app.py

import gradio as gr
from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch
import numpy as np

# Load model and tokenizer from Hugging Face Hub
model_name = "Nicolettem/bert-sentiment-nic"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Label mapping (match your label encoder)
label_map = {0: "negative", 1: "neutral", 2: "positive"}

def predict_sentiment(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=128)
    with torch.no_grad():
        outputs = model(**inputs)
    logits = outputs.logits
    predicted_class_id = int(torch.argmax(logits, dim=-1))
    return label_map.get(predicted_class_id, "Unknown")

# Gradio interface
demo = gr.Interface(
    fn=predict_sentiment,
    inputs=gr.Textbox(lines=3, placeholder="Enter airline feedback here..."),
    outputs="text",
    title="Airline Sentiment Classifier",
    description="Enter a sentence about an airline, and this model predicts the sentiment: positive, neutral, or negative."
)

demo.launch()