data preprocessing

code_0.py

imdb_dir = '../datasets/aclImdb/aclImdb'
train_dir = os.path.join(imdb_dir, 'train')
labels = list()
texts = list()

# Processing the labels of the raw IMDB data
for label_type in ['neg', 'pos']:
    dir_name = os.path.join(train_dir, label_type)
    for fname in os.listdir(dir_name):
        if fname[-4:] == '.txt':
            f = open(os.path.join(dir_name, fname))
            texts.append(f.read())
            f.close()
            if label_type == 'neg':
                labels.append(0)
            else:
                labels.append(1)