lib/svm-light/svm_classify"
model = DIR['DATA'] + "sec-tfidf-model.txt"
outfile = DIR['DATA'] + "svm-out-sent.txt"
#sumlength = 5
client_socket = getConnection()
doc = Document(document)
#-----------------------------------------
# Clubbing sentences in sections and passing to the ranker
sections = []
for sec, block in doc.document.items():
sentences = ''
for key in sorted(block.keys()):
sentences += (str(block[key]))
sections.append(sentences)
sec_ranker = Ranker(sections)
sents, offset = doc.all_sentences()
ranker = TextRank(sents)
ranker.rank()
looper = 20
num = 10
x = 0
summary = []
sent_idx = [0]
sum_len = 0
while num > 0:
idx = ranker.scores[x][0] + offset
x += 1
if not validSentence(doc[idx]):
continue
elif doc.get_section_name(idx) == 'abstract':
continue
sent_idx[0] = idx
#-----------------------------------------
# dependency parse
tree = parseTrees(getDepParse(client_socket,
doc[idx].sentence.encode('utf-8')))
#-----------------------------------------
# The sent_idx needs to be converted to reflect the corresponding
# section index
sec_idx = sent2Section(doc, sent_idx)
#-----------------------------------------
deleteFiles([featurefile])
feature_string = "+1"
feature_string += processTree(tree, sec_ranker, sec_idx[0], False)
writeToFile(featurefile, feature_string + '\n', 'a')
deleteFiles([outfile])
subprocess.call([classify, featurefile, model, outfile])
with open(outfile, 'r') as ofile:
sent_val = float(ofile.read().strip())
if sent_val > 0:
summary.append(doc[idx].sentence.encode('utf-8'))
num -= 1
sum_len += len(doc[idx].sentence.encode('utf-8').split(' '))
if sum_len > 130:
break
looper -= 1
if looper == 0:
print "Looper Done"
break
writeToFile(DIR['DATA'] + "svm_summary.txt", '\n'.join(summary), 'w')
print '\n'.join(summary)
def classifyDoc(document):
featurefile = DIR['DATA'] + 'features_svm.txt'
classify = DIR['BASE'] + "lib/svm-light/svm_classify"
model = DIR['DATA'] + "sec-tfidf-model.txt"
outfile = DIR['DATA'] + "svm-out-sent.txt"
#sumlength = 5
client_socket = getConnection()
doc = Document(document)
#-----------------------------------------
# Clubbing sentences in sections and passing to the ranker
sections = []
for sec, block in doc.document.items():
sentences = ''
for key in sorted(block.keys()):
sentences += (str(block[key]))
sections.append(sentences)
sec_ranker = Ranker(sections)
sents, offset = doc.all_sentences()
ranker = TextRank(sents)
ranker.rank()
looper = 20
num = 10
x = 0
summary = []
sent_idx = [0]
sum_len = 0
while num > 0:
idx = ranker.scores[x][0] + offset
x += 1
if not validSentence(doc[idx]):
continue
elif doc.get_section_name(idx) == 'abstract':
continue
sent_idx[0] = idx
#-----------------------------------------
# dependency parse
tree = parseTrees(
getDepParse(client_socket, doc[idx].sentence.encode('utf-8')))
#-----------------------------------------
# The sent_idx needs to be converted to reflect the corresponding
# section index
sec_idx = sent2Section(doc, sent_idx)
#-----------------------------------------
deleteFiles([featurefile])
feature_string = "+1"
feature_string += processTree(tree, sec_ranker, sec_idx[0], False)
writeToFile(featurefile, feature_string + '\n', 'a')
deleteFiles([outfile])
subprocess.call([classify, featurefile, model, outfile])
with open(outfile, 'r') as ofile:
sent_val = float(ofile.read().strip())
if sent_val > 0:
summary.append(doc[idx].sentence.encode('utf-8'))
num -= 1
sum_len += len(doc[idx].sentence.encode('utf-8').split(' '))
if sum_len > 130:
break
looper -= 1
if looper == 0:
print "Looper Done"
break
writeToFile(DIR['DATA'] + "svm_summary.txt", '\n'.join(summary), 'w')
print '\n'.join(summary)
def generateTrainFeatures(client_socket, infile, featurefile):
#------------------------------------------------
doc = Document(infile)
all_sentences, all_offset = doc.all_sentences()
#------------------------------------------------
# For display and analysis
dir, filename = os.path.split(infile)
fcode = re.match(r'(.+)-parscit-section\.xml', filename).group(1)
#------------------------------------------------
#------------------------------------------------
# Positive sentences
pos_sents, offset = doc.section_sentences('abstract')
sent_indices = range(offset, offset + len(pos_sents))
#-----------------------------------------
# Sectional Ranker
sections = []
for sec, block in doc.document.items():
sentences = ''
for key in sorted(block.keys()):
sentences += (str(block[key]))
sections.append(sentences)
sec_ranker = Ranker(sections)
sec_indices = sent2Section(doc, sent_indices)
#-----------------------------------------
# Count ranker
#count_ranker = Ranker(all_sentences, tfidf=False)
#-----------------------------------------
for sentence, sent_idx, sec_idx in zip(pos_sents, sent_indices,
sec_indices):
key = fcode + '-' + str(sent_idx)
feature_string = '+1'
tree = parseTrees(getDepParse(client_socket, sentence))
feature_string += processTree(tree, sec_ranker, sec_idx, 1, False)
train_data[key] = {'sentence': doc[sent_idx].sentence.encode('utf-8'),
'reallbl': '+1',
'features': feature_string}
writeToFile(featurefile, feature_string + '\n', 'a')
#------------------------------------------------
# Negative sentences
neg_ranker = TextRank(all_sentences)
neg_ranker.rank()
num = 5
x = -1
neg_sents = []
sent_indices = []
while num > 0:
idx = neg_ranker.scores[x][0] + all_offset
x -= 1
if not validSentence(doc[idx]):
continue
else:
sent_indices.append(idx)
neg_sents.append(doc[idx].sentence.encode('utf-8'))
num -= 1
sec_indices = sent2Section(doc, sent_indices)
#------------------------------------------------
for sentence, sent_idx, sec_idx in zip(neg_sents, sent_indices,
sec_indices):
key = fcode + '-' + str(sent_idx)
feature_string = '-1'
tree = parseTrees(getDepParse(client_socket, sentence))
feature_string += processTree(tree, sec_ranker, sec_idx, 1, False)
train_data[key] = {'sentence': doc[sent_idx].sentence.encode('utf-8'),
'reallbl': '-1',
'features': feature_string}
writeToFile(featurefile, feature_string + '\n', 'a')
#------------------------------------------------
print "All input files processed to create feature vectors for training."
