df['line'].iloc[:2981] = 'train' df['line'].iloc[2982:] = 'test' with open('job_post_01.txt', 'a') as f: dfAsString = df.to_string(header=False, index=True) f.write(dfAsString) f.close() data = pd.read_csv('job_post_01.csv') df = data.sample(frac = 1).reset_index(drop = True) doc_name_list = df.values.tolist() doc_train_list = df.iloc[:2981].values.tolist() doc_test_list = df.iloc[2982:].values.tolist()