Refactor sentiment prediction function for improved clarity and performance

app.py

@@ -1,3 +1,6 @@
+# This script creates a Gradio web app for sentiment analysis of movie reviews using a pre-trained BERT model.
+
+# Import necessary libraries
 from transformers import BertTokenizer, BertForSequenceClassification
 import torch
 import gradio as gr
@@ -19,7 +22,7 @@ def predict_sentiment(text):
     sentiment = "Positive 😊" if prediction == 1 else "Negative 😠"
     return f"{sentiment} (Confidence: {confidence * 100:.2f}%)", probs.detach().numpy()[0]
 
-# Plotting function
+# Plotting function for probabilities
 def plot_probs(probs):
     labels = ["Negative", "Positive"]
     fig, ax = plt.subplots()
@@ -67,5 +70,6 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     clear_btn.click(fn=clear_all, outputs=[review_input, result_output, prob_plot])
 
     gr.Markdown("### Made with ❤️ by [Meet Mendapara](https://github.com/Meetmendapara09)")
-# Launch
-demo.launch(share=True)
+
+# Launch the app
+demo.launch(share=True)