prediction = []
for r in reviews_bigramtest:
test_labels.append(r[1])
prediction.append(classifier.classify(r[0]))
print("Results....")
print(accuracy_score(test_labels, prediction))
print(classification_report(test_labels, prediction))
#load reviews
reviews = loadReviews("imdbMovieReviews3.txt")
#bigram NV without title
processedReviews = textProcessing(reviews, False, 3)
result = generateTrainingTestSet(processedReviews, False)
reviews_training = result[0]
reviews_test = result[1]
ngramNaiveBayesClassifier(reviews_training, reviews_test)
#bigram NV with title
processedReviews = textProcessing(reviews, False, 3)
result = generateTrainingTestSet(processedReviews, True)
reviews_training = result[0]
reviews_test = result[1]
ngramNaiveBayesClassifier(reviews_training, reviews_test)
t0 = time.time()
classifier_liblinear.fit(train_vectors, train_labels)
t1 = time.time()
prediction_liblinear = classifier_liblinear.predict(test_vectors)
t2 = time.time()
time_liblinear_train = t1-t0
time_liblinear_predict = t2-t1
# Print results in tabular format
print("Results for LinearSVC()")
print("Training time: %fs; Prediction time: %fs" % (time_liblinear_train, time_liblinear_predict))
print(accuracy_score(test_labels, prediction_liblinear))
print(classification_report(test_labels, prediction_liblinear))
#load reviews
reviews = loadReviews("imdbMovieReviews3.txt")
#SVM without title
result = generateTrainingTestSet(reviews, False)
reviews_training = result[0]
reviews_test = result[1]
print("SVM without Review title....")
linearSVMClassifier(reviews_training, reviews_test)
#SVM with title
result = generateTrainingTestSet(reviews, True)
reviews_training = result[0]
reviews_test = result[1]
print("SVM with Review title....")
linearSVMClassifier(reviews_training, reviews_test)
