try ChatGPT edit

app.py

@@ -17,48 +17,36 @@ logger = logging.getLogger(__name__)
 logger.info("Initializing emotion classification pipeline...")
 classifier = pipeline(
     "text-classification",
-    model="bhadresh-savani/distilbert-base-uncased-emotion",
-    top_k=None  # Return all scores
+    model="bhadresh-savani/distilbert-base-uncased-emotion"
 )
 logger.info("Pipeline initialized successfully")
 
+# Default DataFrame for BarPlot
+emotion_labels = [pred['label'] for pred in classifier("test")]
+default_scores = [0] * len(emotion_labels)
+default_df = pd.DataFrame({'label': emotion_labels, 'score': default_scores})
+
+# Error DataFrame for BarPlot
+error_df = pd.DataFrame({'label': ['error'], 'score': [1.0]})
+
 def predict_emotion(text):
     """Predict emotions from text and return formatted results."""
     try:
-        logger.info(f"Received input text: {text}")
-        
         if not text:
             logger.warning("Empty text received")
-            return gr.BarPlot.update(
-                value=pd.DataFrame({
-                    'label': ['sadness', 'joy', 'love', 'anger', 'fear', 'surprise'],
-                    'score': [0, 0, 0, 0, 0, 0]
-                })
-            )
+            return gr.BarPlot.update(value=default_df)
         
-        # Get predictions
+        # Get predictions and create DataFrame
         logger.info("Running prediction...")
         predictions = classifier(text)[0]
-        logger.info(f"Raw predictions: {predictions}")
-        
-        # Sort predictions by score
-        sorted_predictions = sorted(predictions, key=lambda x: x['score'], reverse=True)
-        
-        # Create DataFrame with the correct format
-        df = pd.DataFrame(sorted_predictions)
-        df.columns = ['label', 'score']  # Rename columns to match expected format
+        df = pd.DataFrame(predictions)
         logger.info(f"Processed scores:\n{df}")
         
         return gr.BarPlot.update(value=df)
         
     except Exception as e:
         logger.error(f"Error in prediction: {str(e)}")
-        return gr.BarPlot.update(
-            value=pd.DataFrame({
-                'label': ['error'],
-                'score': [1.0]
-            })
-        )
+        return gr.BarPlot.update(value=error_df)
 
 # Create the Gradio interface
 demo = gr.Interface(
@@ -69,14 +57,11 @@ demo = gr.Interface(
         lines=4
     ),
     outputs=gr.BarPlot(
-        value=pd.DataFrame({
-            'label': ['sadness', 'joy', 'love', 'anger', 'fear', 'surprise'],
-            'score': [0, 0, 0, 0, 0, 0]
-        }),
+        value=default_df,
         x="label",
         y="score",
         title="Emotion Probabilities",
-        color="#2563eb",
+        color=["#ff6f61", "#6b5b95", "#88b04b", "#f7cac9", "#92a8d1", "#f7786b"],  # Dynamic color
         height=400,
         vertical=True
     ),
@@ -93,4 +78,4 @@ demo = gr.Interface(
 )
 
 if __name__ == "__main__":
-    demo.launch(debug=True)
+    demo.launch(debug=True)