def index(a1_file, articles, max_sentences):
global a_file
a_file = a1_file
q1= a1_file.protein1
q2= a1_file.protein2
query = queries.main(q1,q2) # Creates Queries
q1_syns = query.q1_syns # Retrieves Q1 and Q2 synonyms
q2_syns = query.q2_syns
print a1_file.protein1, ' synonyms = ', q1_syns
print a1_file.protein2, ' synonyms = ', q2_syns
ID_sentence_position_list = Papers.main(query, articles)
if len(ID_sentence_position_list) > 0:
print str(len(ID_sentence_position_list)) + " sentences with co-occurrence found"
sentences_with_score1 = Syntax_Scorer.main(ID_sentence_position_list, query, max_sentences)
sentences_with_score2 = Semantics_Scorer.main(sentences_with_score1, query)
sorted_sentences_with_score2 = sorted(sentences_with_score2, key=operator.attrgetter('score'), reverse=True)
if sorted_sentences_with_score2:
with open (r'txt_files_Testing\calibration unlimited sentences','a') as f:
f.write(query.q1+'\t'+query.q2+'\n')
for sent in sorted_sentences_with_score2:
sent_w_replaced_queries = Organize.insert_syns(sent.sentence,q1,q1_syns,q2,q2_syns)
if str(sent.sentence)[0] != '<':
f.write(str(sent.score) +' '+ str(sent.method_scored)+'\t'+ sent_w_replaced_queries + '\n')
print str(sent.score) +' '+ sent_w_replaced_queries
f.write('\n')
print_output_to_file(sorted_sentences_with_score2, q1_syns, q1, q2_syns, q2, a1_file)
print ""
def print_output_to_file(sorted_sentences_with_score2, q1_syns, q1, q2_syns,
q2, a1_file):
for sent_obj in sorted_sentences_with_score2[:1]: #Organizes output
if sorted_sentences_with_score2 == "No Papers with both queries were found on PubMed":
with open(r'text_files\generated_test_data.txt', 'a') as f:
f.write('\n' + a1_file.protein1 + '\t')
f.write(a1_file.protein2 + '\t')
if a1_file.paper_ID:
f.write(a1_file.paper_ID + '\n')
if not a1_file.paper_ID:
f.write('\n')
f.write("No Papers with both queries were found on PubMed!" +
'\n')
f.close()
elif sorted_sentences_with_score2 == "No sentences with co-occurrence found":
with open(r'text_files\generated_test_data.txt', 'a') as f:
f.write('\n' + a1_file.protein1 + '\t')
f.write(a1_file.protein2 + '\t')
if a1_file.paper_ID:
f.write(a1_file.paper_ID + '\n')
if not a1_file.paper_ID:
f.write('\n')
f.write('No sentences with co-occurrence found!' + '\n')
f.close()
else:
score = sent_obj.score
method_scored = str(sent_obj.method_scored)
sent = sent_obj.sentence
PMID = sent_obj.paper_id
sent_w_replaced_queries = Organize.insert_syns(
sent, q1, q1_syns, q2, q2_syns)
with open(r'text_files\generated_test_data.txt', 'a') as f:
f.write('\n' + a1_file.protein1 + '\t')
f.write(a1_file.protein2 + '\t')
f.write(str(score) + '\t')
f.write(str(method_scored) + '\t')
if a1_file.paper_ID:
f.write(a1_file.paper_ID + '\n')
if not a1_file.paper_ID:
f.write('\n')
f.write(sent_w_replaced_queries + '\n')
f.close()
def print_output_to_file(sorted_sentences_with_score2, q1_syns, q1, q2_syns, q2, a1_file):
for sent_obj in sorted_sentences_with_score2[:1]: #Organizes output
if sorted_sentences_with_score2 == "No Papers with both queries were found on PubMed":
with open(r'text_files\generated_test_data.txt','a') as f:
f.write('\n'+a1_file.protein1+'\t')
f.write(a1_file.protein2+'\t')
if a1_file.paper_ID:
f.write(a1_file.paper_ID+'\n')
if not a1_file.paper_ID:
f.write('\n')
f.write("No Papers with both queries were found on PubMed!"+'\n')
f.close()
elif sorted_sentences_with_score2 == "No sentences with co-occurrence found":
with open(r'text_files\generated_test_data.txt','a') as f:
f.write('\n'+a1_file.protein1+'\t')
f.write(a1_file.protein2+'\t')
if a1_file.paper_ID:
f.write(a1_file.paper_ID+'\n')
if not a1_file.paper_ID:
f.write('\n')
f.write('No sentences with co-occurrence found!'+'\n')
f.close()
else:
score = sent_obj.score
method_scored = str(sent_obj.method_scored)
sent= sent_obj.sentence
PMID = sent_obj.paper_id
sent_w_replaced_queries = Organize.insert_syns(sent,q1,q1_syns,q2,q2_syns)
with open(r'text_files\generated_test_data.txt','a') as f:
f.write('\n'+a1_file.protein1+'\t')
f.write(a1_file.protein2+'\t')
f.write(str(score)+'\t')
f.write(str(method_scored) + '\t')
if a1_file.paper_ID:
f.write(a1_file.paper_ID+'\n')
if not a1_file.paper_ID:
f.write('\n')
f.write(sent_w_replaced_queries+'\n')
f.close()
def index(a1_file, articles, max_sentences):
global a_file
a_file = a1_file
q1 = a1_file.protein1
q2 = a1_file.protein2
query = queries.main(q1, q2) # Creates Queries
q1_syns = query.q1_syns # Retrieves Q1 and Q2 synonyms
q2_syns = query.q2_syns
print a1_file.protein1, ' synonyms = ', q1_syns
print a1_file.protein2, ' synonyms = ', q2_syns
ID_sentence_position_list = Papers.main(query, articles)
if len(ID_sentence_position_list) > 0:
print str(len(
ID_sentence_position_list)) + " sentences with co-occurrence found"
sentences_with_score1 = Syntax_Scorer.main(ID_sentence_position_list,
query, max_sentences)
sentences_with_score2 = Semantics_Scorer.main(sentences_with_score1, query)
sorted_sentences_with_score2 = sorted(sentences_with_score2,
key=operator.attrgetter('score'),
reverse=True)
if sorted_sentences_with_score2:
with open(r'txt_files_Testing\calibration unlimited sentences',
'a') as f:
f.write(query.q1 + '\t' + query.q2 + '\n')
for sent in sorted_sentences_with_score2:
sent_w_replaced_queries = Organize.insert_syns(
sent.sentence, q1, q1_syns, q2, q2_syns)
if str(sent.sentence)[0] != '<':
f.write(
str(sent.score) + ' ' + str(sent.method_scored) +
'\t' + sent_w_replaced_queries + '\n')
print str(sent.score) + ' ' + sent_w_replaced_queries
f.write('\n')
print_output_to_file(sorted_sentences_with_score2, q1_syns, q1, q2_syns,
q2, a1_file)
print ""