Update src/streamlit_app.py

src/streamlit_app.py

@@ -6,6 +6,8 @@ import os
 from datetime import datetime
 from bs4 import BeautifulSoup
 import re # New import for regex operations
+import plotly.express as px # Ensure plotly imports are present
+import plotly.graph_objects as go # Ensure plotly imports are present
 
 # --- IMPORTANT: Addressing PermissionError in Containerized Environments ---
 # The error "PermissionError: [Errno 13] Permission denied: '/.streamlit'"
@@ -19,7 +21,7 @@ import re # New import for regex operations
 #
 # Option 2: Disable Streamlit's usage statistics gathering.
 #    In your Dockerfile: ENV STREAMLIT_BROWSER_GATHER_USAGE_STATS=False
-#    Or when running: docker run -e STREAMLIT_BROWSER_GATHER_USAGE_STATS=False your_image_name
+#    Or when running: docker run -e STREAMIT_BROWSER_GATHER_USAGE_STATS=False your_image_name
 #
 # Option 1 is generally more robust as it provides a writable home directory
 # for any application that might need it.
@@ -159,7 +161,17 @@ def player_season_stats(bbr_url):
         return pd.DataFrame()
 
     df = parse_table(html, table_id="per_game")
-    if df.empty or "Season" not in df.columns:
+    if df.empty: # Check if df is empty first
+        return pd.DataFrame()
+
+    # Flatten multi-index columns if they exist (common with pd.read_html)
+    if isinstance(df.columns, pd.MultiIndex):
+        df.columns = ['_'.join(col).strip() for col in df.columns.values]
+    else:
+        df.columns = [col.strip() for col in df.columns.values]
+
+    # Now check for 'Season' column after flattening
+    if "Season" not in df.columns:
         return pd.DataFrame()
 
     # drop repeated header rows (e.g., rows where 'Season' is literally 'Season')
@@ -201,7 +213,17 @@ def team_per_game(year):
         return pd.DataFrame()
 
     df = parse_table(html, table_id="per_game-team") # Correct table ID for team stats
-    if df.empty or "Team" not in df.columns:
+    if df.empty: # Check if df is empty first
+        return pd.DataFrame()
+
+    # Flatten multi-index columns if they exist
+    if isinstance(df.columns, pd.MultiIndex):
+        df.columns = ['_'.join(col).strip() for col in df.columns.values]
+    else:
+        df.columns = [col.strip() for col in df.columns.values]
+
+    # Now check for 'Team' column after flattening
+    if "Team" not in df.columns:
         return pd.DataFrame()
 
     # drop repeated headers & rename
@@ -221,7 +243,7 @@ def team_per_game(year):
     })
 
     # coerce numeric columns
-    non_numeric_cols = {"Tm", "RANK"} # 'RANK' is usually numeric, but 'Tm' is not
+    non_numeric_cols = {"Tm", "RANK"}
     for col in df.columns:
         if col not in non_numeric_cols:
             df[col] = pd.to_numeric(df[col], errors="coerce")
@@ -283,6 +305,62 @@ def get_available_seasons(num_seasons=6):
         seasons_list.append(f"{start_year}–{end_year}")
     return sorted(seasons_list, reverse=True) # Sort to show most recent first
 
+# —————————————————————————————————————————————————————————————————————————————
+# Plotting functions (retained from previous version)
+def create_comparison_chart(data, players_names, metric):
+    """Create comparison chart for players"""
+    fig = go.Figure()
+
+    for i, player in enumerate(players_names):
+        if player in data['Player'].values: # Changed to 'Player' column
+            player_data = data[data['Player'] == player]
+            fig.add_trace(go.Scatter(
+                x=player_data['Season'], # Changed to 'Season' column
+                y=player_data[metric],
+                mode='lines+markers',
+                name=player,
+                line=dict(width=3)
+            ))
+
+    fig.update_layout(
+        title=f"{metric} Comparison",
+        xaxis_title="Season",
+        yaxis_title=metric,
+        hovermode='x unified',
+        height=500
+    )
+
+    return fig
+
+def create_radar_chart(player_stats, categories):
+    """Create radar chart for player comparison"""
+    fig = go.Figure()
+
+    for player_name, stats in player_stats.items():
+        # Ensure all categories are present, default to 0 if not
+        r_values = [stats.get(cat, 0) for cat in categories]
+
+        fig.add_trace(go.Scatterpolar(
+            r=r_values,
+            theta=categories,
+            fill='toself',
+            name=player_name,
+            opacity=0.7
+        ))
+
+    fig.update_layout(
+        polar=dict(
+            radialaxis=dict(
+                visible=True,
+                # The range should be adjusted based on the scaled data (0-100)
+                range=[0, 100]
+            )),
+        showlegend=True,
+        title="Player Comparison Radar Chart"
+    )
+
+    return fig
+
 # —————————————————————————————————————————————————————————————————————————————
 # Main App Structure
 # ————���————————————————————————————————————————————————————————————————————————
@@ -324,27 +402,44 @@ def player_vs_player():
 
         stats_tabs = st.tabs(["Basic Stats", "Advanced Stats", "Visualizations"])
         all_player_season_data = [] # To store individual season rows for each player
+        players_not_found_in_index = []
+        players_with_no_season_data = []
 
         with st.spinner("Fetching player data..."):
             for player_name in selected_players:
-                player_url = idx.loc[idx.name == player_name, 'url'].iat[0]
+                player_url_row = idx.loc[idx.name == player_name, 'url']
+                if player_url_row.empty:
+                    players_not_found_in_index.append(player_name)
+                    continue
+
+                player_url = player_url_row.iat[0]
                 df_player_career = player_season_stats(player_url)
 
                 if not df_player_career.empty:
                     # Filter for selected seasons and ensure 'Season' column is consistent
-                    df_player_career['Season'] = df_player_career['Season'].str.replace('-', '–')
+                    # The player_season_stats already handles the hyphen to en-dash replacement
                     filtered_df = df_player_career[df_player_career['Season'].isin(selected_seasons)].copy()
 
                     if not filtered_df.empty:
                         filtered_df['Player'] = player_name # Add player name for identification
                         all_player_season_data.append(filtered_df)
                     else:
-                        st.info(f"No data found for {player_name} in selected seasons.")
+                        # This means player was found, but no data for selected seasons
+                        players_with_no_season_data.append(player_name)
                 else:
-                    st.info(f"Could not fetch career stats for {player_name}.")
+                    # This means player_season_stats returned an empty DF (fetch/parse failed)
+                    players_with_no_season_data.append(player_name) # Treat as no data for selected seasons
+
+        # Report on players not found in index
+        if players_not_found_in_index:
+            st.error(f"The following players were not found in the Basketball-Reference index: {', '.join(players_not_found_in_index)}. Please check spelling.")
+
+        # Report on players with no data for selected seasons
+        if players_with_no_season_data:
+            st.info(f"No data found for the selected seasons ({', '.join(selected_seasons)}) for: {', '.join(players_with_no_season_data)}. This might be because the season hasn't started or data is not yet available.")
 
         if not all_player_season_data:
-            st.info("No data available for the selected players and seasons.")
+            st.error("No data available for any of the selected players and seasons to display. Please adjust your selections.")
             return
 
         # Concatenate all collected season data into one DataFrame
@@ -416,7 +511,7 @@ def player_vs_player():
                             )
                         else:
                             # Average over selected seasons for multiple players for bar chart
-                            avg_comparison_df = comparison_df_raw.groupby('Player')[available_metrics].mean().reset_index()
+                            avg_comparison_df = comparison_df_raw.groupby('Player')[available_metrics].mean(numeric_only=True).reset_index()
                             fig = px.bar(
                                 avg_comparison_df,
                                 x='Player',
@@ -469,16 +564,16 @@ def player_vs_player():
 
 def team_vs_team():
     st.markdown('<h2 class="section-header">Team vs Team Analysis</h2>', unsafe_allow_html=True)
-    
+
     available_seasons = get_available_seasons()
     selected_season_str = st.selectbox("Select Season", available_seasons, index=0)
-    
+
     # Extract the end year from the season string (e.g., "2024–25" -> 2025)
     year_for_team_stats = int(selected_season_str.split('–')[1])
 
     tm_df = team_per_game(year_for_team_stats)
     if tm_df.empty:
-        st.info(f"No team data available for the {selected_season_str} season.")
+        st.info(f"No team data available for the {selected_season_str} season. This might be because the season hasn't started or data is not yet available.")
         return
 
     teams = tm_df['Tm'].unique().tolist()
@@ -490,19 +585,25 @@ def team_vs_team():
             return
 
         stats = []
-        for t in selected_teams:
-            df = tm_df[tm_df.Tm == t].copy() # Use .copy() to avoid SettingWithCopyWarning
-            if not df.empty:
-                # For team stats, we usually get one row per team per season from team_per_game
-                # So, no need for .mean() here, just take the row.
-                df['Team'] = t # Add 'Team' column for consistency
-                df['Season'] = selected_season_str # Add 'Season' column
-                stats.append(df.iloc[0].to_dict()) # Convert the single row to dict
-            else:
-                st.info(f"No data found for team {t} in {selected_season_str}.")
+        teams_with_no_data = []
+
+        with st.spinner("Fetching team data..."):
+            for t in selected_teams:
+                df = tm_df[tm_df.Tm == t].copy() # Use .copy() to avoid SettingWithCopyWarning
+                if not df.empty:
+                    # For team stats, we usually get one row per team per season from team_per_game
+                    # So, no need for .mean() here, just take the row.
+                    df['Team'] = t # Add 'Team' column for consistency
+                    df['Season'] = selected_season_str # Add 'Season' column
+                    stats.append(df.iloc[0].to_dict()) # Convert the single row to dict
+                else:
+                    teams_with_no_data.append(t)
+
+        if teams_with_no_data:
+            st.info(f"No data found for the selected season ({selected_season_str}) for: {', '.join(teams_with_no_data)}. This might be because the season hasn't started or data is not yet available.")
 
         if not stats:
-            st.info("No data available for the selected teams.")
+            st.error("No data available for the selected teams to display. Please adjust your selections.")
             return
 
         comp = pd.DataFrame(stats)
@@ -611,10 +712,14 @@ def young_projections():
         ppg = st.number_input("PPG",0.0,40.0,15.0)
         rpg = st.number_input("RPG",0.0,20.0,5.0)
         apg = st.number_input("APG",0.0,15.0,3.0)
-        if st.button("Project"):
+        if st.button("Generate AI Projection"):
             prompt = (
-              f"Project {sp}'s next 5-year stats based on Age={age}, "
-              f"Yrs={yrs}, PPG={ppg}, RPG={rpg}, APG={apg}."
+              f"Analyze and project the future potential of NBA player {sp}: "
+              f"Current Stats: Age={age}, Years in NBA={yrs}, PPG={ppg}, RPG={rpg}, APG={apg}. "
+              "Please provide: 1. 3-year projection of their stats. "
+              "2. Peak potential analysis. 3. Areas for improvement. "
+              "4. Comparison to similar players at the same age. 5. Career trajectory prediction. "
+              "Base your analysis on historical player development patterns and current NBA trends."
             )
             out = ask_perp(prompt, system="You are an NBA projection expert AI.", max_tokens=800)
             st.markdown("### Projection Analysis")
@@ -633,13 +738,13 @@ def similar_players():
     tp = st.selectbox("Target Player", all_p)
     crit = st.multiselect("Criteria",["Position","Height/Weight","Playing Style","Statistical Profile","Age/Experience"],default=["Playing Style","Statistical Profile"])
     if tp and crit and st.button("Find Similar"):
-        prompt = f"Find top 5 current and top 3 historical similar to {tp} by {', '.join(crit)}. Provide detailed reasoning."
+        prompt = f"Find top 5 current and top 3 historical similar to {tp} based on the following criteria: {', '.join(crit)}. Provide detailed reasoning."
         st.write(ask_perp(prompt, system="You are a similarity expert AI.", max_tokens=800))
     st.subheader("Manual Compare")
     p1 = st.selectbox("Player 1", all_p, key="p1")
     p2 = st.selectbox("Player 2", all_p, key="p2")
     if p1 and p2 and p1!=p2 and st.button("Compare Players"):
-        prompt = f"Compare {p1} vs {p2} on statistical comparison (current season), playing style similarities and differences, strengths and weaknesses, team impact and role, and overall similarity score (1-10)."
+        prompt = f"Compare {p1} vs {p2} in detail: 1. Statistical comparison (current season). 2. Playing style similarities and differences. 3. Strengths and weaknesses of each. 4. Team impact and role. 5. Overall similarity score (1-10). Provide a comprehensive comparison with specific examples."
         st.write(ask_perp(prompt, system="You are a comparison expert AI.", max_tokens=700))
 
 def roster_builder():