app.py

#importing the necessary libraries
import gradio as gr
import numpy as np
import pandas as pd
import re
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

#Defining the labels of the models
labels = ["business", "science","health", "world", "sport", "politics", "entertainment", "tech"]

#Defining the models and tokenuzer
model_name = "valurank/finetuned-distilbert-news-article-categorization"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

"""
#Reading in the text file
def read_in_text(url):
  with open(url, 'r') as file:
    article = file.read()
      
    return article
"""

def clean_text(raw_text):
  text = raw_text.encode("ascii", errors="ignore").decode(
          "ascii"
    )  # remove non-ascii, Chinese characters
    
  text = re.sub(r"\n", " ", text)
  text = re.sub(r"\n\n", " ", text)
  text = re.sub(r"\t", " ", text)
  text = text.strip(" ")
  text = re.sub(
        " +", " ", text
    ).strip()  # get rid of multiple spaces and replace with a single

  text = re.sub(r"Date\s\d{1,2}\/\d{1,2}\/\d{4}", "", text) #remove date
  text = re.sub(r"\d{1,2}:\d{2}\s[A-Z]+\s[A-Z]+", "", text) #remove time
    
  return text
 
#Defining a function to get the category of the news article   
def get_category(text):
  text = clean_text(text)

  input_tensor = tokenizer.encode(text, return_tensors="pt", truncation=True)
  logits = model(input_tensor).logits

  softmax = torch.nn.Softmax(dim=1)
  probs = softmax(logits)[0]
  probs = probs.cpu().detach().numpy()
  max_index = np.argmax(probs)
  emotion = labels[max_index]
    
  return emotion
  
#Creating the interface for the radio app
demo = gr.Interface(get_category, inputs=gr.Textbox(label="Drop your articles here"),
                    outputs = "text",
                    title="News Article Categorization")


#Launching the gradio app
if __name__ == "__main__":
  demo.launch(debug=True)