Add simulation of statistical projections in app.py. Introduced a new function to simulate player statistics using a normal distribution, generating percentiles for kills, deaths, assists, and CS projections. This enhancement allows for a more comprehensive analysis of player performance by incorporating simulated data, improving the overall depth of statistical insights available in the application.

app.py

@@ -5,6 +5,7 @@ import pandas as pd
 import pymongo
 import time
 from datetime import datetime, timedelta
+from scipy import stats
 
 @st.cache_resource
 def init_conn():
@@ -102,6 +103,24 @@ with st.sidebar:
             value=5
         )
 
+@st.cache_data(ttl = 60)
+def simulate_stats(row, num_sims=1000):
+    """Simulate stats using normal distribution"""
+    # Using coefficient of variation of 0.3 to generate reasonable standard deviations
+    cv = 0.3
+    percentiles = [10, 25, 50, 75, 90]
+    
+    results = {}
+    for stat in ['Kill_Proj', 'Death_Proj', 'Assist_Proj', 'CS_Proj']:
+        mean = row[stat]
+        std = mean * cv  # Using coefficient of variation to determine std
+        sims = stats.norm.rvs(loc=mean, scale=std, size=num_sims)
+        # Ensure no negative values
+        sims = np.maximum(sims, 0)
+        results[stat] = np.percentile(sims, percentiles)
+    
+    return pd.Series(results)
+
 @st.cache_data(ttl = 60)
 def init_team_data(team, opponent, win_loss, kill_prediction, death_prediction, start_date, end_date):  
         
@@ -297,8 +316,40 @@ def init_team_data(team, opponent, win_loss, kill_prediction, death_prediction,
 
 if st.button("Run"):
     team_data, opp_boost = init_team_data(selected_team, selected_opponent, win_loss, kill_prediction, death_prediction, start_date, end_date)
+
+    # Create simulated percentiles
+    sim_results = []
+    for idx, row in team_data.iterrows():
+        percentiles = simulate_stats(row)
+        sim_results.append({
+            'Player': idx,
+            'Position': row['position'],
+            'Stat': 'Kills',
+            'P10': percentiles['Kill_Proj'][0],
+            'P25': percentiles['Kill_Proj'][1],
+            'P50': percentiles['Kill_Proj'][2],
+            'P75': percentiles['Kill_Proj'][3],
+            'P90': percentiles['Kill_Proj'][4]
+        })
+        # Repeat for other stats
+        for stat, name in [('Death_Proj', 'Deaths'), ('Assist_Proj', 'Assists'), ('CS_Proj', 'CS')]:
+            sim_results.append({
+                'Player': idx,
+                'Position': row['position'],
+                'Stat': name,
+                'P10': percentiles[stat][0],
+                'P25': percentiles[stat][1],
+                'P50': percentiles[stat][2],
+                'P75': percentiles[stat][3],
+                'P90': percentiles[stat][4]
+            })
+    
+    sim_df = pd.DataFrame(sim_results)
+
     tab1, tab2 = st.tabs(["Team Data", "Opponent Data"])
     with tab1:
         st.dataframe(team_data.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(display_formats, precision=2), use_container_width = True)
     with tab2:
-        st.dataframe(opp_boost.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(precision=2), use_container_width = True)
+        st.dataframe(opp_boost.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(precision=2), use_container_width = True)
+
+    st.dataframe(sim_df.style.format(precision=2), use_container_width=True)