def get_best_indices(list, sin_val):
''' The function takes on single row and finds out the best indexes according to similarity distance. The similarity values used are
Euclidean distance, Manhattan distance, Minkowski distance, Cosine distance and Jaccard distance.
It returns a dictionary of list'''
### local optima saves a dictionary where dictionary is like { distance_type: [best_distance_value, best_lowest_index, best_upper_index] }
local_optima = {
"Euclidean": [9999999999, 9999999, 99999999],
"Manhattan": [9999999999, 9999999, 99999999],
"Minkowski": [9999999999, 9999999, 99999999],
"Cosine": [9999999999, 9999999, 99999999],
"Jaccard": [9999999999, 9999999, 99999999]
}
measures = Similarity() ### Calling Similarity class
size = len(sin_val) ### size of sine value list which is 40
for i in range(len(list) - size):
### Euclidean Portion
val = measures.euclidean_distance(list[i:i + size], sin_val)
if val <= local_optima["Euclidean"][0]:
local_optima["Euclidean"] = [val, i, i + size]
### Manhattan Portion
val = measures.manhattan_distance(list[i:i + size], sin_val)
if val <= local_optima["Manhattan"][0]:
local_optima["Manhattan"] = [val, i, i + size]
### Minkowski Portion
val = measures.minkowski_distance(list[i:i + size], sin_val, 3)
if val <= local_optima["Minkowski"][0]:
local_optima["Minkowski"] = [val, i, i + size]
### Cosine Portion
val = measures.cosine_similarity(list[i:i + size], sin_val)
if val <= local_optima["Cosine"][0]:
local_optima["Cosine"] = [val, i, i + size]
### Jaccard Portion
val = measures.jaccard_similarity(list[i:i + size], sin_val)
if val <= local_optima["Jaccard"][0]:
local_optima["Jaccard"] = [val, i, i + size]
return local_optima
values = predictions[:, 1]
answer = x[np.where(values == max(values)), 1]
text = str(answer)
encoding = tokenizer.encode_plus(qst, text, max_length=256)
input_ids, token_type_ids = encoding["input_ids"], encoding[
"token_type_ids"]
start_scores, end_scores = modelExtractor(torch.tensor([input_ids]),
token_type_ids=torch.tensor(
[token_type_ids]))
all_tokens = tokenizer.convert_ids_to_tokens(input_ids)
a = ' '.join(
all_tokens[torch.argmax(start_scores):torch.argmax(end_scores) + 1])
cleaned_answer = a.replace(" ##", "")
txt_file.write("#################################### \n")
txt_file.write("#################################### \n")
txt_file.write("Question ====> \t" + row[0] + "\n")
txt_file.write("Réponse prédite ====> \t" + cleaned_answer + "\n")
txt_file.write("La vraie réponse ====> \t" + row[1] + "\n")
txt_file.write("Dice Similarity ====> \t" +
str(Similarity.dice_similarity(cleaned_answer, row[1])) +
"\n")
txt_file.write("Jaccard Similarity ====> \t" +
str(Similarity.jaccard_similarity(cleaned_answer, row[1])) +
"\n")
txt_file.write("#################################### \n")
searchObject.reader.close()
searchObject.directory.close()
tsv_file.close()
txt_file.close()
