import streamlit as st st.set_page_config(layout="wide") for name in dir(): if not name.startswith('_'): del globals()[name] import numpy as np import pandas as pd import streamlit as st import gspread import plotly.express as px import random import gc @st.cache_resource def init_conn(): scope = ['https://www.googleapis.com/auth/spreadsheets', "https://www.googleapis.com/auth/drive"] credentials = { "type": "service_account", "project_id": "model-sheets-connect", "private_key_id": "0e0bc2fdef04e771172fe5807392b9d6639d945e", "private_key": "-----BEGIN PRIVATE KEY-----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\nF/j9eUXfXjAlb042MphoF3ZC\n-----END PRIVATE KEY-----\n", "client_email": "gspread-connection@model-sheets-connect.iam.gserviceaccount.com", "client_id": "100369174533302798535", "auth_uri": "https://accounts.google.com/o/oauth2/auth", "token_uri": "https://oauth2.googleapis.com/token", "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs", "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/gspread-connection%40model-sheets-connect.iam.gserviceaccount.com" } gc_con = gspread.service_account_from_dict(credentials) return gc_con gcservice_account = init_conn() master_hold = 'https://docs.google.com/spreadsheets/d/1D526UlXmrz-8qxVcUKrA-u7f6FftUiBufxDnzQv980k/edit#gid=791804525' sim_format = {'Top_finish': '{:.2%}', 'Top_5_finish': '{:.2%}', 'Top_10_finish': '{:.2%}'} @st.cache_resource(ttl = 600) def init_baselines(): sh = gcservice_account.open_by_url(master_hold) worksheet = sh.worksheet('Pitcher_Proj') raw_display = pd.DataFrame(worksheet.get_all_records()) raw_display.replace("", np.nan, inplace=True) pitcher_proj = raw_display.dropna() sh = gcservice_account.open_by_url(master_hold) worksheet = sh.worksheet('Hitter_Proj') raw_display = pd.DataFrame(worksheet.get_all_records()) raw_display.replace("", np.nan, inplace=True) hitter_proj = raw_display.dropna() sh = gcservice_account.open_by_url(master_hold) worksheet = sh.worksheet('Display') raw_display = pd.DataFrame(worksheet.get_all_records()) wins_proj = raw_display.dropna() return pitcher_proj, hitter_proj, wins_proj def convert_df_to_csv(df): return df.to_csv().encode('utf-8') pitcher_proj, hitter_proj, wins_proj = init_baselines() total_teams = pitcher_proj['Team'].values.tolist() tab1, tab2, tab3, tab4, tab5 = st.tabs(["Team Win Projections", "Pitcher Projections", "Hitter Projections", "Pitcher Simulations", "Hitter Simulations"]) with tab1: if st.button("Reset Data", key='reset1'): st.cache_data.clear() pitcher_proj, hitter_proj, wins_proj = init_baselines() total_teams = pitcher_proj['Team'].values.tolist() raw_frame = wins_proj.copy() export_frame_team = raw_frame[['Team', '2B', 'HR', 'SB', 'P_SO', 'P_H', 'P_R', 'P_HR', 'P_BB', 'LY Added', 'Added', 'LY Adj Wins', 'Adj Wins', 'Vegas', 'Proj wins', 'Diff']] export_frame_team = export_frame_team.sort_values(by='Proj wins', ascending=False) disp_frame = raw_frame[['Team', '2B', 'HR', 'SB', 'P_SO', 'P_H', 'P_R', 'P_HR', 'P_BB', 'LY Added', 'Added', 'LY Adj Wins', 'Adj Wins', 'Vegas', 'Proj wins', 'Diff']] disp_frame = disp_frame.sort_values(by='Proj wins', ascending=False) st.dataframe(disp_frame.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(precision=2), height = 1000, use_container_width = True) st.download_button( label="Export Team Win Projections", data=convert_df_to_csv(export_frame_team), file_name='MLB_team_win_export.csv', mime='text/csv', key='team_win_export', ) with tab2: if st.button("Reset Data", key='reset2'): st.cache_data.clear() pitcher_proj, hitter_proj, wins_proj = init_baselines() total_teams = pitcher_proj['Team'].values.tolist() raw_frame = pitcher_proj.copy() split_var1 = st.radio("Would you like to view all teams or specific ones?", ('All', 'Specific Teams'), key='split_var1') if split_var1 == 'Specific Teams': team_var1 = st.multiselect('Which teams would you like to include in the tables?', options = total_teams, key='team_var1') elif split_var1 == 'All': team_var1 = total_teams working_data = raw_frame[raw_frame['Team'].isin(team_var1)] export_frame_sp = raw_frame[['Name', 'Team', 'TBF', 'Ceiling_var', 'True_AVG', 'Hits', 'Singles%', 'Singles', 'Doubles%', 'Doubles', 'xHR%', 'Homeruns', 'Strikeout%', 'Strikeouts', 'Walk%', 'Walks', 'Runs%', 'Runs', 'ERA', 'Wins', 'Quality_starts', 'ADP', 'UD_fpts', 'DK_fpts']] disp_frame_sp = working_data[['Name', 'Team', 'TBF', 'True_AVG', 'Hits', 'Singles', 'Doubles', 'Homeruns', 'Strikeouts', 'Walks', 'Runs', 'ERA', 'Wins', 'Quality_starts', 'ADP', 'UD_fpts', 'DK_fpts']] disp_frame_sp = disp_frame_sp.sort_values(by='UD_fpts', ascending=False) st.dataframe(disp_frame_sp.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn_r').background_gradient(cmap='RdYlGn', subset=['TBF', 'Strikeouts', 'Wins', 'Quality_starts', 'UD_fpts', 'DK_fpts']).format(precision=2), height = 1000, use_container_width = True) st.download_button( label="Export Pitcher Projections", data=convert_df_to_csv(export_frame_sp), file_name='MLB_pitcher_proj_export.csv', mime='text/csv', key='pitcher_proj_export', ) with tab3: if st.button("Reset Data", key='reset3'): st.cache_data.clear() pitcher_proj, hitter_proj, wins_proj = init_baselines() total_teams = pitcher_proj['Team'].values.tolist() raw_frame = hitter_proj.copy() split_var2 = st.radio("Would you like to view all teams or specific ones?", ('All', 'Specific Teams'), key='split_var2') if split_var2 == 'Specific Teams': team_var2 = st.multiselect('Which teams would you like to include in the tables?', options = total_teams, key='team_var2') elif split_var2 == 'All': team_var2 = total_teams working_data = raw_frame[raw_frame['Team'].isin(team_var2)] export_frame_h = raw_frame[['Name', 'Team', 'PA', 'Ceiling_var', 'Walk%', 'Walks', 'xHits', 'Singles%', 'Singles', 'Doubles%', 'Doubles', 'xHR%', 'Homeruns', 'Runs%', 'Runs', 'RBI%', 'RBI', 'Steal%', 'Stolen_bases', 'ADP', 'UD_fpts', 'DK_fpts']] disp_frame_h = working_data[['Name', 'Team', 'PA', 'Walks', 'xHits', 'Singles', 'Doubles', 'Homeruns', 'Runs', 'RBI', 'Stolen_bases', 'ADP', 'UD_fpts', 'DK_fpts']] disp_frame_h = disp_frame_h.sort_values(by='UD_fpts', ascending=False) st.dataframe(disp_frame_h.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').background_gradient(cmap='RdYlGn_r', subset=['ADP']).format(precision=2), height = 1000, use_container_width = True) st.download_button( label="Export Hitter Projections", data=convert_df_to_csv(export_frame_h), file_name='MLB_hitter_proj_export.csv', mime='text/csv', key='hitter_proj_export', ) with tab4: if st.button("Reset Data", key='reset4'): st.cache_data.clear() pitcher_proj, hitter_proj, wins_proj = init_baselines() total_teams = pitcher_proj['Team'].values.tolist() col1, col2 = st.columns([1, 5]) with col2: df_hold_container = st.empty() with col1: prop_type_var_sp = st.selectbox('Select type of prop to simulate', options = ['Strikeouts', 'Wins', 'Quality_starts'], key='prop_type_var_sp') if st.button('Simulate Stat', key='sim_sp'): with col2: with df_hold_container.container(): df = pitcher_proj.copy() total_sims = 5000 df.replace("", 0, inplace=True) if prop_type_var_sp == 'Strikeouts': df['Median'] = df['Strikeouts'] stat_cap = 300 elif prop_type_var_sp == 'Wins': df['Median'] = df['Wins'] stat_cap = 25 elif prop_type_var_sp == 'Quality_starts': df['Median'] = df['Quality_starts'] stat_cap = 30 flex_file = df.copy() flex_file.rename(columns={"Name": "Player"}, inplace = True) flex_file['Floor'] = (flex_file['Median'] * .25) flex_file['Ceiling'] = np.where((flex_file['Median'] + (flex_file['Median'] * flex_file['Ceiling_var'])) > stat_cap, stat_cap + (flex_file['Median']/10), (flex_file['Median'] + (flex_file['Median'] * flex_file['Ceiling_var']))) flex_file['STD'] = (flex_file['Median']/3) flex_file = flex_file[['Player', 'Floor', 'Median', 'Ceiling', 'STD']] hold_file = flex_file.copy() hold_file = hold_file.sort_values(by='Median', ascending=False) overall_file = flex_file.copy() overall_file = overall_file.sort_values(by='Median', ascending=False) overall_players = overall_file[['Player']] for x in range(0,total_sims): overall_file['g'] = np.random.gumbel(overall_file['Median'] * .75,overall_file['STD']) overall_file[x] = np.where((overall_file['g']<=overall_file['Ceiling']),overall_file['g'],overall_file['Ceiling']) check_file = overall_file.copy() overall_file=overall_file.drop(['Player', 'Floor', 'Median', 'Ceiling', 'STD', 'g'], axis=1) overall_file.astype('int').dtypes players_only = hold_file[['Player']] raw_lineups_file = players_only.copy() for x in range(0,total_sims): maps_dict = {'proj_map':dict(zip(hold_file.Player,overall_file[x]))} raw_lineups_file[x] = sum([raw_lineups_file['Player'].map(maps_dict['proj_map'])]) players_only[x] = raw_lineups_file[x].rank(ascending=False) players_only=players_only.drop(['Player'], axis=1) players_only.astype('int').dtypes players_only['Average_Rank'] = players_only.mean(axis=1) players_only['Top_finish'] = players_only[players_only == 1].count(axis=1)/total_sims players_only['Top_5_finish'] = players_only[players_only <= 5].count(axis=1)/total_sims players_only['Top_10_finish'] = players_only[players_only <= 10].count(axis=1)/total_sims players_only['10%'] = overall_file.quantile(0.1, axis=1) players_only['90%'] = overall_file.quantile(0.9, axis=1) players_only['Player'] = hold_file[['Player']] final_outcomes = players_only[['Player', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '10%', '90%']] final_Proj = pd.merge(hold_file, final_outcomes, on="Player") final_Proj = final_Proj[['Player', '10%', 'Median', '90%', 'Top_finish', 'Top_5_finish', 'Top_10_finish']] final_Proj.rename(columns={"Median": "Projection"}, inplace = True) with df_hold_container.container(): df_hold_container = st.empty() st.dataframe(final_Proj.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(sim_format, precision=2), use_container_width = True) with tab5: if st.button("Reset Data", key='reset5'): st.cache_data.clear() pitcher_proj, hitter_proj, wins_proj = init_baselines() total_teams = pitcher_proj['Team'].values.tolist() col1, col2 = st.columns([1, 5]) with col2: df_hold_container = st.empty() with col1: prop_type_var_h = st.selectbox('Select type of prop to simulate', options = ['Hits', 'Doubles', 'Home Runs', 'RBI', 'Stolen Bases'], key='prop_type_var_h') if st.button('Simulate Stat', key='sim_h'): with col2: with df_hold_container.container(): df = hitter_proj.copy() total_sims = 5000 df.replace("", 0, inplace=True) if prop_type_var_h == 'Hits': df['Median'] = df['xHits'] stat_cap = 250 elif prop_type_var_h == 'Doubles': df['Median'] = df['Doubles'] stat_cap = 65 elif prop_type_var_h == 'Home Runs': df['Median'] = df['Homeruns'] stat_cap = 75 elif prop_type_var_h == 'RBI': df['Median'] = df['RBI'] stat_cap = 150 elif prop_type_var_h == 'Stolen Bases': df['Median'] = df['Stolen_bases'] stat_cap = 80 flex_file = df.copy() flex_file.rename(columns={"Name": "Player"}, inplace = True) flex_file['Floor'] = (flex_file['Median'] * .15) flex_file['Ceiling'] = np.where((flex_file['Median'] + (flex_file['Median'] * flex_file['Ceiling_var'])) > stat_cap, stat_cap + (flex_file['Median']/20), (flex_file['Median'] + (flex_file['Median'] * flex_file['Ceiling_var']))) flex_file['STD'] = (flex_file['Median']/2) flex_file = flex_file[['Player', 'Floor', 'Median', 'Ceiling', 'STD']] hold_file = flex_file.copy() hold_file = hold_file.sort_values(by='Median', ascending=False) overall_file = flex_file.copy() overall_file = overall_file.sort_values(by='Median', ascending=False) overall_players = overall_file[['Player']] for x in range(0,total_sims): overall_file['g'] = np.random.gumbel(overall_file['Median'] * .5,overall_file['STD']) overall_file[x] = np.where((overall_file['g']<=overall_file['Ceiling']),overall_file['g'],overall_file['Ceiling']) check_file = overall_file.copy() overall_file=overall_file.drop(['Player', 'Floor', 'Median', 'Ceiling', 'STD', 'g'], axis=1) overall_file.astype('int').dtypes players_only = hold_file[['Player']] raw_lineups_file = players_only.copy() for x in range(0,total_sims): maps_dict = {'proj_map':dict(zip(hold_file.Player,overall_file[x]))} raw_lineups_file[x] = sum([raw_lineups_file['Player'].map(maps_dict['proj_map'])]) players_only[x] = raw_lineups_file[x].rank(ascending=False) players_only=players_only.drop(['Player'], axis=1) players_only.astype('int').dtypes players_only['Average_Rank'] = players_only.mean(axis=1) players_only['Top_finish'] = players_only[players_only == 1].count(axis=1)/total_sims players_only['Top_5_finish'] = players_only[players_only <= 5].count(axis=1)/total_sims players_only['Top_10_finish'] = players_only[players_only <= 10].count(axis=1)/total_sims players_only['10%'] = overall_file.quantile(0.1, axis=1) players_only['90%'] = overall_file.quantile(0.9, axis=1) players_only['Player'] = hold_file[['Player']] final_outcomes = players_only[['Player', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '10%', '90%']] final_Proj = pd.merge(hold_file, final_outcomes, on="Player") final_Proj = final_Proj[['Player', '10%', 'Median', '90%', 'Top_finish', 'Top_5_finish', 'Top_10_finish']] final_Proj.rename(columns={"Median": "Projection"}, inplace = True) with df_hold_container.container(): df_hold_container = st.empty() st.dataframe(final_Proj.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(sim_format, precision=2), use_container_width = True)