Delete app.py

app.py

@@ -1,157 +0,0 @@
-import streamlit as st
-import plotly.graph_objects as go
-import pandas as pd
-import numpy as np
-import os
-import xgboost as xgb
-import shap
-
-st.set_page_config(page_title="FairValue Transfer Cap Estimator", layout="wide")
-
-st.title("FairValue Transfer Cap Estimator")
-st.markdown("A rigorous, data-driven 'Transfer Ceiling Calculator' grounded in ML and Hedonic Pricing Theory.")
-
-@st.cache_resource
-def load_data_and_model():
-    df_path = "data/processed/app_features.csv"
-    if not os.path.exists(df_path):
-        return None, None
-    df = pd.read_csv(df_path)
-    
-    # Standardize ALL possible market value names to match model
-    # We look for ANY column containing 'market_value' and 'eur'
-    mv_cols = [c for c in df.columns if 'market_value' in c.lower()]
-    if mv_cols:
-        target_col = next((c for c in mv_cols if 'eur' in c.lower()), mv_cols[0])
-        df.rename(columns={target_col: 'market_value_in_eur'}, inplace=True)
-    
-    # Deduplicate early
-    df = df.loc[:, ~df.columns.duplicated()].copy()
-    
-    # Load model
-    model = xgb.XGBRegressor()
-    try:
-        path = "fairvalue_xgboost.json"
-        if not os.path.exists(path):
-            path = "FairValue_xgboost.json"
-            
-        if os.path.exists(path):
-            model.load_model(path)
-        else:
-            return df, "MODEL_FILE_NOT_FOUND"
-    except Exception as e:
-        return df, f"LOAD_ERROR: {str(e)}"
-        
-    return df, model
-
-df, model = load_data_and_model()
-
-if isinstance(model, str):
-    st.error(f"⚠️ {model}")
-    st.stop()
-if df is None:
-    st.error("⚠️ Data file not found.")
-    st.stop()
-
-# ======= Sidebar =======
-st.sidebar.header("Player Transfer Profile")
-input_mode = st.sidebar.radio("Input Mode", ["Select Existing Player", "Create Custom Player"])
-
-name_col = next((c for c in ['name', 'name_x', 'Player_Name', 'Name'] if c in df.columns), None)
-
-if input_mode == "Select Existing Player":
-    if name_col:
-        player_list = sorted(df[name_col].unique().tolist())
-        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 name column missing.")
-        st.stop()
-        
-    st.sidebar.markdown("---")
-    st.sidebar.markdown("**Simulation Parameters**")
-    
-    # Use position-based access (iloc) for everything to avoid KeyError
-    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:
-        injury_default = max(0, min(500, int(player_data[injury_col].iloc[0])))
-    
-    contract_years = st.sidebar.slider("Contract Years Remaining", 0.5, 6.0, contract_default, 0.5)
-    age = st.sidebar.slider("Age", 16, 40, age_default)
-    injuries = st.sidebar.number_input("Injury missed days (24m)", 0, 500, injury_default)
-    
-else:
-    st.sidebar.markdown("---")
-    st.sidebar.markdown("**Custom Player Attributes**")
-    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)
-    
-    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['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)
-
-# Build X_infer with safety
-player_data['Contract_Years_Left'] = contract_years
-player_data['Age'] = age
-if 'Injury_Days_Total_24m' in player_data.columns:
-    player_data['Injury_Days_Total_24m'] = injuries
-
-expected_cols = model.feature_names_in_
-X_infer = player_data.reindex(columns=expected_cols, fill_value=0)
-
-if st.button("Calculate Prediction", type="primary"):
-    # SAFE CHECK FOR ANY KEYERRORS
-    mv_v = 0.0
-    if 'market_value_in_eur' in X_infer.columns:
-        mv_v = X_infer['market_value_in_eur'].iloc[0]
-    
-    if mv_v == 0:
-        st.warning("⚠️ Market Value is 0.0. Prediction may be inaccurate.")
-
-    log_pv = model.predict(X_infer)[0]
-    baseline_pv = np.expm1(log_pv)
-
-    # UI Logic
-    baseline_pv_m = baseline_pv / 1_000_000
-    conservative_bound = baseline_pv * 0.85
-    
-    risk_discount = 0.0
-    if contract_years < 1.5: risk_discount += 0.20
-    if age > 30: risk_discount += 0.15
-    if injuries > 60: risk_discount += 0.10
-    
-    hard_cap = conservative_bound * (1 - risk_discount)
-    hard_cap_m = hard_cap / 1_000_000
-
-    col1, col2 = st.columns([2, 1])
-    with col1:
-        st.subheader("Price Range Recommendation")
-        fig = go.Figure(go.Indicator(
-            mode="gauge+number+delta",
-            value=asking_price,
-            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 (Baseline)", f"£{baseline_pv_m:.1f}m")
-        st.metric("Recommended Hard Cap", f"£{hard_cap_m:.1f}m")
-        if asking_price > hard_cap_m:
-            st.error(f"Winner's Curse Risk: £{asking_price-hard_cap_m:.1f}m Overpay")
-
-st.markdown("---")
-st.subheader("Model Performance Assessment")
-st.markdown(f"**Training Set:** `{len(df):,}` transfers | **Features:** `{len(expected_cols)}` cols")
-st.markdown("**Validation MAE:** `~£23,980,000` | **Engine:** XGBoost + SHAP")