Upload app.py

app.py

@@ -3,14 +3,24 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.cluster import KMeans
 import gradio as gr
 
-def topic_modeling(file, n_clusters):
-    df = pd.read_csv(file.name)
-    titles = df['title'].astype(str).tolist()
+# Adjust the file path to where titles.csv is located in your environment
+CSV_FILE_PATH = 'titles.csv'  # Update this with the correct path to your CSV file
+
+def topic_modeling(n_clusters):
+    # Read the CSV file directly from the specified file path
+    df = pd.read_csv(CSV_FILE_PATH)
+    
+    if 'title' not in df.columns:
+        return "Error: CSV does not contain a 'title' column"
+    
+    titles = df['title'].astype(str).tolist()  # Convert the 'title' column to a list of strings
     vectorizer = TfidfVectorizer(stop_words='english', ngram_range=(1, 2), max_df=0.9)
     X = vectorizer.fit_transform(titles)
+    
     model = KMeans(n_clusters=n_clusters, random_state=42)
     df['topic'] = model.fit_predict(X)
     
+    # Prepare the output to display the top titles for each topic
     output = ""
     for i in range(n_clusters):
         output += f"\n### Topic {i}\n"
@@ -18,12 +28,13 @@ def topic_modeling(file, n_clusters):
         output += "\n".join(f"- {t}" for t in top_titles) + "\n"
     return output
 
+# Define the Gradio interface (no file input, just a slider for n_clusters)
 iface = gr.Interface(
     fn=topic_modeling,
-    inputs=[gr.File(label="CSV File (must have a 'title' column)"), gr.Slider(2, 10, step=1, value=5, label="Number of Topics")],
+    inputs=[gr.Slider(2, 10, step=1, value=5, label="Number of Topics")],
     outputs="markdown",
     title="Topic Modeling App (TF-IDF + KMeans)",
-    description="Upload a CSV with a 'title' column. This app clusters titles into topics using TF-IDF and KMeans."
+    description="This app clusters titles from a CSV file into topics using TF-IDF and KMeans. No file upload needed."
 )
 
 if __name__ == "__main__":