a1

a1

!wget https://raw.githubusercontent.com/Tony607/Keras-Text-Transfer-Learning/master/train_5500.txt
!wget https://raw.githubusercontent.com/Tony607/Keras-Text-Transfer-Learning/master/test_data.txt



def get_dataframe(filename):
    lines = open(filename, 'r').read().splitlines()
    data = []
    for i in range(0, len(lines)):
        label = lines[i].split(' ')[0]
        label = label.split(":")[0]
        text = ' '.join(lines[i].split(' ')[1:])
        text = re.sub('[^A-Za-z0-9 ,\?\'\"-._\+\!/\`@=;:]+', '', text)
        data.append([label, text])

    df = pd.DataFrame(data, columns=['label', 'text'])
    df.label = df.label.astype('category')
    return df

df_train = get_dataframe('train_5500.txt')