Update app.py

app.py

@@ -90,33 +90,25 @@ print(f"Recall: {(1 - recall) * 100:.2f}%")
 print(f"F1 Score: {(1 - f1) * 100:.2f}%")
 
 def predict_tone(text):
-    # Vectorize
     text_tfidf = tfidf.transform([text])
     
-    # Get prediction probabilities
     probs = model.predict_proba(text_tfidf)[0]
     
-    # Get predicted class and its probability
     pred_class_encoded = model.classes_[np.argmax(probs)]
     pred_class = label_encoder.inverse_transform([pred_class_encoded])[0]
     
-    # Get the labels used during training
     trained_labels = model.classes_  
 
-    # Decode to string (Labels)
     trained_label_names = label_encoder.inverse_transform(trained_labels)
 
     results = {label: float(prob) for label, prob in zip(trained_label_names, probs)}
     
-    # Sort results by probability (descending)
     sorted_results = {k: v for k, v in sorted(results.items(), key=lambda item: item[1], reverse=True)}
     
-    # Create visualization
     top_n = 5  # Top 5, adjust later if needed
     top_labels = list(sorted_results.keys())[:top_n]
     top_probs = list(sorted_results.values())[:top_n]
     
-    # OPTIONAL: color-code probabilities
     colors = ["rgba(64, 128, 255, " + str(min(1.0, p + 0.3)) + ")" for p in top_probs]
     
     fig = go.Figure()