Add total points columns and improve MCP tool names

- Add Total Pts and Last GW Pts to top predictions, value picks, and my team views
- Rename get_differentials to get_value_picks with clearer description
- Rename get_manager_team_predictions to get_my_team

app.py

@@ -341,7 +341,7 @@ def load_and_process_data():
             )
             manager_players_df = pd.merge(
                 manager_players_df,
-                final_predictions_df[['element', 'XGB Pred', 'difficulty', 'Next Opponent']],
+                final_predictions_df[['element', 'XGB Pred', 'Total Pts', 'Last GW Pts', 'difficulty', 'Next Opponent']],
                 on='element', how='left'
             )
         else:
@@ -379,7 +379,7 @@ def get_top_predictions(top_n: int = 10, position: Optional[str] = None) -> pd.D
     df = df.sort_values('XGB Pred', ascending=False).head(top_n)
 
     cols = ['player_name', 'team_name', 'position', 'value', 'XGB Pred',
-            'Pts Mean (5GW)', 'Trend', 'difficulty']
+            'Total Pts', 'Last GW Pts', 'Pts Mean (5GW)', 'Trend', 'difficulty']
 
     return df[cols]
 
@@ -443,9 +443,9 @@ def get_team_stats(team_name: Optional[str] = None) -> pd.DataFrame:
     return df[cols]
 
 
-def get_differentials(max_price: float = 10.0, min_predicted: float = 4.0, top_n: int = 10) -> pd.DataFrame:
+def get_value_picks(max_price: float = 10.0, min_predicted: float = 4.0, top_n: int = 10) -> pd.DataFrame:
     """
-    Find best differential players (high predicted points at low price).
+    Find high-value players (good predicted points relative to price).
 
     Args:
         max_price (float): Maximum player price in millions (default: 10.0)
@@ -453,7 +453,7 @@ def get_differentials(max_price: float = 10.0, min_predicted: float = 4.0, top_n
         top_n (int): Number of results to return (default: 10)
 
     Returns:
-        pd.DataFrame: Best differential players
+        pd.DataFrame: Best value players sorted by predicted points
     """
     df = final_predictions_df.copy()
 
@@ -461,17 +461,17 @@ def get_differentials(max_price: float = 10.0, min_predicted: float = 4.0, top_n
     df = df.sort_values('XGB Pred', ascending=False).head(top_n)
 
     cols = ['player_name', 'team_name', 'position', 'value', 'XGB Pred',
-            'Pts Mean (5GW)', 'Trend', 'difficulty']
+            'Total Pts', 'Last GW Pts', 'Pts Mean (5GW)', 'Trend', 'difficulty']
 
     return df[cols]
 
 
-def get_manager_team_predictions() -> pd.DataFrame:
+def get_my_team() -> pd.DataFrame:
     """
-    Get your current FPL manager team with predictions for next gameweek.
+    Get predictions for players in manager ID 8679881's team.
 
     Returns:
-        pd.DataFrame: Manager team with predictions
+        pd.DataFrame: Team players with predictions for next gameweek
     """
     return manager_players_df
 
@@ -535,7 +535,7 @@ with gr.Blocks(title=f"FPL GW {NEXT_GW} Predictor (MCP)") as demo:
         diff_output = gr.Dataframe()
 
         diff_btn.click(
-            fn=get_differentials,
+            fn=get_value_picks,
             inputs=[max_price, min_pred, diff_top_n],
             outputs=diff_output
         )
@@ -544,7 +544,7 @@ with gr.Blocks(title=f"FPL GW {NEXT_GW} Predictor (MCP)") as demo:
         mgr_btn = gr.Button("Load My Team")
         mgr_output = gr.Dataframe()
 
-        mgr_btn.click(fn=get_manager_team_predictions, outputs=mgr_output)
+        mgr_btn.click(fn=get_my_team, outputs=mgr_output)
 
 
 if __name__ == "__main__":