class qrels:
"""
A class to create the qrels of the questions for SQUAD dataset.
"""
def __init__(self, index_dir):
self.searchObject = Searcher(index_dir)
def get_id_section(self, pair):
"""
This is the function that returns the id of the passage that is similar to the context.
:param index_dir: the folder where the dataset index is stored.
:param input_query: the query that represents the context.
:return:
"""
result = self.searchObject.pairSearch(pair, BM25Similarity())
id = None
for i in range(len(result)):
hitDoc = self.searchObject.searcher.doc(result[i].doc)
id = hitDoc.get("id_section")
content = hitDoc.get("content_section")
if id != "":
break
return id, content
def process(self, input_file, output_dir):
"""
This is the main function that creates the qrels file.
:param input_file: the file to process.
:param index_dir: the folder where the dataset index is stored.
:param output_dir: the folder where to store the qrels file.
:return:
"""
num_lines = 0
with open(input_file, encoding="utf-8") as json_file:
data = json.load(json_file)
for p in data['data']:
for par in p['paragraphs']:
num_lines += 1
output_file = open(output_dir + "/qrels.txt", 'a+', encoding="utf-8")
with tqdm(total=num_lines) as pbar:
with open(input_file, encoding="utf-8") as json_file:
data = json.load(json_file)
for p in data['data']:
for par in p['paragraphs']:
pbar.update(1)
psg_id, content = self.get_id_section(
(p['title'], par["context"]))
# print("Content: "+content+"\n")
#similarity = round(len(set(par["context"]) & set(content)) / len(set(par["context"])), 2)
for q in par["qas"]:
qst_id = q["id"]
if q["is_impossible"] is False:
output_file.write(qst_id + " 0 " + psg_id +
" 1 \n")
print("==> Qrels successfully created.\n")
class ResultsGenerator:
def __init__(self, index_dir):
self.searcher = Searcher(index_dir)
def get_id_section(self, request):
idList = list()
for i in range(len(request)):
hitDoc = self.searcher.searcher.doc(request[i].doc)
idList.append(hitDoc.get("id_section"))
return idList
def process(self, input_file, index_dir, output_dir):
output_file_1 = open(output_dir + "/results_BM25_1.txt",
'a+',
encoding="utf-8")
output_file_2 = open(output_dir + "/results_BM25_2.txt",
'a+',
encoding="utf-8")
output_file_3 = open(output_dir + "/results_BM25_3.txt",
'a+',
encoding="utf-8")
output_file_4 = open(output_dir + "/results_BM25_4.txt",
'a+',
encoding="utf-8")
output_file_5 = open(output_dir + "/results_VSM_1.txt",
'a+',
encoding="utf-8")
output_file_6 = open(output_dir + "/results_VSM_2.txt",
'a+',
encoding="utf-8")
output_file_7 = open(output_dir + "/results_VSM_3.txt",
'a+',
encoding="utf-8")
output_file_8 = open(output_dir + "/results_VSM_4.txt",
'a+',
encoding="utf-8")
num_lines = 0
with open(input_file, encoding="utf-8") as json_file:
data = json.load(json_file)
for p in data['data']:
for par in p['paragraphs']:
for q in par["qas"]:
num_lines += 1
with tqdm(total=num_lines) as pbar:
with open(input_file, encoding="utf-8") as json_file:
data = json.load(json_file)
for p in data['data']:
title = p["title"]
for par in p['paragraphs']:
for q in par["qas"]:
pbar.update(1)
if q["is_impossible"] is False:
question_content_s_BM25 = self.searcher.simpleSearch(
q["question"], BM25Similarity())
id_question_content_s_BM25 = self.get_id_section(
question_content_s_BM25)
question_title_content_s_BM25 = self.searcher.pairSearch(
[title, q["question"]], BM25Similarity())
id_question_title_content_s_BM25 = self.get_id_section(
question_title_content_s_BM25)
question_content_m_BM25 = self.searcher.multiFieldsSearch(
q["question"], BM25Similarity())
id_question_content_m_BM25 = self.get_id_section(
question_content_m_BM25)
question_title_content_m_BM25 = self.searcher.multiFieldsPairSearch(
[title, q["question"]], BM25Similarity())
id_question_title_content_m_BM25 = self.get_id_section(
question_title_content_m_BM25)
question_content_s_TDF = self.searcher.simpleSearch(
q["question"], ClassicSimilarity())
id_question_content_s_TDF = self.get_id_section(
question_content_s_TDF)
question_title_content_s_TDF = self.searcher.pairSearch(
[title, q["question"]],
ClassicSimilarity())
id_question_title_content_s_TDF = self.get_id_section(
question_title_content_s_TDF)
question_content_m_TDF = self.searcher.multiFieldsSearch(
q["question"], ClassicSimilarity())
id_question_content_m_TDF = self.get_id_section(
question_content_m_TDF)
question_title_content_m_TDF = self.searcher.multiFieldsPairSearch(
[title, q["question"]],
ClassicSimilarity())
id_question_title_content_m_TDF = self.get_id_section(
question_title_content_m_TDF)
for i in range(len(question_content_s_BM25)):
output_file_1.write(
q["id"] + " Q0 " +
str(id_question_content_s_BM25[i]) +
" " + str(i + 1) + " " +
str(question_content_s_BM25[i].score) +
" STANDARD\n")
for i in range(
len(question_title_content_s_BM25)):
output_file_2.write(
q["id"] + " Q0 " +
str(id_question_title_content_s_BM25[i]
) + " " + str(i + 1) + " " +
str(question_title_content_s_BM25[i].
score) + " STANDARD\n")
for i in range(len(question_content_m_BM25)):
output_file_3.write(
q["id"] + " Q0 " +
str(id_question_content_m_BM25[i]) +
" " + str(i + 1) + " " +
str(question_content_m_BM25[i].score) +
" STANDARD\n")
for i in range(
len(question_title_content_m_BM25)):
output_file_4.write(
q["id"] + " Q0 " +
str(id_question_title_content_m_BM25[i]
) + " " + str(i + 1) + " " +
str(question_title_content_m_BM25[i].
score) + " STANDARD\n")
for i in range(len(question_content_s_TDF)):
output_file_5.write(
q["id"] + " Q0 " +
str(id_question_content_s_TDF[i]) +
" " + str(i + 1) + " " +
str(question_content_s_TDF[i].score) +
" STANDARD\n")
for i in range(
len(question_title_content_s_TDF)):
output_file_6.write(
q["id"] + " Q0 " +
str(id_question_title_content_s_TDF[i])
+ " " + str(i + 1) + " " +
str(question_title_content_s_TDF[i].
score) + " STANDARD\n")
for i in range(len(question_content_m_TDF)):
output_file_7.write(
q["id"] + " Q0 " +
str(id_question_content_m_TDF[i]) +
" " + str(i + 1) + " " +
str(question_content_m_TDF[i].score) +
" STANDARD\n")
for i in range(
len(question_title_content_m_TDF)):
output_file_8.write(
q["id"] + " Q0 " +
str(id_question_title_content_m_TDF[i])
+ " " + str(i + 1) + " " +
str(question_title_content_m_TDF[i].
score) + " STANDARD\n")
print("==> Results successfully created.\n")