Update app.py

app.py

@@ -98,18 +98,18 @@ 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))
             
             st.header("Inference Description")
-            insurance_claims.describe().T
+            insurance_claims_reduced.describe().T
 
-            cat_col = insurance_claims.select_dtypes(include=['object']).columns
-            num_col = insurance_claims.select_dtypes(exclude=['object']).columns
+            cat_col = insurance_claims_reduced.select_dtypes(include=['object']).columns
+            num_col = insurance_claims_reduced.select_dtypes(exclude=['object']).columns
 
             # insurance_claims[num_col].hist(bins=15, figsize=(20, 15), layout=(5, 4))
             # Calculate the correlation matrix
-            corr_matrix = insurance_claims[num_col].corr()
+            corr_matrix = insurance_claims_reduced[num_col].corr()
             # Create a Matplotlib figure
             fig, ax = plt.subplots(figsize=(12, 8))
             # Create a heatmap using seaborn
@@ -120,19 +120,19 @@ def main():
             # Display the heatmap in Streamlit
             st.pyplot(fig)
 
-            all_columns = insurance_claims.columns.tolist()
+            all_columns = insurance_claims_reduced.columns.tolist()
             selected_columns = st.multiselect("Choose columns", all_columns, default=all_columns)
 
             if st.button("Prediction"):
-                insurance_claims = insurance_claims[selected_columns].copy()
+                insurance_claims_reduced = insurance_claims_reduced[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_clustering = ClusteringExperiment()
                 # init setup on exp
-                exp_clustering.setup(insurance_claims, session_id = 123)
+                exp_clustering.setup(insurance_claims_reduced, session_id = 123)
 
                 with st.spinner("Analyzing..."):
                     # train kmeans model