start = time.time()
y_test = []
y_pred = []
for j in range(len(data_test[i]["tweet"])):
prediction = nb.predict(data_test[i]["tweet"][j],
data_test[i]["target"][j])
y_test.append(data_test[i]["target"][j])
y_pred.append(prediction)
print("nb pred")
print(time.time() - start)
start = time.time()
cm = ConfusionMatrix()
accuracy, precision, recall, fmeasure = cm.score(y_test, y_pred)
print("Stopwords")
print(stopwords)
print("\nRemoved Stopwords")
print(removed_words)
print("\nAccuracy : {}".format(accuracy))
print("Precision : {}".format(precision))
print("Recall : {}".format(recall))
print("FMeasure : {}".format(fmeasure))
# df = pd.DataFrame({'X':x_array,'Y':y_array,'L':l_array,'K-Fold':kfold_per_combination,'Accuracy':list_acc,'Precision':list_prec,'Recall':list_recall,'F-Measure':list_fmeasure,'Fold Accuracy':fold_accuracy,'Fold Precision':fold_precision,'Fold Recall':fold_recall,'Fold F-Measure':fold_fmeasure})
# print(df)
# df.to_excel(r'cobabarunih.xlsx', index = False, header=True)
tfidf = weight.get_tf_idf_weighting()
idf = weight.get_idf()
nb = NBMultinomial()
nb.fit(new_cleaned_data, new_terms, data_train[i]["target"], stopwords,
idf, tfidf)
for j in range(len(data_test[i]["tweet"])):
print("Test ke " + str(j))
prediction = nb.predict(data_test[i]["tweet"][j],
data_test[i]["target"][j])
y_test.append(data_test[i]["target"][j])
y_pred.append(prediction)
cm = ConfusionMatrix()
accuracy, accuracy_each_class, precision_each_class, recall_each_class, fmeasure_each_class = cm.score(
y_test, y_pred)
acc_neg.append(accuracy_each_class[0])
acc_net.append(accuracy_each_class[1])
acc_pos.append(accuracy_each_class[2])
prec_neg.append(precision_each_class[0])
prec_net.append(precision_each_class[1])
prec_pos.append(precision_each_class[2])
recall_neg.append(recall_each_class[0])
recall_net.append(recall_each_class[1])
recall_pos.append(recall_each_class[2])
fmeasure_neg.append(fmeasure_each_class[0])
fmeasure_net.append(fmeasure_each_class[1])
fmeasure_pos.append(fmeasure_each_class[2])
acc_per_fold.append(accuracy)