How to split the pandas dataframe column result?

Question

I try to split the text column in df['text'], but paddleocr output the text with conf, so I don't know how to separate it into two part, I tried using lstrip but didnt work. The result as follow:

ID                               Text
0                     (7-Eleven Malaysia, 0.9709457)
1                             (Sdn.Bhd., 0.97443557)
2                                (ELEVEn, 0.9140763)
3               (LevelA,Podfum BfockPla, 0.88208693)
4     (No.12Jalan lmbi.55100Kuaia Lumpur, 0.9308618)
5           (#0463 Tmn Me]ur Ampang SEL, 0.94200194)
6                   (Tel No.:60321142463, 0.9128232)
7                   (WELCOME TO 7-ELEVEN, 0.9357082)
8         (18/04/202121:28RCPT01-288319, 0.97587883)
9      (Staff Name: DASHATARAN A/L RAJAM, 0.9589798)
10                   (Coke Vanilla500ml, 0.98303896)
11                                 (3.20, 0.9908478)

Because if in this part I can't do then follow part the text clean will remove the () and combine text with conf as following:

TEXT
7elevenmalaysia09528224
sdnbhd12009405007
eleven0941575   

Here is the code:

from tqdm import tqdm
import os
import cv2
import re

imgPaths = glob('C:/Users/23573/Desktop/img/*.jpg')

dfs = []
for imgPath in tqdm(imgPaths,desc='Receipt'):   
    _, filename = os.path.split(imgPath) 
    ocr = PaddleOCR(lang='en')   
    result = ocr.ocr(imgPath)
    img_df = pd.DataFrame(result, columns=['bbox','text'])
    print(img_df['text'])

    img_df['img_id'] = filename
    
paddleocr_df = pd.concat(dfs)

Because I can't clean that (result) format as I wanted. The paddle ocr output, text was stick with conf. Result is a list format I can't split. df['text'] is a tuple format I can't lstrip and all this I can't use str and split.

My expected result as:

ID                 TEXT                 conf
0              7-Eleven Malaysia        0.9709457
1              Sdn.Bhd                  0.97443557
2              ELEVEn                   0.9140763

Answer 1

df[['text', 'num']] = df['Text'].str.split(',', 1, expand=True)

or this one :

df = pd.DataFrame(df.row.str.split(',',1).tolist(),
                                 columns = ['text','num'])

or this :

df.join(df['Text'].str.split(',', 1, expand=True).rename(columns={0:'text', 1:'num'}))