Update app.py

app.py

@@ -108,8 +108,7 @@ def preprocess_data(df):
     return df
 
 def cluster_data(df):
-    # Set the number of clusters here
-    num_clusters = 5  
+    num_clusters = 15  # Set the number of clusters to 15
     vectorizer = TfidfVectorizer(stop_words='english')
     X = vectorizer.fit_transform(df['texts'])
 
@@ -139,7 +138,12 @@ def main(file):
         df = preprocess_data(df)
         df = cluster_data(df)
         visualize_clusters(df)
-        
+
+        cluster_sizes = df['Cluster'].value_counts()
+        sorted_clusters = cluster_sizes.index.tolist()
+        df['Cluster'] = pd.Categorical(df['Cluster'], categories=sorted_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