Spaces:
Running
Running
James McCool
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.
6244ceb
| import streamlit as st | |
| st.set_page_config(layout="wide") | |
| import numpy as np | |
| import pandas as pd | |
| import pymongo | |
| import time | |
| from datetime import datetime, timedelta | |
| from scipy import stats | |
| def init_conn(): | |
| uri = st.secrets['mongo_uri'] | |
| client = pymongo.MongoClient(uri, retryWrites=True, serverSelectionTimeoutMS=500000) | |
| db = client["League_of_Legends_Database"] | |
| current_date = datetime.now() | |
| collection = db["gamelogs"] | |
| max_date = current_date - timedelta(days=1) | |
| min_date = current_date - timedelta(days=365) | |
| team_names = collection.distinct("teamname") | |
| player_names = collection.distinct("playername") | |
| return db, team_names, player_names, min_date, max_date | |
| db, team_names, player_names, min_date, max_date = init_conn() | |
| display_formats = {'wKill%': '{:.2%}', 'wDeath%': '{:.2%}', 'wAssist%': '{:.2%}', 'lKill%': '{:.2%}', 'lDeath%': '{:.2%}', 'lAssist%': '{:.2%}'} | |
| # Create sidebar container for options | |
| with st.sidebar: | |
| st.header("Team Analysis Options") | |
| # Date filtering options | |
| st.subheader("Date Range") | |
| date_filter = st.radio( | |
| "Select Date Range", | |
| ["Last Year", "Custom Range"] | |
| ) | |
| if date_filter == "Last Year": | |
| end_date = max_date | |
| start_date = (end_date - timedelta(days=365)) | |
| else: | |
| col1, col2 = st.columns(2) | |
| with col1: | |
| start_date = st.date_input( | |
| "Start Date", | |
| value=max_date.date() - timedelta(days=30), | |
| min_value=min_date.date(), | |
| max_value=max_date.date() | |
| ) | |
| with col2: | |
| end_date = st.date_input( | |
| "End Date", | |
| value=max_date.date(), | |
| min_value=min_date.date(), | |
| max_value=max_date.date() | |
| ) | |
| selected_team = st.selectbox( | |
| "Select Team", | |
| options=team_names, | |
| index=team_names.index("T1") if "T1" in team_names else 0 | |
| ) | |
| selected_opponent = st.selectbox( | |
| "Select Opponent", | |
| options=team_names, | |
| index=team_names.index("T1") if "T1" in team_names else 0 | |
| ) | |
| st.subheader("Prediction Settings") | |
| win_loss = st.selectbox( | |
| "Select Win/Loss", | |
| options=["Win", "Loss"], | |
| index=0 | |
| ) | |
| game_settings = st.selectbox( | |
| "Predict kills/deaths or use average?", | |
| options=["Average", "Predict"], | |
| index=0 | |
| ) | |
| if game_settings == "Average": | |
| kill_prediction = 0 | |
| death_prediction = 0 | |
| else: | |
| kill_prediction = st.number_input( | |
| "Predicted Team Kills", | |
| min_value=1, | |
| max_value=100, | |
| value=20 | |
| ) | |
| death_prediction = st.number_input( | |
| "Predicted Team Deaths", | |
| min_value=1, | |
| max_value=100, | |
| value=5 | |
| ) | |
| 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) | |
| def init_team_data(team, opponent, win_loss, kill_prediction, death_prediction, start_date, end_date): | |
| # Convert date objects to datetime strings in the correct format | |
| start_datetime = datetime.combine(start_date, datetime.min.time()).strftime("%Y-%m-%d %H:%M:%S") | |
| end_datetime = datetime.combine(end_date, datetime.max.time()).strftime("%Y-%m-%d %H:%M:%S") | |
| collection = db["gamelogs"] | |
| cursor = collection.find({"teamname": team, "date": {"$gte": start_datetime, "$lte": end_datetime}}) | |
| raw_display = pd.DataFrame(list(cursor)) | |
| cursor = collection.find({"date": {"$gte": start_datetime, "$lte": end_datetime}}) | |
| raw_opponent = pd.DataFrame(list(cursor)) | |
| tables_to_loop = [raw_display, raw_opponent] | |
| for loop in range(len(tables_to_loop)): | |
| tables = tables_to_loop[loop] | |
| calc_columns = ['kills', 'deaths', 'assists', 'total_cs'] | |
| league_pos_win_stats = {} | |
| league_pos_loss_stats = {} | |
| Opponent_pos_win_allowed_stats = {} | |
| Opponent_pos_loss_allowed_stats = {} | |
| playername_win_stats = {} | |
| playername_loss_stats = {} | |
| teamname_win_stats = {} | |
| teamname_loss_stats = {} | |
| if loop == 0: | |
| for stats in calc_columns: | |
| playername_win_stats[stats] = tables[tables['result'] == 1].groupby(['playername'])[stats].mean().to_dict() | |
| playername_loss_stats[stats] = tables[tables['result'] == 0].groupby(['playername'])[stats].mean().to_dict() | |
| teamname_win_stats[stats] = tables[(tables['result'] == 1) & (tables['position'] == 'team')].groupby(['teamname'])[stats].mean().to_dict() | |
| teamname_loss_stats[stats] = tables[(tables['result'] == 0) & (tables['position'] == 'team')].groupby(['teamname'])[stats].mean().to_dict() | |
| for stat in calc_columns: | |
| column_name = f'playername_avg_{stat}_win' | |
| tables[column_name] = tables.apply( | |
| lambda row: playername_win_stats[stat].get(row['playername'], 0), | |
| axis=1 | |
| ) | |
| column_name = f'playername_avg_{stat}_loss' | |
| tables[column_name] = tables.apply( | |
| lambda row: playername_loss_stats[stat].get(row['playername'], 0), | |
| axis=1 | |
| ) | |
| column_name = f'teamname_avg_{stat}_win' | |
| tables[column_name] = tables.apply( | |
| lambda row: teamname_win_stats[stat].get(row['teamname'], 0), | |
| axis=1 | |
| ) | |
| column_name = f'teamname_avg_{stat}_loss' | |
| tables[column_name] = tables.apply( | |
| lambda row: teamname_loss_stats[stat].get(row['teamname'], 0), | |
| axis=1 | |
| ) | |
| tables['playername_avg_kill_share_win'] = tables['playername_avg_kills_win'] / tables['teamname_avg_kills_win'] | |
| tables['playername_avg_death_share_win'] = tables['playername_avg_deaths_win'] / tables['teamname_avg_deaths_win'] | |
| tables['playername_avg_assist_share_win'] = tables['playername_avg_assists_win'] / tables['teamname_avg_kills_win'] | |
| tables['playername_avg_cs_share_win'] = tables['playername_avg_total_cs_win'] / tables['teamname_avg_total_cs_win'] | |
| tables['playername_avg_kill_share_loss'] = tables['playername_avg_kills_loss'] / tables['teamname_avg_kills_loss'] | |
| tables['playername_avg_death_share_loss'] = tables['playername_avg_deaths_loss'] / tables['teamname_avg_deaths_loss'] | |
| tables['playername_avg_assist_share_loss'] = tables['playername_avg_assists_loss'] / tables['teamname_avg_kills_loss'] | |
| tables['playername_avg_cs_share_loss'] = tables['playername_avg_total_cs_loss'] / tables['teamname_avg_total_cs_loss'] | |
| player_tables = tables | |
| else: | |
| for stats in calc_columns: | |
| league_pos_win_stats[stats] = { | |
| league: group.groupby('position')[stats].mean().to_dict() | |
| for league, group in tables[tables['result'] == 1].groupby('league') | |
| } | |
| league_pos_loss_stats[stats] = { | |
| league: group.groupby('position')[stats].mean().to_dict() | |
| for league, group in tables[tables['result'] == 0].groupby('league') | |
| } | |
| Opponent_pos_win_allowed_stats[stats] = { | |
| opponent: group.groupby('position')[stats].mean().to_dict() | |
| for opponent, group in tables[tables['result'] == 1].groupby('Opponent') | |
| } | |
| Opponent_pos_loss_allowed_stats[stats] = { | |
| opponent: group.groupby('position')[stats].mean().to_dict() | |
| for opponent, group in tables[tables['result'] == 0].groupby('Opponent') | |
| } | |
| for stat in calc_columns: | |
| column_name = f'league_pos_avg_{stat}_win' | |
| tables[column_name] = tables.apply( | |
| lambda row: league_pos_win_stats[stat].get(row['league'], {}).get(row['position'], 0), | |
| axis=1 | |
| ) | |
| column_name = f'league_pos_avg_{stat}_loss' | |
| tables[column_name] = tables.apply( | |
| lambda row: league_pos_loss_stats[stat].get(row['league'], {}).get(row['position'], 0), | |
| axis=1 | |
| ) | |
| column_name = f'Opponent_pos_avg_{stat}_allowed_win' | |
| tables[column_name] = tables.apply( | |
| lambda row: Opponent_pos_win_allowed_stats[stat].get(row['Opponent'], {}).get(row['position'], 0), | |
| axis=1 | |
| ) | |
| column_name = f'Opponent_pos_avg_{stat}_allowed_loss' | |
| tables[column_name] = tables.apply( | |
| lambda row: Opponent_pos_loss_allowed_stats[stat].get(row['Opponent'], {}).get(row['position'], 0), | |
| axis=1 | |
| ) | |
| tables = tables[tables['Opponent'] == opponent] | |
| tables['overall_win_kills_boost_pos'] = tables['Opponent_pos_avg_kills_allowed_win'] / tables['league_pos_avg_kills_win'] | |
| tables['overall_win_deaths_boost_pos'] = tables['Opponent_pos_avg_deaths_allowed_win'] / tables['league_pos_avg_deaths_win'] | |
| tables['overall_win_assists_boost_pos'] = tables['Opponent_pos_avg_assists_allowed_win'] / tables['league_pos_avg_assists_win'] | |
| tables['overall_win_total_cs_boost_pos'] = tables['Opponent_pos_avg_total_cs_allowed_win'] / tables['league_pos_avg_total_cs_win'] | |
| tables['overall_loss_kills_boost_pos'] = tables['Opponent_pos_avg_kills_allowed_loss'] / tables['league_pos_avg_kills_loss'] | |
| tables['overall_loss_deaths_boost_pos'] = tables['Opponent_pos_avg_deaths_allowed_loss'] / tables['league_pos_avg_deaths_loss'] | |
| tables['overall_loss_assists_boost_pos'] = tables['Opponent_pos_avg_assists_allowed_loss'] / tables['league_pos_avg_assists_loss'] | |
| tables['overall_loss_total_cs_boost_pos'] = tables['Opponent_pos_avg_total_cs_allowed_loss'] / tables['league_pos_avg_total_cs_loss'] | |
| opp_tables = tables | |
| opp_pos_kills_boost_win = dict(zip(opp_tables['position'], opp_tables['overall_win_kills_boost_pos'])) | |
| opp_pos_deaths_boost_win = dict(zip(opp_tables['position'], opp_tables['overall_win_deaths_boost_pos'])) | |
| opp_pos_assists_boost_win = dict(zip(opp_tables['position'], opp_tables['overall_win_assists_boost_pos'])) | |
| opp_pos_cs_boost_win = dict(zip(opp_tables['position'], opp_tables['overall_win_total_cs_boost_pos'])) | |
| opp_pos_kills_boost_loss = dict(zip(opp_tables['position'], opp_tables['overall_loss_kills_boost_pos'])) | |
| opp_pos_deaths_boost_loss = dict(zip(opp_tables['position'], opp_tables['overall_loss_deaths_boost_pos'])) | |
| opp_pos_assists_boost_loss = dict(zip(opp_tables['position'], opp_tables['overall_loss_assists_boost_pos'])) | |
| opp_pos_cs_boost_loss = dict(zip(opp_tables['position'], opp_tables['overall_loss_total_cs_boost_pos'])) | |
| opp_boosts = pd.DataFrame({ | |
| 'opp_pos_kills_boost_win': opp_pos_kills_boost_win, | |
| 'opp_pos_deaths_boost_win': opp_pos_deaths_boost_win, | |
| 'opp_pos_assists_boost_win': opp_pos_assists_boost_win, | |
| 'opp_pos_cs_boost_win': opp_pos_cs_boost_win, | |
| 'opp_pos_kills_boost_loss': opp_pos_kills_boost_loss, | |
| 'opp_pos_deaths_boost_loss': opp_pos_deaths_boost_loss, | |
| 'opp_pos_assists_boost_loss': opp_pos_assists_boost_loss, | |
| 'opp_pos_cs_boost_loss': opp_pos_cs_boost_loss | |
| }).set_index(pd.Index(list(opp_pos_kills_boost_win.keys()), name='position')) | |
| if kill_prediction > 0: | |
| player_tables = player_tables[['playername', 'teamname', 'position', 'playername_avg_kill_share_win', 'playername_avg_death_share_win','playername_avg_assist_share_win', | |
| 'playername_avg_total_cs_win', 'playername_avg_kill_share_loss', 'playername_avg_death_share_loss', 'playername_avg_assist_share_loss', 'playername_avg_total_cs_loss']] | |
| player_tables = player_tables.rename(columns = {'playername_avg_kill_share_win': 'wKill%', 'playername_avg_death_share_win': 'wDeath%', 'playername_avg_assist_share_win': 'wAssist%', | |
| 'playername_avg_total_cs_win': 'wCS', 'playername_avg_kill_share_loss': 'lKill%', 'playername_avg_death_share_loss': 'lDeath%', | |
| 'playername_avg_assist_share_loss': 'lAssist%', 'playername_avg_total_cs_loss': 'lCS'}) | |
| team_data = player_tables.drop_duplicates(subset = ['playername']) | |
| if win_loss == "Win": | |
| team_data['Kill_Proj'] = team_data.apply(lambda row: row['wKill%'] * opp_pos_kills_boost_win.get(row['position'], 1), axis=1) | |
| team_data['Death_Proj'] = team_data.apply(lambda row: row['wDeath%'] * opp_pos_deaths_boost_win.get(row['position'], 1), axis=1) | |
| team_data['Assist_Proj'] = team_data.apply(lambda row: row['wAssist%'] * opp_pos_assists_boost_win.get(row['position'], 1), axis=1) | |
| team_data['CS_Proj'] = team_data.apply(lambda row: row['wCS'] * opp_pos_cs_boost_win.get(row['position'], 1), axis=1) | |
| team_data = team_data[['playername', 'teamname', 'position', 'Kill_Proj', 'Death_Proj', 'Assist_Proj', 'CS_Proj']] | |
| else: | |
| team_data['Kill_Proj'] = team_data.apply(lambda row: row['lKill%'] * opp_pos_kills_boost_loss.get(row['position'], 1), axis=1) | |
| team_data['Death_Proj'] = team_data.apply(lambda row: row['lDeath%'] * opp_pos_deaths_boost_loss.get(row['position'], 1), axis=1) | |
| team_data['Assist_Proj'] = team_data.apply(lambda row: row['lAssist%'] * opp_pos_assists_boost_loss.get(row['position'], 1), axis=1) | |
| team_data['CS_Proj'] = team_data.apply(lambda row: row['lCS'] * opp_pos_cs_boost_loss.get(row['position'], 1), axis=1) | |
| team_data = team_data[['playername', 'teamname', 'position', 'Kill_Proj', 'Death_Proj', 'Assist_Proj', 'CS_Proj']] | |
| else: | |
| player_tables = player_tables[['playername', 'teamname', 'position', 'playername_avg_kills_win', 'playername_avg_deaths_win', 'playername_avg_assists_win', 'playername_avg_total_cs_win', | |
| 'playername_avg_kills_loss', 'playername_avg_deaths_loss', 'playername_avg_assists_loss', 'playername_avg_total_cs_loss']] | |
| player_tables = player_tables.rename(columns = {'playername_avg_kills_win': 'wKill%', 'playername_avg_deaths_win': 'wDeath%', 'playername_avg_assists_win': 'wAssist%', | |
| 'playername_avg_total_cs_win': 'wCS', 'playername_avg_kills_loss': 'lKill%', 'playername_avg_deaths_loss': 'lDeath%', | |
| 'playername_avg_assists_loss': 'lAssist%', 'playername_avg_total_cs_loss': 'lCS'}) | |
| team_data = player_tables.drop_duplicates(subset = ['playername']) | |
| if win_loss == "Win": | |
| team_data['Kill_Proj'] = team_data.apply(lambda row: row['wKill%'] * opp_pos_kills_boost_win.get(row['position'], 1), axis=1) | |
| team_data['Death_Proj'] = team_data.apply(lambda row: row['wDeath%'] * opp_pos_deaths_boost_win.get(row['position'], 1), axis=1) | |
| team_data['Assist_Proj'] = team_data.apply(lambda row: row['wAssist%'] * opp_pos_assists_boost_win.get(row['position'], 1), axis=1) | |
| team_data['CS_Proj'] = team_data.apply(lambda row: row['wCS'] * opp_pos_cs_boost_win.get(row['position'], 1), axis=1) | |
| team_data = team_data[['playername', 'teamname', 'position', 'Kill_Proj', 'Death_Proj', 'Assist_Proj', 'CS_Proj']] | |
| else: | |
| team_data['Kill_Proj'] = team_data.apply(lambda row: row['lKill%'] * opp_pos_kills_boost_loss.get(row['position'], 1), axis=1) | |
| team_data['Death_Proj'] = team_data.apply(lambda row: row['lDeath%'] * opp_pos_deaths_boost_loss.get(row['position'], 1), axis=1) | |
| team_data['Assist_Proj'] = team_data.apply(lambda row: row['lAssist%'] * opp_pos_assists_boost_loss.get(row['position'], 1), axis=1) | |
| team_data['CS_Proj'] = team_data.apply(lambda row: row['lCS'] * opp_pos_cs_boost_loss.get(row['position'], 1), axis=1) | |
| team_data = team_data[['playername', 'teamname', 'position', 'Kill_Proj', 'Death_Proj', 'Assist_Proj', 'CS_Proj']] | |
| return team_data.dropna().set_index('playername'), opp_boosts | |
| 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(sim_df.style.format(precision=2), use_container_width=True) |