Update app.py

app.py

@@ -21,14 +21,10 @@ emotion_labels = ["admiration", "amusement", "anger", "annoyance", "approval",
                   "pride", "realization", "relief", "remorse", "sadness", "surprise",
                   "neutral"]
 
-# Function to classify emotions in batches and save results after each batch
-def classify_emotions_in_batches(texts, batch_size=64, output_file="enron_emails_with_emotions.csv"):
+# Function to classify emotions in batches
+def classify_emotions_in_batches(texts, batch_size=64):
     results = []
     start_time = time.time()
-
-    # DataFrame to store the results
-    result_df = pd.DataFrame(columns=['From', 'To', 'body', 'emotion'])
-
     for i in range(0, len(texts), batch_size):
         batch = texts[i:i+batch_size]
         inputs = tokenizer(batch, return_tensors="pt", truncation=True, padding=True).to(device)
@@ -37,26 +33,12 @@ def classify_emotions_in_batches(texts, batch_size=64, output_file="enron_emails
             logits = outputs.logits
             predicted_class_ids = torch.argmax(logits, dim=-1).tolist()
             results.extend(predicted_class_ids)
-
-        # Save the batch results
-        batch_results = {
-            'From': enron_data['From'][i:i+batch_size],
-            'To': enron_data['To'][i:i+batch_size],
-            'body': batch,
-            'emotion': [emotion_labels[idx] for idx in predicted_class_ids]
-        }
-        batch_df = pd.DataFrame(batch_results)
-        result_df = pd.concat([result_df, batch_df])
-
-        # Save to CSV
-        result_df.to_csv(output_file, index=False)
-
+        
         # Log progress
         batch_time = time.time() - start_time
         st.write(f"Processed batch {i//batch_size + 1} of {len(texts)//batch_size + 1} in {batch_time:.2f} seconds")
         start_time = time.time()
-
-    return result_df
+    return results
 
 # Streamlit interface
 st.title("Enron Emails Emotion Analysis")
@@ -71,6 +53,8 @@ if st.button("Run Inference"):
     # Apply emotion classification to the email content
     with st.spinner('Running inference...'):
         email_texts = enron_data['body'].tolist()
-        classify_emotions_in_batches(email_texts, batch_size=64)
+        enron_data['emotion'] = classify_emotions_in_batches(email_texts, batch_size=64)
 
+    # Save the results to a CSV file
+    enron_data.to_csv("enron_emails_with_emotions.csv", index=False)
     st.success("Inference completed and results saved!")