app.py

# Import required libraries
import gradio as gr
from transformers import pipeline

def create_sentiment_analyzer():
    """Initialize the BERT sentiment analyzer"""
    return pipeline("sentiment-analysis", model="zavora/bert-sentiment-imdb")

def analyze_sentiment(text, classifier):
    """
    Analyze sentiment of input text using BERT model
    Returns sentiment and confidence score
    """
    try:
        if not text.strip():
            return "Please enter some text"
            
        result = classifier(text)[0]
        label = result['label']
        confidence = result['score']
        
        sentiment = "Positive" if label == "LABEL_1" else "Negative"
        # Format the output
        return f"Sentiment: {sentiment}\nConfidence: {confidence:.2%}"
        
    except Exception as e:
        return f"Error: {str(e)}"

# Create and cache the classifier
classifier = create_sentiment_analyzer()

# Create the Gradio interface
demo = gr.Interface(
    fn=lambda text: analyze_sentiment(text, classifier),
    inputs=[
        gr.Textbox(
            lines=4,
            placeholder="Enter your movie review here...",
            label="Movie Review"
        )
    ],
    outputs=[
        gr.Textbox(
            label="Analysis Result"
        )
    ],
    title="Movie Review Sentiment Analysis",
    description="""This app uses a BERT model fine-tuned on IMDB movie reviews to analyze sentiment.
                   Enter your movie review and get an analysis of whether it's positive or negative.""",
    examples=[
        ["This movie was absolutely fantastic! The acting was superb and the plot kept me engaged throughout."],
        ["I couldn't sit through this movie. The plot was confusing and the acting was terrible."],
        ["While the movie had some good moments, overall it was just average."]
    ],
    theme=gr.themes.Soft()
)

# Launch the app
if __name__ == "__main__":
    demo.launch()