Update app.py

app.py

@@ -138,54 +138,20 @@ class SpeechAnalyzer:
         sentiment_scores = []
         basic_emotions = []
         
-        # Add emotion classifier pipeline
-        emotion_classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", return_all_scores=True)
-        
         for segment in segments:
-            sentences = nltk.sent_tokenize(segment)
-            batch_size = 64
-            segment_scores = []
-            segment_emotions = []
-            
-            for i in range(0, len(sentences), batch_size):
-                batch = sentences[i:i+batch_size]
-                batch = [sent[:512] for sent in batch]
-                batch = [sent if sent.strip() else "." for sent in batch]
-                
-                # Get sentiment scores
-                try:
-                    results = self.sentiment_pipeline(batch)
-                    batch_scores = []
-                    for result in results:
-                        score = result['score']
-                        # Enhanced score scaling for better visualization
-                        if result['label'] == 'POSITIVE':
-                            score = 0.5 + (score * 0.5)  # Scale from 0.5 to 1.0
-                        else:
-                            score = 0.5 - (score * 0.5)  # Scale from 0.0 to 0.5
-                        batch_scores.append(score)
-                    segment_scores.extend(batch_scores)
-                    
-                    # Get emotion classifications
-                    emotion_results = emotion_classifier(batch)
-                    batch_emotions = []
-                    for result in emotion_results:
-                        # Get the dominant emotion
-                        dominant_emotion = max(result[0], key=lambda x: x['score'])
-                        batch_emotions.append(dominant_emotion['label'])
-                    segment_emotions.extend(batch_emotions)
-                    
-                except Exception as e:
-                    print(f"Batch processing error: {e}")
-                    segment_scores.extend([0.5] * len(batch))
-                    segment_emotions.extend(['neutral'] * len(batch))
-            
-            sentiment_scores.append(np.mean(segment_scores))
-            # Get most frequent emotion in segment
-            if segment_emotions:
-                basic_emotions.append(max(set(segment_emotions), key=segment_emotions.count))
+            # Get sentiment scores
+            sentiment_result = self.sentiment_pipeline(segment)
+            score = sentiment_result[0]['score']
+            if sentiment_result[0]['label'] == 'POSITIVE':
+                score = 0.5 + (score * 0.5)
             else:
-                basic_emotions.append('neutral')
+                score = 0.5 - (score * 0.5)
+            sentiment_scores.append(score)
+            
+            # Get emotion classification
+            emotion_result = self.emotion_classifier(segment)
+            emotion = emotion_result[0]['label']
+            basic_emotions.append(emotion)
         
         return sentiment_scores, basic_emotions
 
@@ -417,13 +383,15 @@ def main():
                 unified_fig.add_trace(go.Bar(
                     x=segment_labels,
                     y=[1] * len(basic_emotions),  # Full height bars
-                    name='Basic Emotions',
+                    name=f'Emotions Found: {", ".join(sorted(set(basic_emotions)))}',  # Shows all unique emotions
                     marker=dict(
-                        color=[emotion_colors.get(e.lower(), '#808080') for e in basic_emotions]
+                        color=[emotion_colors.get(e.lower(), '#808080') for e in basic_emotions],
+                        line=dict(width=1, color='#000000')  # Adds border for better visibility
                     ),
                     opacity=0.8,
-                    hovertemplate="Segment: %{x}<br>Emotion: %{text}<extra></extra>",
-                    text=basic_emotions
+                    hovertemplate="Segment %{x}<br>Emotion: %{text}<extra></extra>",
+                    text=basic_emotions,
+                    textposition='auto'
                 ))
 
             st.plotly_chart(unified_fig, use_container_width=True)