Update app.py

app.py

@@ -17,13 +17,13 @@ classifier = pipeline("zero-shot-classification", model="Fralet/personality")
 st.title("Resume-based Personality Prediction by Serikov Ayanbek")
 
 # Load data from Excel
-data = pd.read_excel("ResponseTest.xlsx")  # Replace 'your_excel_file.xlsx' with your actual file name
+data = pd.read_excel("ResponseTest.xlsx")  # Replace 'ResponseTest.xlsx' with your actual file name
 
 # Preprocess text function
 def preprocess_text(text):
     text = re.sub(r'\W', ' ', str(text))
     text = text.lower()
-    text is re.sub(r'\s+[a-z]\s+', ' ', text)
+    text = re.sub(r'\s+[a-z]\s+', ' ', text)
     text = re.sub(r'^[a-z]\s+', ' ', text)
     text = re.sub(r'\s+', ' ', text)
     stop_words = set(stopwords.words('english'))
@@ -41,13 +41,14 @@ data['processed_text'] = data['combined_text'].apply(preprocess_text)
 confidence_threshold = st.slider("Confidence Threshold", 0.0, 1.0, 0.5)
 
 if st.button("Predict Personality"):
-    # Function to apply predictions using dynamic labels from MAX1, MAX2, MAX3
+    # 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
         processed_text = row['processed_text']
         result = classifier(processed_text, custom_labels)
-        return result
+        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['predicted_labels'] = data.apply(get_predictions, axis=1)
-    st.dataframe(data[['True_label', 'Predicted', 'predicted_labels']])
+    data['Predicted'] = data.apply(get_predictions, axis=1)
+    st.dataframe(data[['True_label', 'Predicted']])