def main(q1, q2, articles, batch, input_type, outputFileName, dictType):
num_articles = int(articles)
query = queries.main(q1, q2)
if batch == "yes":
q1_id_list, q2_id_list = pmids.main(query, num_articles)
q1_file_paths = run_tees_batch(q1, q1_id_list)
q2_file_paths = run_tees_batch(q2, q2_id_list)
if batch == "no":
q1_id_list, q2_id_list = pmids.main(query, num_articles)
q1_file_paths = run_tees(q1, q1_id_list)
q2_file_paths = run_tees(q2, q2_id_list)
q1_dict = get_info_from_interaction_xml(q1_file_paths)
q2_dict = get_info_from_interaction_xml(q2_file_paths)
if dictType == 'all' or dictType == 'both':
all_words_dict = get_all_words_dict(q1, q2, q1_dict, q2_dict)
normalized_all_words_dict = normalize_dict(all_words_dict, query)
angle_list_all = Cosine_Sim.main(normalized_all_words_dict, q1, q2)
print_pair_score_dict(angle_list_all, normalized_all_words_dict, q1,
q2, input_type, outputFileName)
if dictType == 'protein' or dictType == 'both':
query_dicts = [q1_dict, q2_dict]
combined_dict = combine_dictionaries(query_dicts)
normalized_protein_dict = normalize_dict(combined_dict, query)
angle_list_protein = Cosine_Sim.main(normalized_protein_dict, q1, q2)
print_pair_score_dict(angle_list_protein, normalized_protein_dict, q1,
q2, input_type, outputFileName)
def get_all_predicted_relations_dict(hprd50_paper_dict, max_sentences):
all_predicted_relations_dict = {}
for key in hprd50_paper_dict:
found_relation_score_tuples_list = []
for relation in hprd50_paper_dict[key].possible_relations_Tnumber:
q1 = relation[0]
q2 = relation[1]
found_relation_score_tuple = ((q1, q2), 0)
if q1 == q2:
continue
query = queries.main(q1,q2)
ID_sentence_list = []
ID_sentence_list = find_cooccurrence_sents(hprd50_paper_dict[key], query)
print 'ID_sentence_list: ',ID_sentence_list
if not ID_sentence_list:
found_relation_score_tuple = ((q1, q2), 0)
print found_relation_score_tuple
found_relation_score_tuples_list.append(found_relation_score_tuple)
if ID_sentence_list:
sentences_with_score1 = Score1.rank_sentences(ID_sentence_list, query, max_sentences)
sentences_with_score2 = Score2.main(sentences_with_score1, query)
sorted_sentences_with_score2 = list(sorted(sentences_with_score2, key=operator.attrgetter('score'), reverse=True))
#------------------------------ if sorted_sentences_with_score2:
#----------------- if len(sorted_sentences_with_score2) > 1:
#-------------------------------------------------- pass
#----------------------------------------------------- else:
for sentence_object in sorted_sentences_with_score2:
found_relation_score_tuple = ((q1, q2), sentence_object.score, sentence_object.order_in_abstract)
print found_relation_score_tuple
found_relation_score_tuples_list.append(found_relation_score_tuple)
all_predicted_relations_dict[key]=found_relation_score_tuples_list
return all_predicted_relations_dict
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 main(q1, q2, articles, batch, input_type, outputFileName, dictType):
num_articles = int(articles)
query = queries.main(q1,q2)
if batch == "yes":
q1_id_list, q2_id_list = pmids.main(query, num_articles)
q1_file_paths= run_tees_batch(q1, q1_id_list)
q2_file_paths= run_tees_batch(q2, q2_id_list)
if batch == "no":
q1_id_list, q2_id_list = pmids.main(query, num_articles)
q1_file_paths= run_tees(q1, q1_id_list)
q2_file_paths= run_tees(q2, q2_id_list)
q1_dict = get_info_from_interaction_xml(q1_file_paths)
q2_dict = get_info_from_interaction_xml(q2_file_paths)
if dictType == 'all' or dictType == 'both':
all_words_dict = get_all_words_dict(q1, q2, q1_dict, q2_dict)
normalized_all_words_dict = normalize_dict(all_words_dict, query)
angle_list_all = Cosine_Sim.main(normalized_all_words_dict, q1, q2)
print_pair_score_dict(angle_list_all, normalized_all_words_dict, q1, q2, input_type, outputFileName)
if dictType == 'protein' or dictType == 'both':
query_dicts = [q1_dict, q2_dict]
combined_dict = combine_dictionaries(query_dicts)
normalized_protein_dict = normalize_dict(combined_dict, query)
angle_list_protein = Cosine_Sim.main(normalized_protein_dict, q1, q2)
print_pair_score_dict(angle_list_protein, normalized_protein_dict, q1, q2, input_type, outputFileName)
def get_all_predicted_relations_dict(hprd50_paper_dict, max_sentences):
all_predicted_relations_dict = {}
for key in hprd50_paper_dict:
found_relation_score_tuples_list = []
for relation in hprd50_paper_dict[key].possible_relations_Tnumber:
q1 = relation[0]
q2 = relation[1]
found_relation_score_tuple = ((q1, q2), 0)
if q1 == q2:
continue
query = queries.main(q1, q2)
ID_sentence_list = []
ID_sentence_list = find_cooccurrence_sents(hprd50_paper_dict[key],
query)
print 'ID_sentence_list: ', ID_sentence_list
if not ID_sentence_list:
found_relation_score_tuple = ((q1, q2), 0)
print found_relation_score_tuple
found_relation_score_tuples_list.append(
found_relation_score_tuple)
if ID_sentence_list:
sentences_with_score1 = Score1.rank_sentences(
ID_sentence_list, query, max_sentences)
sentences_with_score2 = Score2.main(sentences_with_score1,
query)
sorted_sentences_with_score2 = list(
sorted(sentences_with_score2,
key=operator.attrgetter('score'),
reverse=True))
#------------------------------ if sorted_sentences_with_score2:
#----------------- if len(sorted_sentences_with_score2) > 1:
#-------------------------------------------------- pass
#----------------------------------------------------- else:
for sentence_object in sorted_sentences_with_score2:
found_relation_score_tuple = (
(q1, q2), sentence_object.score,
sentence_object.order_in_abstract)
print found_relation_score_tuple
found_relation_score_tuples_list.append(
found_relation_score_tuple)
all_predicted_relations_dict[key] = found_relation_score_tuples_list
return all_predicted_relations_dict
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 main(q1, q2, articles, batch, input_type, outputFileName, dictType,
outputType, evaluation_mode, stemmed, model, text_file):
models = model.split(' ')
num_articles = int(articles)
query = queries.main(q1, q2)
q1_dict = {}
q2_dict = {}
q1_already_downloaded_ids = get_already_downloaded_ids(q1, models)
q2_already_downloaded_ids = get_already_downloaded_ids(q2, models)
q1_already_downloaded_file_path_list = get_already_downloaded_file_paths(
q1, models, num_articles)
q2_already_downloaded_file_path_list = get_already_downloaded_file_paths(
q2, models, num_articles)
q1_already_dl_slice = None
q2_already_dl_slice = None
q1_file_paths = None
q2_file_paths = None
# if num_articles <= len(q1_already_downloaded_file_path_list):
# q1_already_dl_slice = q1_already_downloaded_file_path_list[:num_articles]
# q1_dict = get_info_from_interaction_xml(q1_already_dl_slice)
# else:
if num_articles * 100 <= len(q1_already_downloaded_file_path_list):
q1_already_dl_slice = q1_already_downloaded_file_path_list[:
num_articles]
q1_dict = get_info_from_interaction_xml(q1_already_dl_slice)
else:
q1_id_list = pmids.main(query.q1, num_articles, query.q1_search_string,
evaluation_mode)
if len(q1_id_list) == len(q1_already_downloaded_file_path_list):
q1_dict = get_info_from_interaction_xml(
q1_already_downloaded_file_path_list)
else:
if batch == 'yes':
q1_file_paths = run_tees_batch(q1, q1_id_list, models,
text_file)
elif batch == 'no':
q1_file_paths = run_tees(q1, q1_id_list, models, text_file)
if not q1_file_paths:
q1_file_paths = q1_already_downloaded_file_path_list[:
num_articles]
q1_dict = get_info_from_interaction_xml(q1_file_paths)
if num_articles * 100 <= len(q2_already_downloaded_file_path_list):
q2_already_dl_slice = q2_already_downloaded_file_path_list[:
num_articles]
q2_dict = get_info_from_interaction_xml(q2_already_dl_slice)
else:
q2_id_list = pmids.main(query.q2, num_articles, query.q2_search_string,
evaluation_mode)
if len(q2_id_list) == len(q2_already_downloaded_file_path_list):
q2_dict = get_info_from_interaction_xml(
q2_already_downloaded_file_path_list)
else:
if batch == 'yes':
q2_file_paths = run_tees_batch(q2, q2_id_list, models,
text_file)
elif batch == 'no':
q2_file_paths = run_tees(q2, q2_id_list, models, text_file)
if not q2_file_paths:
q2_file_paths = q2_already_downloaded_file_path_list[:
num_articles]
q2_dict = get_info_from_interaction_xml(q2_file_paths)
if q1_already_dl_slice:
q1_num_docs_processed = len(q1_already_dl_slice)
elif q1_file_paths:
q1_num_docs_processed = len(q1_file_paths)
else:
q1_num_docs_processed = len(q1_already_downloaded_file_path_list)
if q2_already_dl_slice:
q2_num_docs_processed = len(q2_already_dl_slice)
elif q2_file_paths:
q2_num_docs_processed = len(q2_file_paths)
else:
q2_num_docs_processed = len(q2_already_downloaded_file_path_list)
print q1, 'num_docs_processed', q1_num_docs_processed
print q2, 'num_docs_processed', q2_num_docs_processed
num_docs_processed = [q1_num_docs_processed, q2_num_docs_processed]
return_dict_s = []
if dictType == 'all':
all_words_dict = get_all_words_dict(q1, q2, q1_dict, q2_dict)
normalized_all_words_dict = normalize_dict(all_words_dict, query,
stemmed)
return_dict_s.append(normalized_all_words_dict)
if len(normalized_all_words_dict[query.q1.lower()]) < 1 or len(
normalized_all_words_dict[query.q2.lower()]) < 1:
angle_list = [90.00]
else:
angle_list = Cosine_Sim.main(normalized_all_words_dict, q1, q2)
if dictType == 'protein':
query_dicts = [q1_dict, q2_dict]
combined_dict = combine_dictionaries(query_dicts)
normalized_protein_dict = normalize_dict(combined_dict, query, stemmed)
return_dict_s.append(normalized_protein_dict)
if len(normalized_protein_dict[query.q1.lower()]) < 1 or len(
normalized_protein_dict[query.q2.lower()]) < 1:
angle_list = [90.00]
else:
angle_list = Cosine_Sim.main(normalized_protein_dict, q1, q2)
return angle_list, return_dict_s, num_docs_processed
def get_results_pack(self, pack, dbvar, event_string, ignore_numbers):
self.log("Start results_pack generation.")
need_mirror = False
compare_days_str = pack["result_options"]["compare_to_days"]
try:
compare_int = int(compare_days_str)
except ValueError:
self.bug(
"Cannot convert compare_to_days value: {} into int.".format(
compare_days_str))
else:
if compare_int > 0:
need_mirror = True
agg_len = pack["result_options"]["aggregation_period"]
agg_type = pack["result_options"]["aggregation_type"]
# COLLECT PRIME DATA
date_list = []
m_datelist = []
list_of_plot_tuples = []
date_list, result_dict = queries.main(pack,
dbvar,
ignore_numbers=ignore_numbers)
date_list = [chunk[0] for chunk in self.get_chunks(date_list, agg_len)]
list_of_plot_tuples = self.generate_list_of_plot_tuples(
result_dict, list_of_plot_tuples, agg_len, agg_type)
if pack["result_options"]["use_new_breakdowns"]:
breakdown_keys = None
else:
breakdown_keys = list(result_dict["lines"].keys())
# COLLECT MIRROR DATA IF NEEDED
if need_mirror:
pack["data_filters"]["start_datetime"] = (
pack["data_filters"]["start_datetime"] -
datetime.timedelta(compare_int))
pack["data_filters"]["end_datetime"] = (
pack["data_filters"]["end_datetime"] -
datetime.timedelta(compare_int))
m_datelist, m_resultdict = queries.main(
pack,
dbvar,
breakdown_keys=breakdown_keys,
ignore_numbers=ignore_numbers)
m_datelist = [
chunk[0] for chunk in self.get_chunks(m_datelist, agg_len)
]
list_of_plot_tuples = self.generate_list_of_plot_tuples(
m_resultdict,
list_of_plot_tuples,
agg_len,
agg_type,
is_mirror=True)
self.log("Completed request_pack generation.")
# print(list_of_plot_tuples)
return date_list, m_datelist, list_of_plot_tuples
def main(q1, q2, articles, batch, input_type, outputFileName, dictType, outputType, evaluation_mode, stemmed, model, text_file):
models = model.split(' ')
num_articles = int(articles)
query = queries.main(q1,q2)
q1_dict = {}
q2_dict = {}
q1_already_downloaded_ids = get_already_downloaded_ids(q1, models)
q2_already_downloaded_ids = get_already_downloaded_ids(q2, models)
q1_already_downloaded_file_path_list = get_already_downloaded_file_paths(q1, models, num_articles)
q2_already_downloaded_file_path_list = get_already_downloaded_file_paths(q2, models, num_articles)
q1_already_dl_slice = None
q2_already_dl_slice = None
q1_file_paths = None
q2_file_paths = None
# if num_articles <= len(q1_already_downloaded_file_path_list):
# q1_already_dl_slice = q1_already_downloaded_file_path_list[:num_articles]
# q1_dict = get_info_from_interaction_xml(q1_already_dl_slice)
# else:
if num_articles * 100 <= len(q1_already_downloaded_file_path_list):
q1_already_dl_slice = q1_already_downloaded_file_path_list[:num_articles]
q1_dict = get_info_from_interaction_xml(q1_already_dl_slice)
else:
q1_id_list = pmids.main(query.q1, num_articles, query.q1_search_string, evaluation_mode)
if len(q1_id_list) == len(q1_already_downloaded_file_path_list):
q1_dict = get_info_from_interaction_xml(q1_already_downloaded_file_path_list)
else:
if batch == 'yes':
q1_file_paths = run_tees_batch(q1, q1_id_list, models, text_file)
elif batch == 'no':
q1_file_paths = run_tees(q1, q1_id_list, models, text_file)
if not q1_file_paths:
q1_file_paths = q1_already_downloaded_file_path_list[:num_articles]
q1_dict = get_info_from_interaction_xml(q1_file_paths)
if num_articles * 100 <= len(q2_already_downloaded_file_path_list):
q2_already_dl_slice = q2_already_downloaded_file_path_list[:num_articles]
q2_dict = get_info_from_interaction_xml(q2_already_dl_slice)
else:
q2_id_list = pmids.main(query.q2, num_articles, query.q2_search_string, evaluation_mode)
if len(q2_id_list) == len(q2_already_downloaded_file_path_list):
q2_dict = get_info_from_interaction_xml(q2_already_downloaded_file_path_list)
else:
if batch == 'yes':
q2_file_paths= run_tees_batch(q2, q2_id_list, models, text_file)
elif batch == 'no':
q2_file_paths= run_tees(q2, q2_id_list, models, text_file)
if not q2_file_paths:
q2_file_paths = q2_already_downloaded_file_path_list[:num_articles]
q2_dict = get_info_from_interaction_xml(q2_file_paths)
if q1_already_dl_slice:
q1_num_docs_processed = len(q1_already_dl_slice)
elif q1_file_paths:
q1_num_docs_processed = len(q1_file_paths)
else:
q1_num_docs_processed = len(q1_already_downloaded_file_path_list)
if q2_already_dl_slice:
q2_num_docs_processed = len(q2_already_dl_slice)
elif q2_file_paths:
q2_num_docs_processed = len(q2_file_paths)
else:
q2_num_docs_processed = len(q2_already_downloaded_file_path_list)
print q1, 'num_docs_processed', q1_num_docs_processed
print q2, 'num_docs_processed', q2_num_docs_processed
num_docs_processed = [q1_num_docs_processed,q2_num_docs_processed]
return_dict_s = []
if dictType == 'all':
all_words_dict = get_all_words_dict(q1, q2, q1_dict, q2_dict)
normalized_all_words_dict = normalize_dict(all_words_dict, query, stemmed)
return_dict_s.append(normalized_all_words_dict)
if len(normalized_all_words_dict[query.q1.lower()]) < 1 or len(normalized_all_words_dict[query.q2.lower()]) < 1:
angle_list = [90.00]
else:
angle_list = Cosine_Sim.main(normalized_all_words_dict, q1, q2)
if dictType == 'protein':
query_dicts = [q1_dict, q2_dict]
combined_dict = combine_dictionaries(query_dicts)
normalized_protein_dict = normalize_dict(combined_dict, query, stemmed)
return_dict_s.append(normalized_protein_dict)
if len(normalized_protein_dict[query.q1.lower()]) < 1 or len(normalized_protein_dict[query.q2.lower()]) < 1:
angle_list = [90.00]
else:
angle_list = Cosine_Sim.main(normalized_protein_dict, q1, q2)
return angle_list, return_dict_s, num_docs_processed
def send_query(self):
queries.main(arg[1:])
return True
