pretrain_data.py

import tensorflow as tf
import torch as pt
import pandas as pd
import re
from t5_tokenizer_model import SentencePieceUnigramTokenizer
#from pretokenizer import atomwise_tokenizer
from tqdm import tqdm
from transformers import AutoTokenizer, T5Tokenizer, T5ForConditionalGeneration, T5Config
from tokenizers import Tokenizer
import numpy as np 


tokenizer = AutoTokenizer.from_pretrained("./")
dataset = pd.read_csv('./chemT5_data.csv')
train=pd.DataFrame(data=dataset)

for i, line in tqdm(enumerate(dataset['SMILES'])):
    print(i," "+line)
    line = tokenizer.encode(line)
    #print(line) 
    newLine=tokenizer.convert_ids_to_tokens(line)
    #print(newLine)
    #print(int(i/10))
    train.iloc[i]['SMILES']=newLine

#print(train[0:5])
train.to_csv('pretrain.csv',index=False)