Update app.py

app.py

@@ -188,12 +188,12 @@ def main(file, num_clusters_to_display):
         df['Cluster'] = pd.Categorical(df['Cluster'], categories=sorted_clusters, ordered=True)
         df = df.sort_values('Cluster')
 
-        # Filter out base cluster and get the largest clusters
-        filtered_clusters = [cluster for cluster in sorted_clusters if cluster != 10]
-        top_clusters = filtered_clusters[:num_clusters_to_display]
+        # Filter out the largest cluster and get the next largest clusters
+        largest_cluster = sorted_clusters[0]
+        filtered_clusters = sorted_clusters[1:num_clusters_to_display+1]
 
-        df = df[df['Cluster'].isin(top_clusters)]
-        df['Cluster'] = pd.Categorical(df['Cluster'], categories=top_clusters, ordered=True)
+        df = df[df['Cluster'].isin(filtered_clusters)]
+        df['Cluster'] = pd.Categorical(df['Cluster'], categories=filtered_clusters, ordered=True)
         df = df.sort_values('Cluster')
 
         silhouette_avg = silhouette_score(X, kmeans.labels_)