Update src/streamlit_app.py

src/streamlit_app.py

@@ -9,45 +9,38 @@ from sklearn.metrics.pairwise import cosine_similarity
 # File paths for model persistence
 VECTORIZER_PATH = 'src/article_vectorizer.joblib'
 TFIDF_MATRIX_PATH = 'src/article_matrix.joblib'
+DATA_FILE_PATH = 'src/articles.csv' 
 
 # Number of recommendations to display
 NUM_RECOMMENDATIONS = 5
 
-# --- Mock Data Setup (Replace with your actual data loading if necessary) ---
+# --- Data Loading and Preparation (Removed mock data dependency) ---
 @st.cache_data
 def load_and_prepare_data():
-    """Creates a mock DataFrame for demonstration."""
-    data = {
-        "Title": [
-            "Introduction to Machine Learning",
-            "Deep Learning: Neural Networks Explained",
-            "Python for Data Science and Analysis",
-            "The Ethical Future of Artificial Intelligence",
-            "Understanding Vector Space Models in NLP",
-            "Essential Data Cleaning Techniques",
-            "Advanced Time Series Forecasting",
-            "Web Scraping with Python and BeautifulSoup",
-            "Cloud Computing Fundamentals",
-            "Agile Software Development Methodologies"
-        ],
-        "Article": [
-            "Machine learning is a field of computer science that uses statistical techniques to give computer systems the ability to 'learn' with data, without being explicitly programmed. It is a subset of AI and heavily relies on linear algebra.",
-            "Deep learning is a subset of ML that uses neural networks with three or more layers to analyze complex data structures. It is currently the state-of-the-art for image recognition and natural language processing tasks. Understanding the architecture is key.",
-            "Python is a high-level, interpreted programming language widely used in data science, especially due to libraries like Pandas, NumPy, and Scikit-learn. Its simplicity makes data manipulation and analysis easy.",
-            "The future of artificial intelligence involves complex models, ethical guidelines, and responsible integration into all sectors. Researchers predict significant advancements in natural language processing and computer vision.",
-            "Vectors are fundamental objects in linear algebra and are crucial for representing words in a TF-IDF or Word2Vec model. Understanding vector math is key to similarity calculations and NLP.",
-            "Cleaning data is the most time-consuming part of any data science project. Techniques involve handling missing values, outliers, and inconsistencies to prepare data for robust modeling.",
-            "Time series forecasting involves predicting future values based on historically observed values. Methods include ARIMA, Prophet, and advanced deep learning models like LSTMs for complex patterns.",
-            "Web scraping is the process of extracting data from websites. Python libraries like Requests and BeautifulSoup are commonly used to parse HTML and gather structured information efficiently.",
-            "Cloud computing offers on-demand availability of computer system resources, especially data storage and computing power, without direct active management by the user. Major providers are AWS, Azure, and Google Cloud.",
-            "Agile is an iterative approach to project management and software development that helps teams deliver value faster and with fewer headaches. It involves concepts like Scrum and Kanban."
-        ]
-    }
-    df = pd.DataFrame(data)
-    # 1. DEFENSIVE FIX: Ensure the index is a clean, contiguous 0-based positional index
+    """
+    Loads data ONLY from articles.csv and prepares the DataFrame.
+    If the file is not found or reading fails, it returns an empty DataFrame.
+    """
+    df = pd.DataFrame() # Initialize an empty DataFrame
+    
+    if os.path.exists(DATA_FILE_PATH):
+        try:
+            df = pd.read_csv(DATA_FILE_PATH)
+            st.success(f"Data loaded successfully from {DATA_FILE_PATH}.")
+        except Exception as e:
+            st.error(f"Error reading {DATA_FILE_PATH}. Please check file integrity and format (CSV). Error: {e}")
+    else:
+        st.error(f"CRITICAL ERROR: {DATA_FILE_PATH} not found. Please upload the file to your application directory.")
+        
+    if df.empty or 'Article' not in df.columns or 'Title' not in df.columns:
+        # If loading failed or columns are missing, return empty or incomplete DataFrame
+        return pd.DataFrame() 
+
+    # 1. Ensure the index is a clean, contiguous 0-based positional index
     df = df.reset_index(drop=True) 
-    # Ensure all text is string type
+    # Ensure the article column is string type
     df['Article'] = df['Article'].astype(str)
+    
     return df
 
 # --- Model Fitting/Loading Logic ---
@@ -58,13 +51,18 @@ def fit_or_load_models(df):
     Fits the TF-IDF model and calculates Cosine Similarity, 
     or loads them from disk if available.
     """
+    # 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):
         try:
             # Load existing models
             tfidf = joblib.load(VECTORIZER_PATH)
             tfidf_matrix = joblib.load(TFIDF_MATRIX_PATH)
             
-            # Recalculate cosine similarity just in case the data changed or for the current run
+            # Recalculate cosine similarity (This is fast on the loaded matrix)
             cosine_sim = cosine_similarity(tfidf_matrix)
             st.success("Models loaded successfully from disk.")
             return tfidf, tfidf_matrix, cosine_sim
@@ -112,9 +110,9 @@ 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]
     
-    # Get the titles
-    # Since df now has a clean 0-based index, .iloc should be safe here.
-    recommended_titles = df["Title"].iloc[top_n_indices].tolist()
+    # --- CRITICAL FIX: 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]
     
     # Get the similarity scores for display (rounded)
     recommended_scores = [round(i[1] * 100, 2) for i in top_n_recommendations]
@@ -130,11 +128,22 @@ def app():
     st.title("📄 Content-Based Article Recommender")
     st.markdown("This system uses TF-IDF vectorization and Cosine Similarity to recommend articles based on content matching.")
 
-    # 1. Load Data and Models
+    # 1. Load Data
     df = load_and_prepare_data()
-    # The returned values are already cached, so this is fast on subsequent runs
+    
+    # Check if data loading was successful and essential columns exist
+    if df.empty or 'Article' not in df.columns or 'Title' not in df.columns:
+        st.error("Application cannot start: Please ensure 'articles.csv' is uploaded and contains 'Title' and 'Article' columns.")
+        return
+        
+    # 2. Load/Fit Models
     tfidf, tfidf_matrix, cosine_sim = fit_or_load_models(df)
     
+    # Check if models were loaded/calculated successfully
+    if cosine_sim is None:
+        st.error("Application cannot start: Model calculation failed.")
+        return
+    
     # --- Sidebar for Selection ---
     
     # Create a list of titles for the selectbox
@@ -148,14 +157,14 @@ def app():
 
     # Find the index of the selected article
     if selected_title:
-        # 2. DEFENSIVE FIX: Use .tolist().index() to guarantee a 0-based positional index
-        # This index is required for looking up the row in cosine_sim (0 to N-1)
+        # Use .tolist().index() to guarantee a 0-based positional index
         try:
             selected_index = df['Title'].tolist().index(selected_title)
         except ValueError:
             st.error("Error finding article index. Check data consistency.")
             return
     else:
+        # Should not happen if article_titles is non-empty
         st.error("No article selected.")
         return
 
@@ -163,10 +172,10 @@ def app():
     
     st.header(f"Recommendations for: **{selected_title}**")
     
-    # 2. Get Recommendations
+    # 3. Get Recommendations
     recommendations_list = get_recommendations(selected_index, cosine_sim, df)
     
-    # 3. Display Results
+    # 4. Display Results
     if recommendations_list:
         st.subheader(f"Top {NUM_RECOMMENDATIONS} Most Similar Articles:")
         
@@ -191,7 +200,11 @@ def app():
         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__":
-    # Ensure Streamlit is run via the command line interface
     app()