Update app.py

app.py

@@ -132,7 +132,7 @@ def visualize_clusters(df):
     plt.ylabel('PCA Component 2')
     plt.show()
 
-def main(file):
+def main(file, num_clusters_to_display):
     try:
         df = pd.read_excel(file)
         df = preprocess_data(df)
@@ -144,6 +144,14 @@ def main(file):
         df['Cluster'] = pd.Categorical(df['Cluster'], categories=sorted_clusters, ordered=True)
         df = df.sort_values('Cluster')
 
+        # Filter out cluster 0 and get the largest clusters
+        filtered_clusters = [cluster for cluster in sorted_clusters if cluster != 0]
+        top_clusters = filtered_clusters[:num_clusters_to_display]
+
+        df = df[df['Cluster'].isin(top_clusters)]
+        df['Cluster'] = pd.Categorical(df['Cluster'], categories=top_clusters, ordered=True)
+        df = df.sort_values('Cluster')
+
         with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmpfile:
             df.to_csv(tmpfile.name, index=False)
             return tmpfile.name
@@ -152,10 +160,13 @@ def main(file):
 
 interface = gr.Interface(
     fn=main,
-    inputs=gr.File(label="Upload Excel File (.xlsx)"),
+    inputs=[
+        gr.File(label="Upload Excel File (.xlsx)"),
+        gr.Slider(1, 10, step=1, label="Number of Largest Clusters to Display")
+    ],
     outputs=gr.File(label="Clustered Data CSV"),
     title="Unanswered User Queries Clustering",
-    description="Upload an Excel file (.xlsx)"
+    description="Upload an Excel file (.xlsx) and select the number of largest clusters to display (excluding cluster 0)"
 )
 
 interface.launch()