Update app.py

app.py

@@ -91,7 +91,7 @@ def analyze_sentiment(text):
     )
 
     sentiment = response.choices[0].message.content
-    print(sentiment)
+    #print(sentiment)
     sentiment_history.append(sentiment_scores.get(sentiment.lower(), 0))
     print(sentiment_history)
     return sentiment
@@ -126,7 +126,7 @@ def transcribe_audio_azure(audio_file_path):
         language="en",                        # Specify the language of the audio (English in this case)
         temperature=0.0                       # Control the randomness of the output (0.0 means deterministic output)
       )
-      print(f'Transcription done using Azure Whisper')
+      #print(f'Transcription done using Azure Whisper')
       return transcription.text
 
 AZURE_GPT_ENDPOINT = 'https://78382-m7ewtltu-eastus2.openai.azure.com/'
@@ -153,7 +153,7 @@ def analyze_sentiment_gpt(text):
         max_tokens=10     # Limit the response length to 200 tokens
     )
     sentiment = response.choices[0].message.content
-    print(sentiment)
+    #print(sentiment)
     sentiment_history.append(sentiment_scores.get(sentiment.lower(), 0))
     print(sentiment_history)
     return sentiment
@@ -179,7 +179,7 @@ def analyze_sentiment_azure(client, text):
     sentiment = response.sentiment
     #print(sentiment)
     sentiment_history.append(sentiment_scores.get(sentiment.lower(), 0))
-    #print(sentiment_history)
+    print(sentiment_history)
     return sentiment
 
 # CLEANUP transcribed text before doing Sentiment Analysis
@@ -260,7 +260,7 @@ def generate_sentiment_heatmap():
      #   return
     # Convert sentiment scores to corresponding colors
     heatmap_data = np.array(sentiment_history).reshape(1, -1)
-    print(heatmap_data)
+    #print(heatmap_data)
     # Define color mapping for sentiment scores
     color_mapping = ["red", "yellow", "green"]
     plt.figure(figsize=(6, 3))