knn = KNN(tf_idf_calculator.results, k, metric)
# confusion_matrix[A][B] = quantas vezes um documento da classe A foi atribuído à classe B
topics = ['baseball', 'christian', 'guns']
confusion_matrix = {topic:{t:0 for t in topics} for topic in topics}
print_log = False
i = 0
ytrue = []
ypred = []
for topic in topics:
for doc in reader.test[topic]:
ytrue.append(topic)
# classifica os documentos de teste
words = parser.process_sent(doc)
query = tf_idf_calculator.generate_tf_vector(words)
result = knn.classify(query)
confusion_matrix[topic][result] += 1
ypred.append(result)
i += 1
if print_log:
print('')
print(i)
print(doc)
print(words)
print(query)
print(result)
# e imprime os resultados
print('#'*40)
s = '#'*10 + (' K=%d || dist=%s ' % (k, metric)) + '#'*10
