Update app.py

app.py

@@ -107,7 +107,9 @@ def preprocess_data(df):
 
     return df
 
-def cluster_data(df, num_clusters=5):
+def cluster_data(df):
+    # Set the number of clusters here
+    num_clusters = 5  
     vectorizer = TfidfVectorizer(stop_words='english')
     X = vectorizer.fit_transform(df['texts'])
 
@@ -131,11 +133,11 @@ def visualize_clusters(df):
     plt.ylabel('PCA Component 2')
     plt.show()
 
-def main(file, num_clusters):
+def main(file):
     try:
         df = pd.read_excel(file)
         df = preprocess_data(df)
-        df = cluster_data(df, num_clusters)
+        df = cluster_data(df)
         visualize_clusters(df)
         
         with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmpfile:
@@ -146,10 +148,7 @@ def main(file, num_clusters):
 
 interface = gr.Interface(
     fn=main,
-    inputs=[
-        gr.File(label="Upload Excel File (.xlsx)"),
-        gr.Number(value=5, label="Number of Clusters")
-    ],
+    inputs=gr.File(label="Upload Excel File (.xlsx)"),
     outputs=gr.File(label="Clustered Data CSV"),
     title="Unanswered User Queries Clustering",
     description="Upload an Excel file (.xlsx)"