app.py

# app.py
from transformers import pipeline
import gradio as gr

# Load your fine-tuned model from Hugging Face
classifier = pipeline("text-classification", model="Ahmedhany1/my-finetuned-distilbert")

# Optional: map label IDs to readable names (if your model outputs LABEL_0, etc.)
id2label = {
    "LABEL_0": "Negative",
    "LABEL_1": "Neutral",
    "LABEL_2": "Positive"
}

# Define the prediction function
def predict_sentiment(text):
    result = classifier(text)[0]
    label = id2label.get(result['label'], result['label'])
    confidence = round(result['score'], 4)
    return f"Sentiment: {label} (Confidence: {confidence})"

# Gradio interface
demo = gr.Interface(
    fn=predict_sentiment,
    inputs=gr.Textbox(lines=3, placeholder="Enter a tweet here..."),
    outputs="text",
    title="Twitter Sentiment Analyzer Lab Project",
    description="Fine-tuned BERT model for classifying tweets as Positive, Neutral, or Negative."
)

demo.launch()