app.py

import streamlit as st
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load the pre-trained model and tokenizer from Hugging Face
model_name = "tajuarAkash/test2"  # Replace with your Hugging Face model path 

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Title of the web app
st.title("Fraud Detection in Health Insurance Claims")

# Description of the app
st.write("This app predicts whether a health insurance claim is fraudulent based on the input data.")

# Create a text box for the user to input the generated sentence (feature for prediction)
input_text = st.text_area("Enter the claim description")

# Create a button to make predictions
if st.button('Predict Fraud'):
    if input_text:
        # Tokenize the input text
        inputs = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True, max_length=512)

        # Get model predictions
        with torch.no_grad():
            logits = model(**inputs).logits
        predicted_class = torch.argmax(logits, dim=-1).item()

        # Display the result
        if predicted_class == 1:
            st.write("This claim is predicted to be fraudulent.")
        else:
            st.write("This claim is predicted to be legitimate.")
    else:
        st.write("Please enter a claim description.")