Update app.py

app.py

@@ -3,7 +3,6 @@ import pandas as pd
 import numpy as np
 import plotly.graph_objects as go
 import plotly.express as px
-from io import StringIO
 
 # ============================================================
 # LOAD DATA
@@ -23,105 +22,99 @@ df.columns = (
 )
 
 # ============================================================
-# COLUMN SETUP BASED ON YOUR SPREADSHEET
+# COLUMN SETUP
 # ============================================================
 
-PLAYER_COL = "player_name"
-TEAM_COL = "team_name"
-COMP_COL = "competition_name"
-POSITION_COL = "primary_position"
-AGE_COL = "age"
-SEASON_COL = "season_name"
+PLAYER_COL      = "player_name"
+TEAM_COL        = "team_name"
+COMP_COL        = "competition_name"
+POSITION_COL    = "primary_position"
+AGE_COL         = "age"
+SEASON_COL      = "season_name"
 
-MARKET_VALUE_COL = "market_value_eur"
-CONTRACT_COL = "contract_status"
-HEIGHT_COL = "player_height"
-MINUTES_COL = "player_season_minutes"
-ATTAINABILITY_COL = "attainability"
+HEIGHT_COL      = "player_height"
+MINUTES_COL     = "player_season_minutes"
 
-# Main metrics shown in search/profile tables
-KEY_METRICS = [
-    "player_season_goals_90",
-    "player_season_assists_90",
-    "player_season_np_xg_90",
-    "player_season_xa_90",
-    "player_season_passing_ratio",
-    "player_season_defensive_actions_90",
-    "player_season_pressures_90",
-    "player_season_key_passes_90",
-    "player_season_dribbles_90",
-    "player_season_obv_90"
-]
+# GK-specific scoring columns
+ARCHETYPE_COL       = "best_gk_archetype"
+ARCHETYPE_SCORE_COL = "best_gk_archetype_score"
+GK_SCORE_COL        = "gk_score"
 
-# Category scores for scouting profile
+# GK category scores (gk_cat_*)
 CATEGORY_METRICS = [
-    "cat_defensive_ability",
-    "cat_aerial_ability",
-    "cat_finishing",
-    "cat_chance_creation",
-    "cat_dribbling",
-    "cat_ball_progression",
-    "cat_passing",
-    "cat_defensive_intelligence",
-    "cat_pressing_work_rate",
-    "cat_possession_security",
-    "cat_goal_threat",
-    "cat_wide_delivery",
-    "cat_impact",
-    "cat_discipline"
+    "gk_cat_shot_stopping",
+    "gk_cat_sweeping",
+    "gk_cat_short_passing",
+    "gk_cat_long_passing",
+    "gk_cat_ball_claiming",
+    "gk_cat_overall_value",
 ]
 
-# Archetype/scoring system columns
+# GK archetype scores
 SCORING_METRICS = [
-    "defensive_mid_score",
-    "deep_lying_playmaker_score",
-    "box_to_box_score",
-    "advanced_playmaker_score",
-    "wide_mid_score",
-    "attacking_runner_score",
-    "best_midfield_archetype",
-    "best_midfield_archetype_score",
-    "raw_score",
-    "attainability"
+    "shot_stopper_score",
+    "sweeper_keeper_score",
+    "ball_playing_gk_score",
+    "organiser_score",
+    "best_gk_archetype",
+    "best_gk_archetype_score",
+    "gk_score",
+]
+
+# Key per-90 / ratio metrics shown in tables and profile
+KEY_METRICS = [
+    "player_season_save_ratio",
+    "player_season_gsaa_90",
+    "player_season_gsaa",
+    "player_season_shots_faced_90",
+    "player_season_goals_faced_90",
+    "player_season_errors_90",
+    "player_season_clcaa",
+    "player_season_da_aggressive_distance",
+    "player_season_passing_ratio",
+    "player_season_long_ball_ratio",
+    "player_season_aerial_ratio",
+    "player_season_obv_gk_90",
+    "player_season_obv_90",
+    "player_season_pressures_90",
 ]
 
+# Radar uses the GK category scores
 RADAR_METRICS = [
-    "cat_defensive_ability",
-    "cat_chance_creation",
-    "cat_dribbling",
-    "cat_ball_progression",
-    "cat_passing",
-    "cat_defensive_intelligence",
-    "cat_pressing_work_rate",
-    "cat_possession_security",
-    "cat_goal_threat",
-    "cat_impact"
+    "gk_cat_shot_stopping",
+    "gk_cat_sweeping",
+    "gk_cat_short_passing",
+    "gk_cat_long_passing",
+    "gk_cat_ball_claiming",
+    "gk_cat_overall_value",
 ]
 
+# Percentile bar chart metrics
 PERCENTILE_METRICS = [
-    "player_season_goals_90",
-    "player_season_assists_90",
-    "player_season_np_xg_90",
-    "player_season_xa_90",
-    "player_season_key_passes_90",
+    "player_season_save_ratio",
+    "player_season_gsaa_90",
+    "player_season_shots_faced_90",
+    "player_season_goals_faced_90",
+    "player_season_errors_90",
+    "player_season_clcaa",
+    "player_season_da_aggressive_distance",
     "player_season_passing_ratio",
-    "player_season_defensive_actions_90",
-    "player_season_pressures_90",
-    "player_season_dribbles_90",
-    "player_season_obv_90",
-    "attainability"
+    "player_season_long_ball_ratio",
+    "player_season_aerial_ratio",
+    "player_season_obv_gk_90",
+    "gk_cat_shot_stopping",
+    "gk_cat_sweeping",
+    "gk_cat_overall_value",
 ]
 
+# Fit score calculator — weights map to these columns
 FIT_SCORE_METRICS = [
-    "cat_defensive_ability",
-    "cat_chance_creation",
-    "cat_ball_progression",
-    "cat_passing",
-    "cat_pressing_work_rate",
-    "cat_possession_security",
-    "cat_goal_threat",
-    "cat_impact",
-    "attainability"
+    "gk_cat_shot_stopping",
+    "gk_cat_sweeping",
+    "gk_cat_short_passing",
+    "gk_cat_long_passing",
+    "gk_cat_ball_claiming",
+    "gk_cat_overall_value",
 ]
 
 # ============================================================
@@ -132,28 +125,25 @@ def available_cols(cols):
     return [c for c in cols if c in df.columns]
 
 def label_col(col):
-    return col.replace("player_season_", "").replace("_90", " per 90").replace("_", " ").title()
-
-def format_money(x):
-    try:
-        if pd.isna(x):
-            return "Not listed"
-        x = float(x)
-        if x >= 1000000:
-            return f"€{x/1000000:.1f}M"
-        if x >= 1000:
-            return f"€{x/1000:.0f}K"
-        return f"€{x:.0f}"
-    except:
-        return "Not listed"
+    return (
+        col.replace("player_season_", "")
+           .replace("gk_cat_", "")
+           .replace("_90", " per 90")
+           .replace("_", " ")
+           .title()
+    )
 
 def safe_numeric(data, col):
     if col in data.columns:
         return pd.to_numeric(data[col], errors="coerce")
     return pd.Series(dtype=float)
 
-for col in available_cols(KEY_METRICS + CATEGORY_METRICS + SCORING_METRICS + PERCENTILE_METRICS + FIT_SCORE_METRICS):
-    if col != "best_midfield_archetype":
+# Coerce numeric columns
+_numeric_cols = available_cols(
+    KEY_METRICS + CATEGORY_METRICS + SCORING_METRICS + PERCENTILE_METRICS + FIT_SCORE_METRICS
+)
+for col in _numeric_cols:
+    if col != ARCHETYPE_COL:
         df[col] = pd.to_numeric(df[col], errors="coerce")
 
 if AGE_COL in df.columns:
@@ -163,72 +153,49 @@ if AGE_COL in df.columns:
 # DROPDOWN OPTIONS
 # ============================================================
 
-player_options = sorted(df[PLAYER_COL].dropna().astype(str).unique().tolist())
-competition_options = ["All"] + sorted(df[COMP_COL].dropna().astype(str).unique().tolist())
-team_options = ["All"] + sorted(df[TEAM_COL].dropna().astype(str).unique().tolist())
-position_options = ["All"] + sorted(df[POSITION_COL].dropna().astype(str).unique().tolist())
+player_options     = sorted(df[PLAYER_COL].dropna().astype(str).unique().tolist())
+competition_options = sorted(df[COMP_COL].dropna().astype(str).unique().tolist())
+team_options        = sorted(df[TEAM_COL].dropna().astype(str).unique().tolist())
+position_options    = sorted(df[POSITION_COL].dropna().astype(str).unique().tolist())
 
 age_min = int(np.floor(df[AGE_COL].min())) if AGE_COL in df.columns else 15
-age_max = int(np.ceil(df[AGE_COL].max())) if AGE_COL in df.columns else 45
+age_max = int(np.ceil(df[AGE_COL].max()))  if AGE_COL in df.columns else 45
 
 metric_options = available_cols(KEY_METRICS + CATEGORY_METRICS + SCORING_METRICS)
 
 shortlist = []
 
 # ============================================================
-# ============================================================
-# REPLACED YOUR PLAYER SEARCH FUNCTION WITH THIS
+# PLAYER SEARCH
 # ============================================================
 
 def search_players(search, competitions, teams, positions, min_age, max_age, min_minutes):
     data = df.copy()
 
-    # Player name search
     if search and PLAYER_COL in data.columns:
-        data = data[
-            data[PLAYER_COL]
-            .astype(str)
-            .str.contains(str(search), case=False, na=False)
-        ]
+        data = data[data[PLAYER_COL].astype(str).str.contains(str(search), case=False, na=False)]
 
-    # Multi-select competition filter
     if competitions and COMP_COL in data.columns:
         data = data[data[COMP_COL].astype(str).isin(competitions)]
 
-    # Multi-select team filter
     if teams and TEAM_COL in data.columns:
         data = data[data[TEAM_COL].astype(str).isin(teams)]
 
-    # Multi-select position filter
     if positions and POSITION_COL in data.columns:
         data = data[data[POSITION_COL].astype(str).isin(positions)]
 
-    # Age filters
     if AGE_COL in data.columns:
         data[AGE_COL] = pd.to_numeric(data[AGE_COL], errors="coerce")
-        data = data[
-            (data[AGE_COL] >= min_age) &
-            (data[AGE_COL] <= max_age)
-        ]
+        data = data[(data[AGE_COL] >= min_age) & (data[AGE_COL] <= max_age)]
 
-    # Minimum minutes filter
     if MINUTES_COL in data.columns:
         data[MINUTES_COL] = pd.to_numeric(data[MINUTES_COL], errors="coerce")
         data = data[data[MINUTES_COL].fillna(0) >= min_minutes]
 
     table_cols = available_cols([
-        PLAYER_COL,
-        TEAM_COL,
-        COMP_COL,
-        POSITION_COL,
-        AGE_COL,
-        MINUTES_COL,
-        MARKET_VALUE_COL,
-        CONTRACT_COL,
-        "best_midfield_archetype",
-        "best_midfield_archetype_score",
-        "raw_score",
-        ATTAINABILITY_COL
+        PLAYER_COL, TEAM_COL, COMP_COL, POSITION_COL,
+        AGE_COL, MINUTES_COL,
+        ARCHETYPE_COL, ARCHETYPE_SCORE_COL, GK_SCORE_COL,
     ] + KEY_METRICS)
 
     out = data[table_cols].copy()
@@ -236,31 +203,17 @@ def search_players(search, competitions, teams, positions, min_age, max_age, min
     if out.empty:
         return pd.DataFrame({"Message": ["No players found. Try clearing some filters."]})
 
-    if MARKET_VALUE_COL in out.columns:
-        out[MARKET_VALUE_COL] = out[MARKET_VALUE_COL].apply(format_money)
-
     if AGE_COL in out.columns:
         out[AGE_COL] = pd.to_numeric(out[AGE_COL], errors="coerce").round(1)
 
     numeric_cols = out.select_dtypes(include=np.number).columns
     out[numeric_cols] = out[numeric_cols].round(2)
 
-    if ATTAINABILITY_COL in out.columns:
-        out = out.sort_values(by=ATTAINABILITY_COL, ascending=False)
+    if GK_SCORE_COL in out.columns:
+        out = out.sort_values(by=GK_SCORE_COL, ascending=False)
 
     return out.reset_index(drop=True)
 
-    if MARKET_VALUE_COL in out.columns:
-        out[MARKET_VALUE_COL] = out[MARKET_VALUE_COL].apply(format_money)
-
-    if AGE_COL in out.columns:
-        out[AGE_COL] = out[AGE_COL].round(1)
-
-    numeric_cols = out.select_dtypes(include=np.number).columns
-    out[numeric_cols] = out[numeric_cols].round(2)
-
-    return out.sort_values(by=ATTAINABILITY_COL, ascending=False).reset_index(drop=True)
-
 # ============================================================
 # PLAYER PROFILE
 # ============================================================
@@ -273,7 +226,6 @@ def get_player_row(player):
 
 def player_profile(player):
     row = get_player_row(player)
-
     if row is None:
         return "Select a player to view their profile."
 
@@ -284,19 +236,22 @@ def player_profile(player):
     lines.append("## Player Details")
     lines.append(f"- **Position:** {row.get(POSITION_COL, 'N/A')}")
     lines.append(f"- **Age:** {round(row.get(AGE_COL, np.nan), 1) if pd.notna(row.get(AGE_COL, np.nan)) else 'N/A'}")
-    lines.append(f"- **Height:** {row.get(HEIGHT_COL, 'N/A')}")
-    lines.append(f"- **Market Value:** {format_money(row.get(MARKET_VALUE_COL, np.nan))}")
-    lines.append(f"- **Contract Status:** {row.get(CONTRACT_COL, 'N/A')}")
+    lines.append(f"- **Height:** {row.get(HEIGHT_COL, 'N/A')} cm")
     lines.append(f"- **Minutes:** {round(row.get(MINUTES_COL, 0), 0)}")
+    lines.append(f"- **Appearances:** {row.get('player_season_appearances', 'N/A')}")
     lines.append("")
-    lines.append("## Scoring System")
-    lines.append(f"- **Best Midfield Archetype:** {row.get('best_midfield_archetype', 'N/A')}")
-    lines.append(f"- **Best Archetype Score:** {round(row.get('best_midfield_archetype_score', np.nan), 2) if pd.notna(row.get('best_midfield_archetype_score', np.nan)) else 'N/A'}")
-    lines.append(f"- **Raw Player Score:** {round(row.get('raw_score', np.nan), 2) if pd.notna(row.get('raw_score', np.nan)) else 'N/A'}")
-    lines.append(f"- **Attainability Score:** {round(row.get(ATTAINABILITY_COL, np.nan), 2) if pd.notna(row.get(ATTAINABILITY_COL, np.nan)) else 'N/A'}")
+    lines.append("## GK Scoring")
+    lines.append(f"- **Best Archetype:** {row.get(ARCHETYPE_COL, 'N/A')}")
+    lines.append(f"- **Best Archetype Score:** {round(row.get(ARCHETYPE_SCORE_COL, np.nan), 2) if pd.notna(row.get(ARCHETYPE_SCORE_COL, np.nan)) else 'N/A'}")
+    lines.append(f"- **Overall GK Score:** {round(row.get(GK_SCORE_COL, np.nan), 2) if pd.notna(row.get(GK_SCORE_COL, np.nan)) else 'N/A'}")
+    lines.append("")
+    lines.append("## Archetype Scores")
+    for col in ["shot_stopper_score", "sweeper_keeper_score", "ball_playing_gk_score", "organiser_score"]:
+        val = row.get(col, np.nan)
+        if col in df.columns and pd.notna(val):
+            lines.append(f"- **{label_col(col.replace('_score', ''))}:** {round(val, 2)}")
     lines.append("")
     lines.append("## Key Season Stats")
-
     for col in available_cols(KEY_METRICS):
         value = row.get(col, np.nan)
         if pd.notna(value):
@@ -306,7 +261,6 @@ def player_profile(player):
 
 def category_table(player):
     row = get_player_row(player)
-
     if row is None:
         return pd.DataFrame({"Message": ["Select a player."]})
 
@@ -315,10 +269,13 @@ def category_table(player):
         value = row.get(col, np.nan)
         if pd.notna(value):
             rows.append({
-                "Category": label_col(col.replace("cat_", "")),
+                "Category": label_col(col),
                 "Score": round(value, 2)
             })
 
+    if not rows:
+        return pd.DataFrame({"Message": ["No category data available."]})
+
     return pd.DataFrame(rows).sort_values("Score", ascending=False)
 
 # ============================================================
@@ -327,48 +284,31 @@ def category_table(player):
 
 def radar_chart(player):
     row = get_player_row(player)
-
     if row is None:
         return go.Figure()
 
     metrics = available_cols(RADAR_METRICS)
-
     if len(metrics) < 3:
         fig = go.Figure()
         fig.update_layout(title="Need at least 3 radar metrics.")
         return fig
 
-    comp = row[COMP_COL]
-    pos = row[POSITION_COL]
+    comp  = row[COMP_COL]
+    group = df[df[COMP_COL] == comp].copy()
 
-    group = df[(df[COMP_COL] == comp) & (df[POSITION_COL] == pos)].copy()
-
-    labels = [label_col(m.replace("cat_", "")) for m in metrics]
-    player_values = [row[m] for m in metrics]
-    avg_values = [group[m].mean() for m in metrics]
+    labels        = [label_col(m) for m in metrics]
+    player_values = [row[m] if pd.notna(row[m]) else 0 for m in metrics]
+    avg_values    = [group[m].mean() for m in metrics]
 
     fig = go.Figure()
-
-    fig.add_trace(go.Scatterpolar(
-        r=player_values,
-        theta=labels,
-        fill="toself",
-        name=str(player)
-    ))
-
-    fig.add_trace(go.Scatterpolar(
-        r=avg_values,
-        theta=labels,
-        fill="toself",
-        name=f"{pos} Avg in {comp}"
-    ))
+    fig.add_trace(go.Scatterpolar(r=player_values, theta=labels, fill="toself", name=str(player)))
+    fig.add_trace(go.Scatterpolar(r=avg_values,    theta=labels, fill="toself", name=f"GK Avg in {comp}"))
 
     fig.update_layout(
-        title=f"{player} vs Position/Competition Average",
-        polar=dict(radialaxis=dict(visible=True)),
+        title=f"{player} vs Competition Average",
+        polar=dict(radialaxis=dict(visible=True, range=[0, 100])),
         showlegend=True
     )
-
     return fig
 
 # ============================================================
@@ -377,45 +317,33 @@ def radar_chart(player):
 
 def percentile_chart(player):
     row = get_player_row(player)
-
     if row is None:
         return go.Figure()
 
-    comp = row[COMP_COL]
-    pos = row[POSITION_COL]
-    group = df[(df[COMP_COL] == comp) & (df[POSITION_COL] == pos)].copy()
+    comp  = row[COMP_COL]
+    group = df[df[COMP_COL] == comp].copy()
 
     rows = []
-
     for metric in available_cols(PERCENTILE_METRICS):
-        value = row.get(metric, np.nan)
+        value  = row.get(metric, np.nan)
         values = pd.to_numeric(group[metric], errors="coerce").dropna()
-
         if pd.notna(value) and len(values) > 1:
             pct = (values < value).mean() * 100
-            rows.append({
-                "Metric": label_col(metric),
-                "Percentile": round(pct, 1),
-                "Value": round(value, 2)
-            })
+            rows.append({"Metric": label_col(metric), "Percentile": round(pct, 1), "Value": round(value, 2)})
 
-    plot_df = pd.DataFrame(rows)
-
-    if plot_df.empty:
+    if not rows:
         fig = go.Figure()
         fig.update_layout(title="No percentile data available.")
         return fig
 
+    plot_df = pd.DataFrame(rows)
     fig = px.bar(
         plot_df.sort_values("Percentile"),
-        x="Percentile",
-        y="Metric",
-        orientation="h",
+        x="Percentile", y="Metric", orientation="h",
         hover_data=["Value"],
-        title=f"{player} Percentiles vs Same Position and Competition",
+        title=f"{player} Percentiles vs Same Competition",
         range_x=[0, 100]
     )
-
     fig.update_layout(yaxis_title="", xaxis_title="Percentile")
     return fig
 
@@ -431,26 +359,16 @@ def performance_chart(player, metric):
 
     if SEASON_COL not in df.columns or row_data[SEASON_COL].nunique() <= 1:
         fig = go.Figure()
-        fig.add_trace(go.Bar(
-            x=[label_col(metric)],
-            y=[row_data.iloc[0][metric]]
-        ))
+        fig.add_trace(go.Bar(x=[label_col(metric)], y=[row_data.iloc[0][metric]]))
         fig.update_layout(
-            title="Only one season is currently in this file, so a true over-time line chart is not available yet.",
+            title="Only one season in this file — showing single-season value.",
             yaxis_title=label_col(metric)
         )
         return fig
 
     row_data[metric] = pd.to_numeric(row_data[metric], errors="coerce")
-
-    fig = px.line(
-        row_data,
-        x=SEASON_COL,
-        y=metric,
-        markers=True,
-        title=f"{player}: {label_col(metric)} Over Time"
-    )
-
+    fig = px.line(row_data, x=SEASON_COL, y=metric, markers=True,
+                  title=f"{player}: {label_col(metric)} Over Time")
     return fig
 
 # ============================================================
@@ -459,82 +377,61 @@ def performance_chart(player, metric):
 
 def compare_players(player_1, player_2, player_3):
     players = [p for p in [player_1, player_2, player_3] if p]
-
     if not players:
         return pd.DataFrame({"Message": ["Select at least one player."]})
 
     data = df[df[PLAYER_COL].astype(str).isin(players)].copy()
 
     cols = available_cols([
-        PLAYER_COL,
-        TEAM_COL,
-        COMP_COL,
-        POSITION_COL,
-        AGE_COL,
-        MINUTES_COL,
-        MARKET_VALUE_COL,
-        CONTRACT_COL,
-        "best_midfield_archetype",
-        "best_midfield_archetype_score",
-        "raw_score",
-        ATTAINABILITY_COL
+        PLAYER_COL, TEAM_COL, COMP_COL, POSITION_COL,
+        AGE_COL, MINUTES_COL, HEIGHT_COL,
+        ARCHETYPE_COL, ARCHETYPE_SCORE_COL, GK_SCORE_COL,
+        "shot_stopper_score", "sweeper_keeper_score",
+        "ball_playing_gk_score", "organiser_score",
     ] + KEY_METRICS + CATEGORY_METRICS)
 
     out = data[cols].copy()
-
-    if MARKET_VALUE_COL in out.columns:
-        out[MARKET_VALUE_COL] = out[MARKET_VALUE_COL].apply(format_money)
-
     numeric_cols = out.select_dtypes(include=np.number).columns
     out[numeric_cols] = out[numeric_cols].round(2)
-
     return out.reset_index(drop=True)
 
 def comparison_radar(player_1, player_2, player_3):
     players = [p for p in [player_1, player_2, player_3] if p]
     metrics = available_cols(RADAR_METRICS)
-
     fig = go.Figure()
 
     if not players or len(metrics) < 3:
         fig.update_layout(title="Select players to compare.")
         return fig
 
-    labels = [label_col(m.replace("cat_", "")) for m in metrics]
-
+    labels = [label_col(m) for m in metrics]
     for player in players:
         row = get_player_row(player)
         if row is not None:
             fig.add_trace(go.Scatterpolar(
-                r=[row[m] for m in metrics],
-                theta=labels,
-                fill="toself",
-                name=str(player)
+                r=[row[m] if pd.notna(row[m]) else 0 for m in metrics],
+                theta=labels, fill="toself", name=str(player)
             ))
 
     fig.update_layout(
         title="Side-by-Side Radar Comparison",
-        polar=dict(radialaxis=dict(visible=True)),
+        polar=dict(radialaxis=dict(visible=True, range=[0, 100])),
         showlegend=True
     )
-
     return fig
 
 # ============================================================
 # FIT SCORE CALCULATOR
 # ============================================================
 
-def fit_score(defense_w, chance_w, progression_w, passing_w, pressing_w, security_w, goal_w, impact_w, attain_w):
+def fit_score(shot_stopping_w, sweeping_w, short_passing_w, long_passing_w, ball_claiming_w, overall_value_w):
     weights = {
-        "cat_defensive_ability": defense_w,
-        "cat_chance_creation": chance_w,
-        "cat_ball_progression": progression_w,
-        "cat_passing": passing_w,
-        "cat_pressing_work_rate": pressing_w,
-        "cat_possession_security": security_w,
-        "cat_goal_threat": goal_w,
-        "cat_impact": impact_w,
-        "attainability": attain_w
+        "gk_cat_shot_stopping": shot_stopping_w,
+        "gk_cat_sweeping":       sweeping_w,
+        "gk_cat_short_passing":  short_passing_w,
+        "gk_cat_long_passing":   long_passing_w,
+        "gk_cat_ball_claiming":  ball_claiming_w,
+        "gk_cat_overall_value":  overall_value_w,
     }
 
     data = df.copy()
@@ -544,42 +441,26 @@ def fit_score(defense_w, chance_w, progression_w, passing_w, pressing_w, securit
         return pd.DataFrame({"Message": ["At least one weight must be above 0."]})
 
     score = 0
-
     for col, weight in weights.items():
         if col in data.columns:
             values = pd.to_numeric(data[col], errors="coerce")
-            min_v = values.min()
-            max_v = values.max()
-
+            min_v, max_v = values.min(), values.max()
             if pd.notna(min_v) and pd.notna(max_v) and max_v != min_v:
                 normalized = ((values - min_v) / (max_v - min_v)) * 100
             else:
                 normalized = values
-
             score += normalized.fillna(0) * weight
 
     data["custom_fit_score"] = score / total_weight
 
     cols = available_cols([
-        PLAYER_COL,
-        TEAM_COL,
-        COMP_COL,
-        POSITION_COL,
-        AGE_COL,
-        MARKET_VALUE_COL,
-        "best_midfield_archetype",
-        "raw_score",
-        ATTAINABILITY_COL
+        PLAYER_COL, TEAM_COL, COMP_COL, AGE_COL, MINUTES_COL,
+        ARCHETYPE_COL, ARCHETYPE_SCORE_COL, GK_SCORE_COL,
     ]) + ["custom_fit_score"]
 
     out = data[cols].sort_values("custom_fit_score", ascending=False).head(25).copy()
-
-    if MARKET_VALUE_COL in out.columns:
-        out[MARKET_VALUE_COL] = out[MARKET_VALUE_COL].apply(format_money)
-
     numeric_cols = out.select_dtypes(include=np.number).columns
     out[numeric_cols] = out[numeric_cols].round(2)
-
     return out.reset_index(drop=True)
 
 # ============================================================
@@ -588,57 +469,33 @@ def fit_score(defense_w, chance_w, progression_w, passing_w, pressing_w, securit
 
 def similar_players(player):
     row = get_player_row(player)
-
     if row is None:
         return pd.DataFrame({"Message": ["Select a player."]})
 
-    metrics = available_cols(CATEGORY_METRICS + KEY_METRICS)
-
-    comp = row[COMP_COL]
-    pos = row[POSITION_COL]
-
-    candidates = df[
-        (df[PLAYER_COL].astype(str) != str(player)) &
-        (df[POSITION_COL] == pos)
-    ].copy()
-
-    if candidates.empty:
-        candidates = df[df[PLAYER_COL].astype(str) != str(player)].copy()
+    metrics    = available_cols(CATEGORY_METRICS + KEY_METRICS)
+    candidates = df[df[PLAYER_COL].astype(str) != str(player)].copy()
 
     for metric in metrics:
         candidates[metric] = pd.to_numeric(candidates[metric], errors="coerce")
-        df_metric = pd.to_numeric(df[metric], errors="coerce")
-        sd = df_metric.std()
-
+        sd = pd.to_numeric(df[metric], errors="coerce").std()
+        player_val = row[metric] if pd.notna(row[metric]) else 0
         if pd.isna(sd) or sd == 0:
             candidates[f"dist_{metric}"] = 0
         else:
-            candidates[f"dist_{metric}"] = ((candidates[metric] - row[metric]) / sd) ** 2
+            candidates[f"dist_{metric}"] = ((candidates[metric] - player_val) / sd) ** 2
 
     dist_cols = [f"dist_{m}" for m in metrics]
     candidates["similarity_distance"] = candidates[dist_cols].sum(axis=1)
-    candidates["similarity_score"] = 100 / (1 + candidates["similarity_distance"])
+    candidates["similarity_score"]    = 100 / (1 + candidates["similarity_distance"])
 
     cols = available_cols([
-        PLAYER_COL,
-        TEAM_COL,
-        COMP_COL,
-        POSITION_COL,
-        AGE_COL,
-        MARKET_VALUE_COL,
-        "best_midfield_archetype",
-        "raw_score",
-        ATTAINABILITY_COL
+        PLAYER_COL, TEAM_COL, COMP_COL, AGE_COL, MINUTES_COL,
+        ARCHETYPE_COL, ARCHETYPE_SCORE_COL, GK_SCORE_COL,
     ]) + ["similarity_score"]
 
     out = candidates[cols].sort_values("similarity_score", ascending=False).head(5).copy()
-
-    if MARKET_VALUE_COL in out.columns:
-        out[MARKET_VALUE_COL] = out[MARKET_VALUE_COL].apply(format_money)
-
     numeric_cols = out.select_dtypes(include=np.number).columns
     out[numeric_cols] = out[numeric_cols].round(2)
-
     return out.reset_index(drop=True)
 
 # ============================================================
@@ -647,10 +504,8 @@ def similar_players(player):
 
 def add_to_shortlist(player):
     global shortlist
-
     if player and player not in shortlist:
         shortlist.append(player)
-
     return view_shortlist()
 
 def clear_shortlist():
@@ -663,34 +518,19 @@ def view_shortlist():
         return pd.DataFrame({"Message": ["No players added to shortlist yet."]})
 
     data = df[df[PLAYER_COL].astype(str).isin(shortlist)].copy()
-
     cols = available_cols([
-        PLAYER_COL,
-        TEAM_COL,
-        COMP_COL,
-        POSITION_COL,
-        AGE_COL,
-        MARKET_VALUE_COL,
-        CONTRACT_COL,
-        "best_midfield_archetype",
-        "raw_score",
-        ATTAINABILITY_COL
+        PLAYER_COL, TEAM_COL, COMP_COL, POSITION_COL,
+        AGE_COL, MINUTES_COL,
+        ARCHETYPE_COL, ARCHETYPE_SCORE_COL, GK_SCORE_COL,
     ] + KEY_METRICS)
-
     out = data[cols].copy()
-
-    if MARKET_VALUE_COL in out.columns:
-        out[MARKET_VALUE_COL] = out[MARKET_VALUE_COL].apply(format_money)
-
     numeric_cols = out.select_dtypes(include=np.number).columns
     out[numeric_cols] = out[numeric_cols].round(2)
-
     return out.reset_index(drop=True)
 
 def export_shortlist_csv():
     if not shortlist:
         return None
-
     data = df[df[PLAYER_COL].astype(str).isin(shortlist)].copy()
     out_file = "shortlist_export.csv"
     data.to_csv(out_file, index=False)
@@ -702,189 +542,155 @@ def export_shortlist_csv():
 
 def export_player_report(player, notes):
     row = get_player_row(player)
-
     if row is None:
         return None
 
     report = []
-    report.append(f"Player Scouting Report: {row[PLAYER_COL]}")
+    report.append(f"GK Scouting Report: {row[PLAYER_COL]}")
     report.append("=" * 60)
     report.append("")
-    report.append(f"Club: {row.get(TEAM_COL, 'N/A')}")
+    report.append(f"Club:        {row.get(TEAM_COL, 'N/A')}")
     report.append(f"Competition: {row.get(COMP_COL, 'N/A')}")
-    report.append(f"Position: {row.get(POSITION_COL, 'N/A')}")
-    report.append(f"Age: {round(row.get(AGE_COL, np.nan), 1) if pd.notna(row.get(AGE_COL, np.nan)) else 'N/A'}")
-    report.append(f"Height: {row.get(HEIGHT_COL, 'N/A')}")
-    report.append(f"Market Value: {format_money(row.get(MARKET_VALUE_COL, np.nan))}")
-    report.append(f"Contract Status: {row.get(CONTRACT_COL, 'N/A')}")
+    report.append(f"Position:    {row.get(POSITION_COL, 'N/A')}")
+    report.append(f"Age:         {round(row.get(AGE_COL, np.nan), 1) if pd.notna(row.get(AGE_COL, np.nan)) else 'N/A'}")
+    report.append(f"Height:      {row.get(HEIGHT_COL, 'N/A')} cm")
+    report.append(f"Minutes:     {round(row.get(MINUTES_COL, 0), 0)}")
     report.append("")
-    report.append("Scoring System")
+    report.append("GK Scoring")
     report.append("-" * 60)
-    report.append(f"Best Midfield Archetype: {row.get('best_midfield_archetype', 'N/A')}")
-    report.append(f"Best Archetype Score: {round(row.get('best_midfield_archetype_score', np.nan), 2) if pd.notna(row.get('best_midfield_archetype_score', np.nan)) else 'N/A'}")
-    report.append(f"Raw Score: {round(row.get('raw_score', np.nan), 2) if pd.notna(row.get('raw_score', np.nan)) else 'N/A'}")
-    report.append(f"Attainability: {round(row.get(ATTAINABILITY_COL, np.nan), 2) if pd.notna(row.get(ATTAINABILITY_COL, np.nan)) else 'N/A'}")
+    report.append(f"Best Archetype:       {row.get(ARCHETYPE_COL, 'N/A')}")
+    report.append(f"Best Archetype Score: {round(row.get(ARCHETYPE_SCORE_COL, np.nan), 2) if pd.notna(row.get(ARCHETYPE_SCORE_COL, np.nan)) else 'N/A'}")
+    report.append(f"Overall GK Score:     {round(row.get(GK_SCORE_COL, np.nan), 2) if pd.notna(row.get(GK_SCORE_COL, np.nan)) else 'N/A'}")
     report.append("")
-    report.append("Key Metrics")
+    report.append("Archetype Scores")
+    report.append("-" * 60)
+    for col in ["shot_stopper_score", "sweeper_keeper_score", "ball_playing_gk_score", "organiser_score"]:
+        if col in df.columns:
+            val = row.get(col, np.nan)
+            if pd.notna(val):
+                report.append(f"{label_col(col.replace('_score', ''))}: {round(val, 2)}")
+    report.append("")
+    report.append("Key Season Metrics")
     report.append("-" * 60)
-
     for col in available_cols(KEY_METRICS):
         value = row.get(col, np.nan)
         if pd.notna(value):
             report.append(f"{label_col(col)}: {round(value, 2)}")
-
     report.append("")
     report.append("Category Scores")
     report.append("-" * 60)
-
     for col in available_cols(CATEGORY_METRICS):
         value = row.get(col, np.nan)
         if pd.notna(value):
-            report.append(f"{label_col(col.replace('cat_', ''))}: {round(value, 2)}")
-
+            report.append(f"{label_col(col)}: {round(value, 2)}")
     report.append("")
     report.append("Scout Notes")
     report.append("-" * 60)
     report.append(notes if notes else "No notes entered.")
 
     safe_name = str(row[PLAYER_COL]).replace(" ", "_").replace("/", "_")
-    out_file = f"{safe_name}_scouting_report.txt"
-
+    out_file  = f"{safe_name}_gk_scouting_report.txt"
     with open(out_file, "w", encoding="utf-8") as f:
         f.write("\n".join(report))
-
     return out_file
 
 # ============================================================
 # APP LAYOUT
 # ============================================================
 
-with gr.Blocks(title="Oldham Athletic Player Scouting") as app:
+with gr.Blocks(title="Oldham Athletic GK Scouting") as app:
 
     gr.Markdown(
         """
-        # Oldham Athletic Player Scouting
-        
-        Interactive player scouting dashboard for midfielders across League One, League Two, the National League, National League N/S, and the Scottish Championship.
+        # Oldham Athletic GK Scouting
+        Interactive goalkeeper scouting dashboard powered by StatsBomb data.
         """
     )
 
     with gr.Tab("Player Search"):
-        gr.Markdown("## Search and Filter Players")
-    
+        gr.Markdown("## Search and Filter Goalkeepers")
+
         with gr.Row():
             search_box = gr.Textbox(label="Search Player Name")
-    
             competition_filter = gr.Dropdown(
-                choices=competition_options[1:],
-                value=[],
-                label="Competition",
-                multiselect=True
+                choices=competition_options, value=[], label="Competition", multiselect=True
             )
-    
             team_filter = gr.Dropdown(
-                choices=team_options[1:],
-                value=[],
-                label="Team",
-                multiselect=True
+                choices=team_options, value=[], label="Team", multiselect=True
             )
-    
+
         with gr.Row():
             position_filter = gr.Dropdown(
-                choices=position_options[1:],
-                value=[],
-                label="Position",
-                multiselect=True
+                choices=position_options, value=[], label="Position", multiselect=True
             )
-    
-            min_age_filter = gr.Slider(
-                minimum=age_min,
-                maximum=age_max,
-                value=age_min,
-                step=1,
-                label="Minimum Age"
-            )
-    
-            max_age_filter = gr.Slider(
-                minimum=age_min,
-                maximum=age_max,
-                value=age_max,
-                step=1,
-                label="Maximum Age"
-            )
-    
+            min_age_filter = gr.Slider(minimum=age_min, maximum=age_max, value=age_min, step=1, label="Minimum Age")
+            max_age_filter = gr.Slider(minimum=age_min, maximum=age_max, value=age_max, step=1, label="Maximum Age")
             minutes_filter = gr.Slider(
                 minimum=0,
                 maximum=int(df[MINUTES_COL].max()) if MINUTES_COL in df.columns else 3000,
-                value=0,
-                step=100,
-                label="Minimum Minutes"
+                value=0, step=100, label="Minimum Minutes"
             )
-    
-        search_button = gr.Button("Search Players")
-        search_results = gr.Dataframe(label="Sortable Player Results", interactive=False)
-    
+
+        search_button  = gr.Button("Search Players")
+        search_results = gr.Dataframe(label="Goalkeeper Results (sorted by GK Score)", interactive=False)
+
         search_button.click(
             fn=search_players,
-            inputs=[
-                search_box,
-                competition_filter,
-                team_filter,
-                position_filter,
-                min_age_filter,
-                max_age_filter,
-                minutes_filter
-            ],
+            inputs=[search_box, competition_filter, team_filter, position_filter,
+                    min_age_filter, max_age_filter, minutes_filter],
             outputs=search_results
         )
 
     with gr.Tab("Player Profile"):
-        gr.Markdown("## Full Player Profile")
+        gr.Markdown("## Full GK Profile")
 
         selected_player = gr.Dropdown(player_options, label="Select Player")
 
         with gr.Row():
-            profile_output = gr.Markdown()
-            category_output = gr.Dataframe(label="Season Stats by Category", interactive=False)
+            profile_output  = gr.Markdown()
+            category_output = gr.Dataframe(label="GK Category Scores", interactive=False)
 
         with gr.Row():
-            radar_output = gr.Plot(label="Radar Chart")
+            radar_output      = gr.Plot(label="Radar Chart")
             percentile_output = gr.Plot(label="Percentile Bars")
 
         with gr.Row():
-            profile_metric = gr.Dropdown(metric_options, value=metric_options[0] if metric_options else None, label="Performance Metric")
+            profile_metric = gr.Dropdown(
+                metric_options,
+                value=metric_options[0] if metric_options else None,
+                label="Performance Metric"
+            )
             trend_button = gr.Button("Show Performance Chart")
 
         trend_output = gr.Plot(label="Performance Over Time")
 
-        scout_notes = gr.Textbox(label="Scout Notes", lines=5, placeholder="Enter notes to include in the scouting report.")
-        report_button = gr.Button("Generate Scouting Report")
-        report_file = gr.File(label="Download Scouting Report")
+        scout_notes    = gr.Textbox(label="Scout Notes", lines=5, placeholder="Enter notes to include in the scouting report.")
+        report_button  = gr.Button("Generate Scouting Report")
+        report_file    = gr.File(label="Download Scouting Report")
 
-        shortlist_button = gr.Button("Add Player to Shortlist")
+        shortlist_button       = gr.Button("Add Player to Shortlist")
         shortlist_from_profile = gr.Dataframe(label="Current Shortlist", interactive=False)
 
-        selected_player.change(player_profile, selected_player, profile_output)
-        selected_player.change(category_table, selected_player, category_output)
-        selected_player.change(radar_chart, selected_player, radar_output)
+        selected_player.change(player_profile,   selected_player, profile_output)
+        selected_player.change(category_table,   selected_player, category_output)
+        selected_player.change(radar_chart,      selected_player, radar_output)
         selected_player.change(percentile_chart, selected_player, percentile_output)
 
-        trend_button.click(performance_chart, [selected_player, profile_metric], trend_output)
-        report_button.click(export_player_report, [selected_player, scout_notes], report_file)
+        trend_button.click(performance_chart,    [selected_player, profile_metric], trend_output)
+        report_button.click(export_player_report,[selected_player, scout_notes],    report_file)
         shortlist_button.click(add_to_shortlist, selected_player, shortlist_from_profile)
 
     with gr.Tab("Player Comparison Tool"):
-        gr.Markdown("## Compare Up To Three Players")
+        gr.Markdown("## Compare Up To Three Goalkeepers")
 
         with gr.Row():
             compare_1 = gr.Dropdown(player_options, label="Player 1")
             compare_2 = gr.Dropdown(player_options, label="Player 2")
             compare_3 = gr.Dropdown(player_options, label="Player 3")
 
-        compare_button = gr.Button("Compare Players")
-
-        comparison_table = gr.Dataframe(label="Stat Comparison Table", interactive=False)
-        comparison_radar_plot = gr.Plot(label="Side-by-Side Radar Chart")
+        compare_button         = gr.Button("Compare Players")
+        comparison_table       = gr.Dataframe(label="Stat Comparison Table", interactive=False)
+        comparison_radar_plot  = gr.Plot(label="Side-by-Side Radar Chart")
 
         compare_button.click(compare_players, [compare_1, compare_2, compare_3], comparison_table)
         compare_button.click(comparison_radar, [compare_1, compare_2, compare_3], comparison_radar_plot)
@@ -892,59 +698,53 @@ with gr.Blocks(title="Oldham Athletic Player Scouting") as app:
     with gr.Tab("Fit Score Calculator"):
         gr.Markdown(
             """
-            ## Custom Fit Score Calculator
-            
-            Move the sliders to weight the traits Oldham cares about most.  
-            The app will rank players based on your custom scouting profile.
+            ## Custom GK Fit Score Calculator
+            Weight the GK attributes that matter most to Oldham.
+            The app will rank all goalkeepers based on your custom profile.
             """
         )
 
         with gr.Row():
-            defense_w = gr.Slider(0, 10, value=5, step=1, label="Defensive Ability")
-            chance_w = gr.Slider(0, 10, value=5, step=1, label="Chance Creation")
-            progression_w = gr.Slider(0, 10, value=5, step=1, label="Ball Progression")
-
-        with gr.Row():
-            passing_w = gr.Slider(0, 10, value=5, step=1, label="Passing")
-            pressing_w = gr.Slider(0, 10, value=5, step=1, label="Pressing Work Rate")
-            security_w = gr.Slider(0, 10, value=5, step=1, label="Possession Security")
+            shot_stopping_w = gr.Slider(0, 10, value=5, step=1, label="Shot Stopping")
+            sweeping_w      = gr.Slider(0, 10, value=5, step=1, label="Sweeping")
+            short_passing_w = gr.Slider(0, 10, value=5, step=1, label="Short Passing")
 
         with gr.Row():
-            goal_w = gr.Slider(0, 10, value=3, step=1, label="Goal Threat")
-            impact_w = gr.Slider(0, 10, value=5, step=1, label="Impact")
-            attain_w = gr.Slider(0, 10, value=5, step=1, label="Attainability")
+            long_passing_w  = gr.Slider(0, 10, value=5, step=1, label="Long Passing")
+            ball_claiming_w = gr.Slider(0, 10, value=5, step=1, label="Ball Claiming")
+            overall_value_w = gr.Slider(0, 10, value=5, step=1, label="Overall Value")
 
         fit_button = gr.Button("Generate Ranked Recommendations")
-        fit_table = gr.Dataframe(label="Ranked Recommendations", interactive=False)
+        fit_table  = gr.Dataframe(label="Ranked Recommendations", interactive=False)
 
         fit_button.click(
             fit_score,
-            [defense_w, chance_w, progression_w, passing_w, pressing_w, security_w, goal_w, impact_w, attain_w],
+            [shot_stopping_w, sweeping_w, short_passing_w, long_passing_w, ball_claiming_w, overall_value_w],
             fit_table
         )
 
     with gr.Tab("Similar Player Finder"):
-        gr.Markdown("## Find Similar Players")
+        gr.Markdown("## Find Similar Goalkeepers")
 
         similar_player_select = gr.Dropdown(player_options, label="Select Player")
-        similar_button = gr.Button("Find Similar Players")
-        similar_table = gr.Dataframe(label="Five Similar Players", interactive=False)
+        similar_button        = gr.Button("Find Similar Players")
+        similar_table         = gr.Dataframe(label="Five Most Similar Goalkeepers", interactive=False)
 
         similar_button.click(similar_players, similar_player_select, similar_table)
 
     with gr.Tab("Shortlist Manager"):
         gr.Markdown("## Shortlist Manager")
 
-        shortlist_player = gr.Dropdown(player_options, label="Add Player")
-        add_shortlist_button = gr.Button("Add to Shortlist")
-        clear_shortlist_button = gr.Button("Clear Shortlist")
+        shortlist_player        = gr.Dropdown(player_options, label="Add Player")
+        add_shortlist_button    = gr.Button("Add to Shortlist")
+        clear_shortlist_button  = gr.Button("Clear Shortlist")
         export_shortlist_button = gr.Button("Export Shortlist CSV")
 
         shortlist_table = gr.Dataframe(label="Saved Players", interactive=False)
-        shortlist_file = gr.File(label="Download Shortlist CSV")
+        shortlist_file  = gr.File(label="Download Shortlist CSV")
 
-        add_shortlist_button.click(add_to_shortlist, shortlist_player, shortlist_table)
-        clear_shortlist_button.click(clear_shortlist, None, shortlist_table)
-        export_shortlist_button.click(export_shortlist_csv, None, shortlist_file)
+        add_shortlist_button.click(add_to_shortlist,    shortlist_player, shortlist_table)
+        clear_shortlist_button.click(clear_shortlist,   None,             shortlist_table)
+        export_shortlist_button.click(export_shortlist_csv, None,         shortlist_file)
 
 app.launch()