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
for x in tf_idf.toarray()[0]:
print(x, end=",")
# count = sum([1 for x in tf_idf.toarray()[0] if x != 0])
# print(count)
# Query text
query_path = 'data\\test-bong-da-trong-nuoc.txt'
tf_idf_query = compute_tf_idf_query(query_path, dictionary, idf)
print(tf_idf_query[0])
count = sum([1 for x in tf_idf_query.toarray()[0] if x != 0])
print('\nquery keyword count: ' + str(count))
# calculate similarity between tf_idf_query with tf_idf of corpus
similarity = Similarity()
# similarities = similarity.cosine_similarity_sprase_matrix(tf_idf, tf_idf_query).flatten()
similarities = []
for tf_idf_e in tf_idf:
# print(tf_idf_e.toarray()[0])
similarities.append(
similarity.cosine_similarity(tf_idf_e.toarray()[0],
tf_idf_query.toarray()[0]))
# display similarity descending between query input with corpus
# sort similarity
similarities, files = zip(*sorted(zip(similarities, files), reverse=True))
print('\n10 file có độ tương đồng giảm dần:\n')
sim_re, files_res = similarities[:10], files[:10]
for i in range(len(files_res)):
print('%s %f' % (files_res[i], sim_re[i]))
