app.py

import streamlit as st
from transformers import AutoModelForSequenceClassification, AutoTokenizer

# Replace with your actual model ID or access token from Hugging Face Hub
model_id = "your-model-id"

# Load the pre-trained sentiment analysis model and tokenizer from Hugging Face Hub
model = AutoModelForSequenceClassification.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)

def classify_sentiment(text):
  """
  Function to preprocess text, make predictions using the loaded model,
  and return the predicted sentiment.
  """
  # Preprocess text (tokenization)
  encoded_text = tokenizer(text, return_tensors="pt")

  # Make prediction using the loaded model
  output = model(**encoded_text)
  predictions = output.logits.argmax(-1)

  # Map predicted class label to sentiment category
  sentiment_mapping = {0: "Negative", 1: "Neutral", 2: "Positive"}
  sentiment = sentiment_mapping[predictions.item()]

  return sentiment

def main():
  """
  Streamlit app for sentiment analysis
  """
  st.title("Sentiment Analysis App")
  text_input = st.text_input("Enter text to analyze:")

  if text_input:
      sentiment = classify_sentiment(text_input)
      st.write(f"Predicted Sentiment: {sentiment}")

if __name__ == "__main__":
  main()