Update app.py

app.py

@@ -233,23 +233,23 @@ def main():
                 insurance_claims = pd.read_csv(selected_csv)
 
             num_rows = int(insurance_claims.shape[0]*int(num_lines)/100)
-            insurance_claims = insurance_claims.head(num_rows)
+            insurance_claims_reduced = insurance_claims.head(num_rows)
             st.write("Rows to be processed: " + str(num_rows))
-            
-            all_columns = insurance_claims.columns.tolist()
-            selected_columns = st.multiselect("Choose columns", all_columns, default=all_columns)
 
+            all_columns = insurance_claims_reduced.columns.tolist()
+            selected_columns = st.multiselect("Choose columns", all_columns, default=all_columns)
+            insurance_claims_reduced = insurance_claims_reduced[selected_columns].copy()
+            
             if st.button("Prediction"):
-                insurance_claims = insurance_claims[selected_columns].copy()
-                
-                s = setup(insurance_claims, session_id = 123, remove_multicollinearity=p_remove_multicollinearity, multicollinearity_threshold=p_multicollinearity_threshold,
+               
+                s = setup(insurance_claims_reduced, session_id = 123, remove_multicollinearity=p_remove_multicollinearity, multicollinearity_threshold=p_multicollinearity_threshold,
                             # remove_outliers=p_remove_outliers, outliers_method=p_outliers_method, 
                             transformation=p_transformation, 
                             normalize=p_normalize, pca=p_pca, pca_method=p_pca_method)
 
                 exp_anomaly = AnomalyExperiment()
                 # init setup on exp
-                exp_anomaly.setup(insurance_claims, session_id = 123)
+                exp_anomaly.setup(insurance_claims_reduced, session_id = 123)
             
                 with st.spinner("Analyzing..."):
                     # train model