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.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
model = create_model()
model.load_weights("5e-5 0.1.h5")
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']:
for q in par["qas"]:
pbar.update(1)
if q["is_impossible"] is False:
result = self.searcher.simpleSearch(q["question"], BM25Similarity())
ids = []
if(result == []):
output_file_1.write('"'+str(q['id'])+'": "",\n')
continue
content = ""
tab = ['']
tab.append(q["question"])
tab.pop(0)
for i in range(len(result)):
hitDoc = self.searcher.searcher.doc(result[i].doc)
content = hitDoc.get("content_section")
tab.append(str(content))
ids.append(hitDoc.get("id_section"))
inputs = []
for i in range(1, len(tab)):
inputs.append([tab[0],tab[i]])
# tokenization
squad_examples = []
for i in inputs:
question = i[0]
context = i[1]
squad_eg = Example(q["question"], context)
squad_eg.preprocess()
squad_examples.append(squad_eg)
dataset_dict = {"input_ids": [],
"token_type_ids": [],
"attention_mask": [],}
for item in squad_examples:
if item.skip == False:
for key in dataset_dict:
dataset_dict[key].append(getattr(item, key))
for key in dataset_dict:
dataset_dict[key] = np.array(dataset_dict[key])
x = [dataset_dict["input_ids"],
dataset_dict["token_type_ids"],
dataset_dict["attention_mask"]]
y_pred = model.predict(x)
sorted_indexes = sorted(range(len(y_pred)), key=lambda k: y_pred[k], reverse=True)
r = 1
for i in sorted_indexes:
output_file_1.write(
q["id"] + " Q0 " + str(ids[i]) + " " + str(r) + " " + str(y_pred[i][0]) + " STANDARD\n")
r += 1
print("==> Results 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")
