Update app.py

app.py

@@ -36,8 +36,10 @@ def preprocess_text(text):
 
 # Combine relevant text columns for processing
 question_columns = [f'Q{i}' for i in range(1, 37)]  # Adjust the range based on your data columns
-data['processed_text'] = data[['CV/Resume'] + question_columns].agg(' '.join, axis=1).apply(preprocess_text)
-data_open['processed_text_open'] = data_open[['CV/Resume', 'Question']].agg(' '.join, axis=1).apply(processed_text_open)
+data['processed_text'] = data[['CV/Resume'] + question_columns].agg(' '.join, axis=1)
+#data['processed_text'] = data[['CV/Resume'] + question_columns].agg(' '.join, axis=1).apply(preprocess_text)
+data_open['processed_text_open'] = data_open[['CV/Resume', 'Question']].agg(' '.join, axis=1)
+#data_open['processed_text_open'] = data_open[['CV/Resume', 'Question']].agg(' '.join, axis=1).apply(preprocess_text)
 
 labels = ["Peacemaker", "Loyalist", "Achiever", "Reformer", "Individualist", "Helper", "Challenger", "Investigator", "Enthusiast"]
 
@@ -47,9 +49,9 @@ confidence_threshold = st.slider("Confidence Threshold", 0.0, 1.0, 0.5)
 if st.button("Predict Personality by Test"):
     # Function to apply predictions using dynamic labels from MAX1, MAX2, MAX3 and only return the highest scored label
     def get_predictions(row):
-        #custom_labels = [row['MAX1'], row['MAX2'], row['MAX3']]  # Get labels from each row
+        custom_labels = [row['MAX1'], row['MAX2'], row['MAX3']]  # Get labels from each row
         processed_text = row['processed_text']
-        result = classifier(processed_text, labels)
+        result = classifier(processed_text, custom_labels)
         highest_score_label = result['labels'][0]  # Assumes the labels are sorted by score, highest first
         return highest_score_label