Snippets Collections
# remove punc, segment and stopword
def punc_jieba(text, sep = ' '):
#     stopword = stopwords(["zh"])
    text_punc = re.sub("[\s+\>\<\:\?\.\!\/_,$%^*(+\"\']+|[+——!,。?、~@#¥%……&*()!,❤。~《》:()【】「」?”“;:、【】╮╯▽╰╭★→「」]+".encode().decode("utf8"),
                        "",text)
    text_cut = sep.join(jieba.cut(text_punc, cut_all=False)).lower()
#     tokens = word_tokenize(text_cut)
#     clean_text = [word for word in tokens if not word in stopword]
    
    return text_cut
# mothod1
def stop_word(text):
    stopword = stopwords(['zh'])
    remove_stw = [word for word in text if not word in stopword]
    return remove_stw
df['text'] = df['text'].apply(stop_word)
# mothod2
stopword = stopwords(['zh'])
df['text'] = df['text'].apply(lambda x: ' '.join([word for word in x.split() if word not in (stopword)]))
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)
star

Fri Aug 13 2021 06:21:01 GMT+0000 (Coordinated Universal Time)

#python #pandas #column #nlp #chinese #trasim
star

Thu Aug 12 2021 07:11:15 GMT+0000 (Coordinated Universal Time)

#python #pandas #column #nlp #chinese #trasim

Save snippets that work with our extensions

Available in the Chrome Web Store Get Firefox Add-on Get VS Code extension