Add Prop Check feature to app.py for statistical analysis of player performance. Users can input a prop value and select a statistic (Kills, Deaths, Assists, CS) to calculate and display the probabilities of exceeding or falling below the specified prop value. This enhancement improves user interaction and provides deeper insights into player statistics during simulations.

app.py

@@ -705,6 +705,43 @@ if st.button("Run"):
                     stat_data.style.format(precision=2).background_gradient(axis=0).background_gradient(cmap='RdYlGn'),
                     use_container_width=True
                 )
+        
+        st.subheader("Prop Check")
+        col1, col2 = st.columns([2, 8])
+        with col1:
+            prop_var = st.number_input("Enter Prop Value", min_value=0.0, max_value=100.0, value=4.5, step=0.5)
+            stat_choice = st.selectbox("Select Stat", ["Kills", "Deaths", "Assists", "CS"])
+        with col2:
+            # Filter data for selected stat
+            stat_data = overall_sim_df[overall_sim_df['Stat'] == stat_choice].copy()
+            
+            # Calculate mean and standard deviation using percentiles
+            # Using the fact that in a normal distribution:
+            # 10th percentile is -1.28 SD from mean
+            # 90th percentile is 1.28 SD from mean
+            stat_data['mean'] = (stat_data['90%'] + stat_data['10%']) / 2
+            stat_data['std'] = (stat_data['90%'] - stat_data['10%']) / (2 * 1.28)
+            
+            # Calculate probabilities
+            stat_data['over_prob'] = stat_data.apply(
+                lambda x: 1 - stats.norm.cdf(prop_var, x['mean'], x['std']), axis=1
+            )
+            stat_data['under_prob'] = stat_data.apply(
+                lambda x: stats.norm.cdf(prop_var, x['mean'], x['std']), axis=1
+            )
+            
+            # Prepare display dataframe
+            display_df = stat_data[['Player', 'Position', 'over_prob', 'under_prob']].copy()
+            display_df['Over %'] = (display_df['over_prob'] * 100).round(1).astype(str) + '%'
+            display_df['Under %'] = (display_df['under_prob'] * 100).round(1).astype(str) + '%'
+            
+            # Display results
+            st.dataframe(
+                display_df[['Player', 'Position', 'Over %', 'Under %']]
+                .set_index('Player')
+                .style.background_gradient(subset=['Over %', 'Under %'], cmap='RdYlGn'),
+                use_container_width=True
+            )
 
     with tab2:
         st.subheader("Individual Game Data")