app.py

# Import necessary libraries 
import streamlit as st
import pandas as pd
import numpy as np
import pandas as pd
import os
import nltk
nltk.download('stopwords')
nltk.download('punkt')
nltk.download('averaged_perceptron_tagger')
import pandas as pd
from collections import Counter
import string
import numpy as np
import re
import pickle
import os
# os.chdir(bert_dir)
from agent.target_extraction.target_extractor import TargetExtractor
#os.chdir('/content/')
from pathos.multiprocessing import ProcessingPool as Pool
import itertools
from time import time
import time
import itertools
import nltk
nltk.download('wordnet')
nltk.download('omw-1.4')
device="cpu"
from gensim.models import word2vec


project_dir='/content'

# # Set a title 
# import torch

st.title("Get entity and relations")

# # Add text to the app 
uploaded_file = st.file_uploader("Choose a file")


if uploaded_file is not None:
  df = pd.read_csv(uploaded_file)
  with open(os.path.join("data",uploaded_file.name),"wb") as f: 
      f.write(uploaded_file.getbuffer() )   
  st.write(df)
  print(os.path.join("data",uploaded_file.name))
  
if(st.button("Submit")):
    with st.spinner('Wait for extraction'):
        te=TargetExtractor("mobile",os.path.join("data",uploaded_file.name), "reviewText")
        te.save_product_representation(project_dir)