sudo pip install opencc
# if nt work, should clone project first
import pandas as pd
import numpy as np
# -*- coding: utf-8 -*-
import opencc
from opencc import OpenCC
df = pd.read_csv('training.csv').astype(str)
def tra_sim(text):
cc = OpenCC('tw2s')
sim = cc.convert(text)
return sim
df['sim_label'] = df['label'].apply(tra_sim)
df['sim_detail_label'] = df['detail_label'].apply(tra_sim)
df['sim_text'] = df['text'].apply(tra_sim)