Update app.py

app.py

@@ -14,98 +14,131 @@ def make_clickable_model(model_name, link):
 
 def get_data():
     """
-    Downloads, processes, and returns the leaderboard data.
+    Downloads, processes, and returns the leaderboard data + status message.
     """
-    print("🔄 Downloading data...")
+    print("🔄 Starting download...")
     try:
-        # Download file from the source space
+        # 1. Download file
         file_path = hf_hub_download(repo_id=REPO_ID, filename=FILENAME, repo_type="space")
         
-        # Load CSV
-        df = pd.read_csv(file_path)
-        
-        # Clean column names (remove whitespace)
+        # 2. Load CSV
+        # utf-8-sig handles the BOM character if present
+        df = pd.read_csv(file_path, encoding='utf-8-sig')
         df.columns = df.columns.str.strip()
         
-        # Debug: Print columns to logs to verify they exist
-        print(f"Columns found: {df.columns.tolist()}")
-
-        # Rename columns to standard names
-        rename_map = {
-            'author/model_name': 'Model',
-            'Model Link': 'Link',
-            'UGI 🏆': 'UGI',
-            'NatInt 💡': 'NatInt',
-            'W/10 👍': 'W/10'
-        }
-        df = df.rename(columns=rename_map)
+        # 3. Fuzzy Column Matching (Robust against emojis)
+        # We look for columns that *contain* the keywords rather than exact match
+        def get_col(keyword):
+            matches = [c for c in df.columns if keyword.lower() in c.lower()]
+            return matches[0] if matches else None
+
+        model_col = get_col("author") or get_col("model")
+        link_col = get_col("link")
+        ugi_col = get_col("ugi")
+        natint_col = get_col("natint")
+        w10_col = get_col("w/10")
 
-        # Ensure required columns exist, create them if missing to prevent crash
-        for col in ['UGI', 'NatInt', 'W/10']:
-            if col not in df.columns:
-                df[col] = 0
-            else:
-                # Force numeric
-                df[col] = pd.to_numeric(df[col], errors='coerce').fillna(0)
+        # 4. Check if we found everything
+        if not all([model_col, ugi_col, natint_col, w10_col]):
+            missing = []
+            if not model_col: missing.append("Model")
+            if not ugi_col: missing.append("UGI")
+            if not natint_col: missing.append("NatInt")
+            if not w10_col: missing.append("W/10")
+            return pd.DataFrame(), f"❌ Error: Could not find columns: {', '.join(missing)}. Found: {list(df.columns)}"
 
-        # --- Calculate UGI Index ---
+        # 5. Clean Numeric Data
+        for col in [ugi_col, natint_col, w10_col]:
+            df[col] = pd.to_numeric(df[col], errors='coerce').fillna(0)
+
+        # 6. Calculate UGI Index
         # Formula: (UGI + NatInt) * (W/10)
-        df['UGI Index'] = (df['UGI'] + df['NatInt']) * df['W/10']
+        df['UGI Index'] = (df[ugi_col] + df[natint_col]) * df[w10_col]
         df['UGI Index'] = df['UGI Index'].round(2)
 
-        # Create Links
-        if 'Link' in df.columns:
-            df['Model'] = df.apply(lambda x: make_clickable_model(x['Model'], x['Link']), axis=1)
-            # Drop the raw link column to clean up UI
-            df = df.drop(columns=['Link'])
+        # 7. Format Links
+        if link_col:
+            df[model_col] = df.apply(lambda x: make_clickable_model(x[model_col], x[link_col]), axis=1)
 
-        # Sort by UGI Index High -> Low
+        # 8. Sort and Rank
         df = df.sort_values(by='UGI Index', ascending=False)
-
-        # Add Rank Column
         df.insert(0, 'Rank', range(1, len(df) + 1))
 
-        # Reorder Columns: Put Rank, Model, Index first
-        cols = ['Rank', 'Model', 'UGI Index', 'UGI', 'NatInt', 'W/10']
-        # Add whatever other columns are left
-        cols += [c for c in df.columns if c not in cols]
+        # 9. Renaming for display
+        final_cols = {
+            model_col: 'Model',
+            ugi_col: 'UGI',
+            natint_col: 'NatInt',
+            w10_col: 'W/10'
+        }
+        df = df.rename(columns=final_cols)
+
+        # 10. Select Columns to Display
+        display_cols = ['Rank', 'Model', 'UGI Index', 'UGI', 'NatInt', 'W/10']
+        # Add remaining columns if you want them
+        # extra_cols = [c for c in df.columns if c not in display_cols and c != link_col]
         
-        print(f"✅ Loaded {len(df)} rows.")
-        return df[cols]
+        final_df = df[display_cols]
+        
+        return final_df, f"✅ Successfully loaded {len(final_df)} models."
 
     except Exception as e:
-        print(f"❌ Error: {e}")
-        # Return a dataframe with the error so it shows in the UI
-        return pd.DataFrame({"Status": ["Error loading data"], "Details": [str(e)]})
+        print(f"Error: {e}")
+        return pd.DataFrame(), f"❌ Error: {str(e)}"
+
+# Global cache for search to use
+CACHED_DF = pd.DataFrame()
+
+def app_load():
+    """Called when app starts."""
+    global CACHED_DF
+    df, status = get_data()
+    CACHED_DF = df
+    return df, status
 
 def search(query):
-    """Search filter function"""
-    df = get_data()
-    if query:
-        return df[df['Model'].astype(str).str.contains(query, case=False, na=False)]
-    return df
+    """Filters the cached dataframe."""
+    if CACHED_DF.empty:
+        return CACHED_DF
+    
+    if not query:
+        return CACHED_DF
+    
+    # Filter
+    return CACHED_DF[CACHED_DF['Model'].astype(str).str.contains(query, case=False, na=False)]
 
 # --- UI ---
-with gr.Blocks(title="UGI Index Leaderboard") as demo:
+custom_css = """
+.gradio-container {max-width: 95% !important}
+footer {visibility: hidden}
+"""
+
+with gr.Blocks(css=custom_css, title="UGI Index Leaderboard") as demo:
     gr.Markdown("# 🏆 UGI Index Leaderboard")
-    gr.Markdown("Reordered by **UGI Index**: `(UGI + NatInt) * (W/10)`")
     
     with gr.Row():
-        search_box = gr.Textbox(label="Search Models", placeholder="Type model name...", scale=4)
-        refresh_btn = gr.Button("Refresh", scale=1)
+        status_box = gr.Textbox(label="Status", value="Initializing...", interactive=False, scale=4)
+        refresh_btn = gr.Button("Refresh Data", scale=1)
     
-    # Passing `value=get_data` tells Gradio to run this function immediately on load
+    with gr.Row():
+        search_box = gr.Textbox(label="Search Models", placeholder="Type model name...", interactive=True)
+
+    # Initialize with empty dataframe
     data_table = gr.Dataframe(
-        value=get_data, 
+        headers=['Rank', 'Model', 'UGI Index', 'UGI', 'NatInt', 'W/10'],
         datatype="markdown",
         interactive=False,
         wrap=True
     )
 
-    # Interactions
-    search_box.submit(fn=search, inputs=search_box, outputs=data_table)
+    # Wire up events
+    # 1. On Load: Fetch data, update table and status
+    demo.load(fn=app_load, outputs=[data_table, status_box])
+    
+    # 2. On Refresh: Fetch data again
+    refresh_btn.click(fn=app_load, outputs=[data_table, status_box])
+    
+    # 3. On Search: Filter existing data
     search_box.change(fn=search, inputs=search_box, outputs=data_table)
-    refresh_btn.click(fn=get_data, outputs=data_table)
 
-if __name__ == "__main__":
-    demo.launch()
+if __name__ == "__ma