Update app.py

app.py

@@ -149,22 +149,22 @@ if page == "Clustering Analysis":
 
                 st.header("Clustering Plots")
                 # plot pca cluster plot 
-                plot_model(cluster_model, plot = 'cluster', display_format = 'streamlit')
+                # plot_model(cluster_model, plot = 'cluster', display_format = 'streamlit')
                 
-                if selected_model != 'ap':
-                    plot_model(cluster_model, plot = 'tsne', display_format = 'streamlit')
+                # if selected_model != 'ap':
+                #     plot_model(cluster_model, plot = 'tsne', display_format = 'streamlit')
                 
-                if selected_model not in ('ap', 'meanshift', 'dbscan', 'optics'):
-                    plot_model(cluster_model, plot = 'elbow', display_format = 'streamlit')
+                # if selected_model not in ('ap', 'meanshift', 'dbscan', 'optics'):
+                #     plot_model(cluster_model, plot = 'elbow', display_format = 'streamlit')
                 
-                if selected_model not in ('ap', 'meanshift', 'sc', 'hclust', 'dbscan', 'optics'):
-                    plot_model(cluster_model, plot = 'silhouette', display_format = 'streamlit')
+                # if selected_model not in ('ap', 'meanshift', 'sc', 'hclust', 'dbscan', 'optics'):
+                #     plot_model(cluster_model, plot = 'silhouette', display_format = 'streamlit')
                 
-                if selected_model not in ('ap', 'sc', 'hclust', 'dbscan', 'optics', 'birch'):
-                    plot_model(cluster_model, plot = 'distance', display_format = 'streamlit')
+                # if selected_model not in ('ap', 'sc', 'hclust', 'dbscan', 'optics', 'birch'):
+                #     plot_model(cluster_model, plot = 'distance', display_format = 'streamlit')
                 
-                if selected_model != 'ap':
-                    plot_model(cluster_model, plot = 'distribution', display_format = 'streamlit')  
+                # if selected_model != 'ap':
+                #     plot_model(cluster_model, plot = 'distribution', display_format = 'streamlit')  
 
                 # Create a Classification Model to extract feature importance
                 st.header("Feature Importance")
@@ -172,6 +172,8 @@ if page == "Clustering Analysis":
                 s = setup(cluster_model_2, target = 'Cluster')
                 lr = create_model('lr')
                 # this is how you can recreate the table
+                print("Number of columns in X_train:", len(get_config('X_train').columns))
+                print("Number of coefficients in lr:", len(lr.coef_[0]))
                 feat_imp = pd.DataFrame({'Feature': get_config('X_train').columns, 'Value' : abs(lr.coef_[0])}).sort_values(by='Value', ascending=False)
                 # sort by feature importance value and filter top 10
                 feat_imp = feat_imp.sort_values(by='Value', ascending=False).head(10)