Update src/streamlit_app.py

src/streamlit_app.py

@@ -14,7 +14,7 @@ DATA_FILE_PATH = 'src/articles.csv'
 # Number of recommendations to display
 NUM_RECOMMENDATIONS = 5
 
-# --- Data Loading and Preparation (Removed mock data dependency) ---
+# --- Data Loading and Preparation ---
 @st.cache_data
 def load_and_prepare_data():
     """
@@ -25,8 +25,8 @@ def load_and_prepare_data():
     
     if os.path.exists(DATA_FILE_PATH):
         try:
-            df = pd.read_csv(DATA_FILE_PATH,  encoding='latin1')
-            st.success(f"Data loaded successfully from {DATA_FILE_PATH}.")
+            df = pd.read_csv(DATA_FILE_PATH,encoding='latin1')
+            # Removed st.success(f"Data loaded successfully...")
         except Exception as e:
             st.error(f"Error reading {DATA_FILE_PATH}. Please check file integrity and format (CSV). Error: {e}")
     else:
@@ -53,7 +53,6 @@ def fit_or_load_models(df):
     """
     # Check if the necessary columns exist before proceeding
     if df.empty or 'Article' not in df.columns or 'Title' not in df.columns:
-        # This check should be redundant if load_and_prepare_data works, but good for defense
         return None, None, None
 
     if os.path.exists(VECTORIZER_PATH) and os.path.exists(TFIDF_MATRIX_PATH):
@@ -64,7 +63,7 @@ def fit_or_load_models(df):
             
             # Recalculate cosine similarity (This is fast on the loaded matrix)
             cosine_sim = cosine_similarity(tfidf_matrix)
-            st.success("Models loaded successfully from disk.")
+            # Removed st.success("Models loaded successfully...")
             return tfidf, tfidf_matrix, cosine_sim
         except Exception as e:
             st.error(f"Error loading models. Recalculating: {e}")
@@ -85,7 +84,7 @@ def fit_or_load_models(df):
         # Save models for future runs
         joblib.dump(tfidf, VECTORIZER_PATH)
         joblib.dump(tfidf_matrix, TFIDF_MATRIX_PATH)
-        st.success("Model calculation complete and saved.")
+        # Removed st.success("Model calculation complete...")
         
         return tfidf, tfidf_matrix, cosine_sim
 
@@ -110,7 +109,7 @@ def get_recommendations(article_index, cosine_sim_matrix, df, num_recommendation
     # Get the indices of the top N recommended articles (these are positional indices)
     top_n_indices = [i[0] for i in top_n_recommendations]
     
-    # --- CRITICAL FIX: Use list indexing instead of DataFrame .iloc to guarantee positional lookup ---
+    # Use list indexing instead of DataFrame .iloc to guarantee positional lookup
     title_list = df["Title"].tolist()
     recommended_titles = [title_list[i] for i in top_n_indices]
     
@@ -126,7 +125,7 @@ def app():
     st.set_page_config(page_title="Article Recommendation System", layout="wide")
     
     st.title("📄 Content-Based Article Recommender")
-    st.markdown("This system uses TF-IDF vectorization and Cosine Similarity to recommend articles based on content matching.")
+    st.markdown("Select an article from the sidebar to see the top **5** most relevant recommendations.")
 
     # 1. Load Data
     df = load_and_prepare_data()
@@ -192,19 +191,6 @@ def app():
             st.markdown("### Article Title (Similarity Score)")
             for title, score in recommendations_list:
                 st.markdown(f"**{title}** - *({score}%)*")
-                
-        st.markdown("""
-        ---
-        **Methodology:**
-        1. **Vectorization:** TF-IDF (Term Frequency-Inverse Document Frequency) transforms article text into numerical vectors.
-        2. **Similarity:** Cosine Similarity measures the angle between vectors to determine content similarity.
-        3. **Result:** Articles with the smallest angle (highest score) are recommended.
-        """)
-        
-        # Add a section to show the current article's content
-        st.subheader("Current Article Content:")
-        article_content = df.iloc[selected_index]['Article']
-        st.markdown(f"*{article_content}*")
-
+                        
 if __name__ == "__main__":
     app()