Upload 2 files

app.py

@@ -18,16 +18,15 @@ def load_data_and_model():
         return None, None
     df = pd.read_csv(df_path)
     
-    # Standardize ALL possible market value names to match model
-    # The common ones are market_value_in_eur, market_value_in_eur_x, market_value_in_eur_y
+    # Standardize ALL possible market value names
     mv_rename_map = {}
     for col in df.columns:
-        if 'market_value' in col.lower() and 'eur' in col.lower():
+        if 'market_value' in col.lower():
             mv_rename_map[col] = 'market_value_in_eur'
     if mv_rename_map:
         df.rename(columns=mv_rename_map, inplace=True)
     
-    # Deduplicate early
+    # Deduplicate
     df = df.loc[:, ~df.columns.duplicated()].copy()
     
     # Load model
@@ -38,9 +37,13 @@ def load_data_and_model():
             path = "FairValue_xgboost.json"
             
         if os.path.exists(path):
+            # Check file size to catch corrupted uploads
+            filesize = os.path.getsize(path)
+            if filesize < 100:
+                return df, f"CORRUPTED_MODEL (Size: {filesize} bytes. Is too small!)"
             model.load_model(path)
         else:
-            return df, f"MODEL_FILE_NOT_FOUND (Checked: {os.getcwd()})"
+            return df, f"MODEL_FILE_NOT_FOUND (Checked root for {path})"
     except Exception as e:
         return df, f"LOAD_ERROR: {str(e)}"
         
@@ -50,10 +53,9 @@ df, model = load_data_and_model()
 
 if isinstance(model, str):
     st.error(f"⚠️ {model}")
-    st.info("Ensure the model file is uploaded to the root of your Space.")
     st.stop()
 if df is None:
-    st.error("⚠️ Data file not found at 'data/processed/app_features.csv'")
+    st.error("⚠️ Data file not found.")
     st.stop()
 
 # ======= Sidebar =======
@@ -68,15 +70,10 @@ if input_mode == "Select Existing Player":
         selected_name = st.sidebar.selectbox("Target Database Player", player_list)
         player_data = df[df[name_col] == selected_name].iloc[0:1].copy()
     else:
-        st.sidebar.error("Player names column not found.")
         st.stop()
-        
-    st.sidebar.markdown("---")
-    st.sidebar.markdown("**Simulation Parameters**")
     
     contract_default = max(0.5, min(6.0, float(player_data['Contract_Years_Left'].iloc[0])))
     age_default = max(16, min(40, int(player_data['Age'].iloc[0])))
-    
     injury_col = next((c for c in ['Injury_Days_Total_24m', 'Injury_Days'] if c in player_data.columns), None)
     injury_default = 0
     if injury_col:
@@ -87,43 +84,33 @@ if input_mode == "Select Existing Player":
     injuries = st.sidebar.number_input("Injury missed days (24m)", 0, 500, injury_default)
     
 else:
-    st.sidebar.markdown("---")
-    st.sidebar.markdown("**Custom Player Attributes**")
-    # MEDIAN fallback to ensure all 20+ columns are filled
     player_data = df.median(numeric_only=True).to_frame().T
-    
     contract_years = st.sidebar.slider("Contract Years Remaining", 0.5, 6.0, 2.0, 0.5)
     age = st.sidebar.slider("Age", 16, 40, 24)
     injuries = st.sidebar.number_input("Injury missed days (24m)", 0, 500, 10)
     
-    # Try to find the market value column to let user edit it
-    mv_col = 'market_value_in_eur'
-    if mv_col in player_data.columns:
+    if 'market_value_in_eur' in player_data.columns:
         m_val = st.sidebar.number_input("Current Market Value Estimation (£m)", 1.0, 200.0, 20.0)
-        player_data[mv_col] = (m_val * 1_000_000) / 0.85
+        player_data['market_value_in_eur'] = (m_val * 1_000_000) / 0.85
 
 asking_price = st.sidebar.number_input("Selling Club Asking Price (£m)", 1.0, 300.0, 45.0)
 
-# Apply overrides
+# Build X_infer
+expected_cols = model.feature_names_in_
 player_data['Contract_Years_Left'] = contract_years
 player_data['Age'] = age
-inj_col_to_set = next((c for c in ['Injury_Days_Total_24m', 'Injury_Days'] if c in player_data.columns), 'Injury_Days_Total_24m')
-player_data[inj_col_to_set] = injuries
+if 'Injury_Days_Total_24m' in player_data.columns:
+    player_data['Injury_Days_Total_24m'] = injuries
 
-# Prepare inference payload
-expected_cols = model.feature_names_in_
 X_infer = player_data.reindex(columns=expected_cols, fill_value=0)
 
 if st.button("Calculate Prediction", type="primary"):
-    # Debug: Check if the market value is zero
-    if X_infer['market_value_in_eur'].iloc[0] == 0:
-        st.warning("⚠️ Market Value feature is 0.0! The model will underestimate. Checking input alignment...")
-        st.write("Columns available in player_data:", player_data.columns.tolist())
-
-    log_pv = model.predict(X_infer)[0]
+    # Debugging Visibility
+    raw_preds = model.predict(X_infer)
+    log_pv = raw_preds[0]
     baseline_pv = np.expm1(log_pv)
 
-    # Hard Cap logic
+    # UI logic
     conservative_bound = baseline_pv * 0.85 
     risk_discount_pct = 0.0
     if contract_years < 1.5: risk_discount_pct += 0.20
@@ -142,37 +129,25 @@ if st.button("Calculate Prediction", type="primary"):
         fig = go.Figure(go.Indicator(
             mode="gauge+number+delta",
             value=asking_price,
-            delta={'reference': hard_cap_m, 'increasing': {'color': "red"}, 'decreasing': {'color': "green"}},
-            title={'text': "Asking Price vs Calculated Hard Cap (£m)"},
-            gauge={
-                'axis': {'range': [0, max(asking_price, hard_cap_m) * 1.5]},
-                'steps': [
-                    {'range': [0, hard_cap_m], 'color': "rgba(0, 255, 0, 0.3)"},
-                    {'range': [hard_cap_m, hard_cap_m*1.2], 'color': "rgba(255, 255, 0, 0.3)"},
-                ],
-                'threshold': {'line': {'color': "white", 'width': 4}, 'thickness': 0.75, 'value': hard_cap_m}
-            }
+            delta={'reference': hard_cap_m, 'increasing': {'color': "red"}},
+            title={'text': "Asking Price vs Hard Cap (£m)"},
+            gauge={'axis': {'range': [0, max(asking_price, 100)]}, 'threshold': {'line': {'color': "white", 'width': 4}, 'value': hard_cap_m}}
         ))
         st.plotly_chart(fig, use_container_width=True)
 
     with col2:
         st.subheader("Metrics Breakdown")
         st.metric("Predicted Market Value (ML Baseline)", f"£{baseline_pv_m:.1f}m")
-        if risk_discount_pct > 0:
-            st.metric("Risk Penalty Applied", f"-£{discount_val/1_000_000:.1f}m", f"-{risk_discount_pct*100:.0f}% Risk penalty!")
-        else:
-            st.metric("Risk Penalty Applied", f"£0m", "0% Risk")
         st.metric("Recommended Hard Cap", f"£{hard_cap_m:.1f}m")
-        
         if asking_price > hard_cap_m:
-            st.error(f"Winner's Curse Risk: The asking price is £{asking_price - hard_cap_m:.1f}m OVER the Cap.")
-        else:
-            st.success("Asking price is within acceptable margins.")
+            st.error(f"Winner's Curse Risk: £{asking_price - hard_cap_m:.1f}m Overpay.")
+
+    with st.expander("🔬 Technical Diagnostics (FOR DEBUGGING)"):
+        st.write("Raw Log-Prediction from Model:", log_pv)
+        st.write("Input Feature Vector (X_infer):", X_infer)
+        if log_pv == 0 and X_infer['market_value_in_eur'].iloc[0] > 0:
+            st.error("CRITICAL: The model is receiving data but returning exactly 0.0. This means the uploaded model file is likely empty or corrupted.")
 
-    # SHAP / Diagnostics
-    with st.expander("Show Model Input Diagnostics"):
-        st.write("X_infer Payload:", X_infer)
-    
     st.subheader("Algorithmic Interpretability (SHAP)")
     try:
         explainer = shap.TreeExplainer(model)
@@ -180,13 +155,9 @@ if st.button("Calculate Prediction", type="primary"):
         shap_df = pd.DataFrame({'Feature': X_infer.columns, 'Impact': shap_values.values[0]}).sort_values(by='Impact', ascending=False)
         st.dataframe(shap_df.head(10), use_container_width=True)
     except:
-        st.info("Global Feature Importances shown as fallback.")
-        imp_df = pd.DataFrame({'Feature': expected_cols, 'Weight': model.feature_importances_}).sort_values(by='Weight', ascending=False)
-        st.dataframe(imp_df.head(10), use_container_width=True)
+        st.warning("SHAP Error. Model file/version mismatch.")
 
 st.markdown("---")
 st.subheader("Model Performance Assessment")
-st.markdown(f"**Training Set Size:** `{len(df):,}` verified transfers")
-st.markdown(f"**Features Engined:** `{len(expected_cols)}` columns")
-st.markdown("**Validation MAE (Mean Absolute Error):** `~£23,980,000` *(Statistical Range)*")
-st.caption("Training occurred utilizing a 5-Folds RandomizedSearchCV across 40 hyperparameter iterations.")
+st.markdown(f"**Training Set Size:** `{len(df):,}` transfers | **Features:** `{len(expected_cols)}` cols")
+st.markdown("**Validation MAE:** `~£23,980,000` | **Engine:** XGBoost + SHAP")