Update app.py

app.py

@@ -8,6 +8,7 @@ import re
 from io import BytesIO
 
 def preprocess_data(df):
+    
     # Renaming the 'Queries' column to 'texts'
     df.rename(columns={'Queries': 'texts'}, inplace=True)
     
@@ -20,6 +21,7 @@ def preprocess_data(df):
     # Remove URL from text
     df['texts'] = df['texts'].apply(lambda text: re.sub(r'https?://\S+|www\.\S+', '', text))
 
+
     # Remove emojis from text
     def remove_emoji(string):
         emoji_pattern = re.compile("["
@@ -96,6 +98,7 @@ def preprocess_data(df):
     for phrase in remove_phrases:
         df['texts'] = df['texts'].str.replace(phrase, '')
 
+
     # Drop rows containing any general words from response and its variations
     general_variations = ["good morning", "good evening", "good afternoon", "good night", "done", "sorry", "top", "query",
                           "stop", "sir", "sure", "oh", "wow", "aaa", "maam", "mam", "ma'am","i'm all set","ask a question","apply the survey",
@@ -125,9 +128,12 @@ def preprocess_data(df):
     df['texts'] = df['texts'].apply(lambda x: x.strip())  # Remove leading and trailing whitespaces
     df = df[df['texts'] != '']
 
+    
+
     return df
 
 def cluster_data(df, num_clusters=5):
+    
     # Vectorize the text data
     vectorizer = TfidfVectorizer(stop_words='english')
     X = vectorizer.fit_transform(df['texts'])
@@ -143,8 +149,10 @@ def cluster_data(df, num_clusters=5):
     df['PCA1'] = principal_components[:, 0]
     df['PCA2'] = principal_components[:, 1]
 
+    
     return df
 
+
 def visualize_clusters(df):
     plt.figure(figsize=(10, 6))
     scatter = plt.scatter(df['PCA1'], df['PCA2'], c=df['Cluster'], cmap='viridis')
@@ -154,25 +162,32 @@ def visualize_clusters(df):
     plt.ylabel('PCA Component 2')
     plt.show()
 
+
 def main(file, num_clusters):
     try:
+        
         df = pd.read_excel(file)
+        
+        
         df = preprocess_data(df)
         df = cluster_data(df, num_clusters)
         visualize_clusters(df)
-        csv_file = BytesIO()
-        df.to_csv(csv_file, index=False)
-        csv_file.seek(0)
-        return csv_file
+        
+        
+        return df
     except Exception as e:
-        import traceback
-        return traceback.format_exc()
+        
+        return str(e)
 
-iface = gr.Interface(
+interface = gr.Interface(
     fn=main,
-    inputs=[gr.inputs.File(label="Upload an Excel File (.xlsx)"), gr.inputs.Number(label="Number of Clusters")],
-    outputs=gr.outputs.File(label="Download Clustered Data as CSV")
+    inputs=[
+        gr.File(label="Upload Excel File (.xlsx)"),
+        gr.Number(value=5, label="Number of Clusters")
+    ],
+    outputs=gr.Dataframe(label="Clustered Data"),
+    title="Unanswered User Queries Clustering",
+    description="Upload an Excel file (.xlsx)"
 )
 
-if __name__ == "__main__":
-    iface.launch()
+interface.launch()