Update app.py

app.py

@@ -36,10 +36,12 @@ 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)
-#data['processed_text'] = data[['CV/Resume'] + question_columns].agg(' '.join, axis=1).apply(preprocess_text)
+data['processed_text'] = data[['CV/Resume'] + question_columns].agg(lambda x: ', '.join(x), axis=1)
+#data['processed_text'] = data[['CV/Resume'] + question_columns].agg(lambda x: ', '.join(x), 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)
+data_open['processed_text_open'] = data_open[['Demo_F', 'Question']].agg(' '.join, axis=1)
+data_open['processed_text_mopen'] = data_open[['Demo_M', 'Question']].agg(' '.join, axis=1)
 
 labels = ["Peacemaker", "Loyalist", "Achiever", "Reformer", "Individualist", "Helper", "Challenger", "Investigator", "Enthusiast"]
 
@@ -57,7 +59,7 @@ if st.button("Predict Personality by Test"):
 
     # Apply predictions across all rows
     data['Predicted'] = data.apply(get_predictions, axis=1)
-    st.dataframe(data[['True_label','MAX1','MAX2','MAX3','processed_text', 'Predicted']])
+    st.dataframe(data[['True_label','MAX1','MAX2','MAX3', 'Predicted']])
 
 if st.button("Predict Personality by Open Question"):
     def get_predictions(row):
@@ -65,7 +67,14 @@ if st.button("Predict Personality by Open Question"):
         result = classifier(processed_text, labels)
         highest_score_label = result['labels'][0]  # Assumes the labels are sorted by score, highest first
         return highest_score_label
+        
+    def get_predictionsM(row):
+        processed_text = row['processed_text_mopen']
+        result = classifier(processed_text, labels)
+        highest_score_label = result['labels'][0]  # Assumes the labels are sorted by score, highest first
+        return highest_score_label
 
     # Apply predictions across all rows
-    data_open['Predicted'] = data_open.apply(get_predictions, axis=1)
-    st.dataframe(data_open[['True_label', 'Predicted']])
+    data_open['Predicted_M'] = data_open.apply(get_predictions, axis=1)
+    data_open['Predicted_F'] = data_open.apply(get_predictionsM, axis=1)
+    st.dataframe(data_open[['True_label', 'Predicted_F', 'Predicted_M']])