import streamlit as st st.set_page_config(layout="wide") import numpy as np import pandas as pd import gspread import pymongo @st.cache_resource def init_conn(): scope = ['https://spreadsheets.google.com/feeds', '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" } uri = "mongodb+srv://multichem:Xr1q5wZdXPbxdUmJ@testcluster.lgwtp5i.mongodb.net/?retryWrites=true&w=majority&appName=TestCluster" client = pymongo.MongoClient(uri, retryWrites=True, serverSelectionTimeoutMS=100000) db = client["testing_db"] collection = db["DK_MLB_seed_frame"] cursor = collection.find() raw_display = pd.DataFrame(list(cursor)) raw_display = raw_display[['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count']] DK_seed = raw_display.to_numpy() collection = db["FD_MLB_seed_frame"] cursor = collection.find() raw_display = pd.DataFrame(list(cursor)) raw_display = raw_display[['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count']] FD_seed = raw_display.to_numpy() MLB_Data = 'https://docs.google.com/spreadsheets/d/1f42Ergav8K1VsOLOK9MUn7DM_MLMvv4GR2Fy7EfnZTc/edit#gid=340831852' gc_con = gspread.service_account_from_dict(credentials, scope) client.close() return gc_con, client, db, DK_seed, FD_seed, MLB_Data gcservice_account, client, db, DK_seed, FD_seed, MLB_Data = init_conn() percentages_format = {'Exposure': '{:.2%}'} dk_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count'] fd_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count'] @st.cache_data(ttl = 60) def init_baselines(): sh = gcservice_account.open_by_url(MLB_Data) worksheet = sh.worksheet('Main_ROO') load_display = pd.DataFrame(worksheet.get_all_records()) load_display.replace('', np.nan, inplace=True) load_display['STDev'] = load_display['Median'] / 3 dk_raw = load_display.dropna(subset=['Median']) worksheet = sh.worksheet('Main_FD_ROO') load_display = pd.DataFrame(worksheet.get_all_records()) load_display.replace('', np.nan, inplace=True) load_display['STDev'] = load_display['Median'] / 3 fd_raw = load_display.dropna(subset=['Median']) return dk_raw, fd_raw @st.cache_data def convert_df(array): array = pd.DataFrame(array, columns=column_names) return array.to_csv().encode('utf-8') @st.cache_data def calculate_DK_value_frequencies(np_array): unique, counts = np.unique(np_array[:, :9], return_counts=True) frequencies = counts / len(np_array) # Normalize by the number of rows combined_array = np.column_stack((unique, frequencies)) return combined_array @st.cache_data def calculate_FD_value_frequencies(np_array): unique, counts = np.unique(np_array[:, :8], return_counts=True) frequencies = counts / len(np_array) # Normalize by the number of rows combined_array = np.column_stack((unique, frequencies)) return combined_array @st.cache_data def sim_contest(Sim_size, seed_frame, maps_dict, sharp_split, Contest_Size): SimVar = 1 Sim_Winners = [] fp_array = seed_frame[:sharp_split, :] # Pre-vectorize functions vec_projection_map = np.vectorize(maps_dict['Projection_map'].__getitem__) vec_stdev_map = np.vectorize(maps_dict['STDev_map'].__getitem__) st.write('Simulating contest on frames') while SimVar <= Sim_size: fp_random = fp_array[np.random.choice(fp_array.shape[0], Contest_Size)] sample_arrays1 = np.c_[ fp_random, np.sum(np.random.normal( loc=vec_projection_map(fp_random[:, :-6]), scale=vec_stdev_map(fp_random[:, :-6])), axis=1) ] sample_arrays = sample_arrays1 final_array = sample_arrays[sample_arrays[:, 10].argsort()[::-1]] best_lineup = final_array[final_array[:, -1].argsort(kind='stable')[::-1][:1]] Sim_Winners.append(best_lineup) SimVar += 1 return Sim_Winners dk_raw, fd_raw = init_baselines() tab1, tab2 = st.tabs(['Data Export', 'Contest Sims']) with tab1: col1, col2 = st.columns([1, 7]) with col1: if st.button("Load/Reset Data", key='reset1'): st.cache_data.clear() for key in st.session_state.keys(): del st.session_state[key] dk_raw, fd_raw = init_baselines() slate_var1 = st.radio("Which data are you loading?", ('Main Slate', 'Other Main Slate')) site_var1 = st.radio("What site are you working with?", ('Draftkings', 'Fanduel')) if site_var1 == 'Draftkings': raw_baselines = dk_raw column_names = dk_columns team_var1 = st.radio("Do you want a frame with specific teams?", ('Full Slate', 'Specific Teams'), key='team_var1') if team_var1 == 'Specific Teams': team_var2 = st.multiselect('Which teams do you want?', options = dk_raw['Team'].unique()) elif team_var1 == 'Full Slate': team_var2 = dk_raw.Team.values.tolist() stack_var1 = st.radio("Do you want a frame with specific stack sizes?", ('Full Slate', 'Specific Stack Sizes'), key='stack_var1') if stack_var1 == 'Specific Stack Sizes': stack_var2 = st.multiselect('Which stack sizes do you want?', options = [5, 4, 3, 2, 1, 0]) elif stack_var1 == 'Full Slate': stack_var2 = [5, 4, 3, 2, 1, 0] elif site_var1 == 'Fanduel': raw_baselines = fd_raw column_names = fd_columns team_var1 = st.radio("Do you want a frame with specific teams?", ('Full Slate', 'Specific Teams'), key='team_var1') if team_var1 == 'Specific Teams': team_var2 = st.multiselect('Which teams do you want?', options = fd_raw['Team'].unique()) elif team_var1 == 'Full Slate': team_var2 = fd_raw.Team.values.tolist() stack_var1 = st.radio("Do you want a frame with specific stack sizes?", ('Full Slate', 'Specific Stack Sizes'), key='stack_var1') if stack_var1 == 'Specific Stack Sizes': stack_var2 = st.multiselect('Which stack sizes do you want?', options = [4, 3, 2, 1, 0]) elif stack_var1 == 'Full Slate': stack_var2 = [4, 3, 2, 1, 0] with col2: if st.button("Load Data", key='load_data'): if site_var1 == 'Draftkings': if 'working_seed' in st.session_state: column_indices = [12, 13] filter_mask = np.logical_or( np.isin(st.session_state.working_seed[:, column_indices[0]], team_var2), np.isin(st.session_state.working_seed[:, column_indices[1]], stack_var2) ) st.session_state.working_seed = st.session_state.working_seed[filter_mask] st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:1000], columns=column_names) if 'data_export_display' in st.session_state: st.session_state.data_export_freq = pd.DataFrame(calculate_DK_value_frequencies(st.session_state.working_seed), columns=['Player', 'Exposure']) st.session_state.data_export_freq = st.session_state.data_export_freq.sort_values(by='Exposure', ascending=False) else: st.session_state.working_seed = DK_seed.copy() column_indices = [12, 13] filter_mask = np.logical_or( np.isin(st.session_state.working_seed[:, column_indices[0]], team_var2), np.isin(st.session_state.working_seed[:, column_indices[1]], stack_var2) ) st.session_state.working_seed = st.session_state.working_seed[filter_mask] st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:1000], columns=column_names) if 'data_export_display' in st.session_state: st.session_state.data_export_freq = pd.DataFrame(calculate_DK_value_frequencies(st.session_state.working_seed), columns=['Player', 'Exposure']) st.session_state.data_export_freq = st.session_state.data_export_freq.sort_values(by='Exposure', ascending=False) elif site_var1 == 'Fanduel': if 'working_seed' in st.session_state: column_indices = [11, 12] filter_mask = np.logical_or( np.isin(st.session_state.working_seed[:, column_indices[0]], team_var2), np.isin(st.session_state.working_seed[:, column_indices[1]], stack_var2) ) st.session_state.working_seed = st.session_state.working_seed[filter_mask] st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:1000], columns=column_names) if 'data_export_display' in st.session_state: st.session_state.data_export_freq = pd.DataFrame(calculate_FD_value_frequencies(st.session_state.working_seed), columns=['Player', 'Exposure']) st.session_state.data_export_freq = st.session_state.data_export_freq.sort_values(by='Exposure', ascending=False) else: st.session_state.working_seed = FD_seed.copy() column_indices = [11, 12] filter_mask = np.logical_or( np.isin(st.session_state.working_seed[:, column_indices[0]], team_var2), np.isin(st.session_state.working_seed[:, column_indices[1]], stack_var2) ) st.session_state.working_seed = st.session_state.working_seed[filter_mask] st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:1000], columns=column_names) if 'data_export_display' in st.session_state: st.session_state.data_export_freq = pd.DataFrame(calculate_FD_value_frequencies(st.session_state.working_seed), columns=['Player', 'Exposure']) st.session_state.data_export_freq = st.session_state.data_export_freq.sort_values(by='Exposure', ascending=False) with st.container(): if 'data_export_display' in st.session_state: st.dataframe(st.session_state.data_export_display.style.format(precision=2), height=500, use_container_width=True) with st.container(): if 'data_export_freq' in st.session_state: st.dataframe(st.session_state.data_export_freq.style.format(percentages_format, precision=2), height=500, use_container_width=True) if st.button("Prepare data export", key='data_export'): data_export = st.session_state.working_seed.copy() st.download_button( label="Export optimals set", data=convert_df(data_export), file_name='MLB_optimals_export.csv', mime='text/csv', ) with tab2: col1, col2 = st.columns([1, 7]) with col1: if st.button("Load/Reset Data", key='reset2'): st.cache_data.clear() for key in st.session_state.keys(): del st.session_state[key] dk_raw, fd_raw = init_baselines() sim_slate_var1 = st.radio("Which data are you loading?", ('Main Slate', 'Other Main Slate'), key='sim_slate_var1') sim_site_var1 = st.radio("What site are you working with?", ('Draftkings', 'Fanduel'), key='sim_site_var1') if sim_site_var1 == 'Draftkings': raw_baselines = dk_raw column_names = dk_columns elif sim_site_var1 == 'Fanduel': raw_baselines = fd_raw column_names = fd_columns contest_var1 = st.selectbox("What contest size are you simulating?", ('Small', 'Medium', 'Large', 'Massive')) if contest_var1 == 'Small': Contest_Size = 1000 elif contest_var1 == 'Medium': Contest_Size = 5000 elif contest_var1 == 'Large': Contest_Size = 10000 elif contest_var1 == 'Massive': Contest_Size = 100000 strength_var1 = st.selectbox("How sharp is the field in the contest?", ('Very', 'Average', 'Not Very')) if strength_var1 == 'Not Very': sharp_split = 500000 elif strength_var1 == 'Average': sharp_split = 250000 elif strength_var1 == 'Very': sharp_split = 100000 with col2: if st.button("Run Contest Sim"): if 'working_seed' in st.session_state: maps_dict = { 'Floor_map':dict(zip(raw_baselines.Player,raw_baselines.Floor)), 'Projection_map':dict(zip(raw_baselines.Player,raw_baselines.Median)), 'Ceiling_map':dict(zip(raw_baselines.Player,raw_baselines.Ceiling)), 'Salary_map':dict(zip(raw_baselines.Player,raw_baselines.Salary)), 'Pos_map':dict(zip(raw_baselines.Player,raw_baselines.Position)), 'Own_map':dict(zip(raw_baselines.Player,raw_baselines['Own%'])), 'Small_Own_map':dict(zip(raw_baselines.Player,raw_baselines['Small Field Own%'])), 'Large_Own_map':dict(zip(raw_baselines.Player,raw_baselines['Large Field Own%'])), 'Team_map':dict(zip(raw_baselines.Player,raw_baselines.Team)), 'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev)), 'team_check_map':dict(zip(raw_baselines.Player,raw_baselines.Team)) } Sim_Winners = sim_contest(1000, st.session_state.working_seed, maps_dict, sharp_split, Contest_Size) Sim_Winner_Frame = pd.DataFrame(np.concatenate(Sim_Winners)) #st.table(Sim_Winner_Frame) # Initial setup Sim_Winner_Frame = pd.DataFrame(np.concatenate(Sim_Winners), columns=column_names + ['Fantasy']) Sim_Winner_Frame['GPP_Proj'] = (Sim_Winner_Frame['proj'] + Sim_Winner_Frame['Fantasy']) / 2 Sim_Winner_Frame['unique_id'] = Sim_Winner_Frame['proj'].astype(str) + Sim_Winner_Frame['salary'].astype(str) + Sim_Winner_Frame['Team'].astype(str) + Sim_Winner_Frame['Secondary'].astype(str) Sim_Winner_Frame = Sim_Winner_Frame.assign(win_count=Sim_Winner_Frame['unique_id'].map(Sim_Winner_Frame['unique_id'].value_counts())) # Type Casting type_cast_dict = {'salary': int, 'proj': np.float16, 'Fantasy': np.float16, 'GPP_Proj': np.float32} Sim_Winner_Frame = Sim_Winner_Frame.astype(type_cast_dict) # Sorting st.session_state.Sim_Winner_Frame = Sim_Winner_Frame.sort_values(by=['win_count', 'GPP_Proj'], ascending= [False, False]).copy().drop_duplicates(subset='unique_id').head(100) st.session_state.Sim_Winner_Frame.drop(columns='unique_id', inplace=True) st.dataframe(st.session_state.Sim_Winner_Frame) # # Data Copying # st.session_state.Sim_Winner_Export = Sim_Winner_Frame.copy() # # Data Copying # st.session_state.Sim_Winner_Display = Sim_Winner_Frame.copy() else: if sim_site_var1 == 'Draftkings': st.session_state.working_seed = DK_seed.copy() elif sim_site_var1 == 'Fanduel': st.session_state.working_seed = FD_seed.copy() maps_dict = { 'Floor_map':dict(zip(raw_baselines.Player,raw_baselines.Floor)), 'Projection_map':dict(zip(raw_baselines.Player,raw_baselines.Median)), 'Ceiling_map':dict(zip(raw_baselines.Player,raw_baselines.Ceiling)), 'Salary_map':dict(zip(raw_baselines.Player,raw_baselines.Salary)), 'Pos_map':dict(zip(raw_baselines.Player,raw_baselines.Position)), 'Own_map':dict(zip(raw_baselines.Player,raw_baselines['Own%'])), 'Small_Own_map':dict(zip(raw_baselines.Player,raw_baselines['Small Field Own%'])), 'Large_Own_map':dict(zip(raw_baselines.Player,raw_baselines['Large Field Own%'])), 'Team_map':dict(zip(raw_baselines.Player,raw_baselines.Team)), 'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev)), 'team_check_map':dict(zip(raw_baselines.Player,raw_baselines.Team)) } Sim_Winners = sim_contest(1000, st.session_state.working_seed, maps_dict, sharp_split, Contest_Size) Sim_Winner_Frame = pd.DataFrame(np.concatenate(Sim_Winners)) #st.table(Sim_Winner_Frame) # Initial setup Sim_Winner_Frame = pd.DataFrame(np.concatenate(Sim_Winners), columns=column_names + ['Fantasy']) Sim_Winner_Frame['GPP_Proj'] = (Sim_Winner_Frame['proj'] + Sim_Winner_Frame['Fantasy']) / 2 Sim_Winner_Frame['unique_id'] = Sim_Winner_Frame['proj'].astype(str) + Sim_Winner_Frame['salary'].astype(str) + Sim_Winner_Frame['Team'].astype(str) + Sim_Winner_Frame['Secondary'].astype(str) Sim_Winner_Frame = Sim_Winner_Frame.assign(win_count=Sim_Winner_Frame['unique_id'].map(Sim_Winner_Frame['unique_id'].value_counts())) # Type Casting type_cast_dict = {'salary': int, 'proj': np.float16, 'Fantasy': np.float16, 'GPP_Proj': np.float32} Sim_Winner_Frame = Sim_Winner_Frame.astype(type_cast_dict) # Sorting st.session_state.Sim_Winner_Frame = Sim_Winner_Frame.sort_values(by=['win_count', 'GPP_Proj'], ascending= [False, False]).copy().drop_duplicates(subset='unique_id').head(100) st.session_state.Sim_Winner_Frame.drop(columns='unique_id', inplace=True) st.dataframe(st.session_state.Sim_Winner_Frame) # # Data Copying # st.session_state.Sim_Winner_Export = Sim_Winner_Frame.copy() # # Data Copying # st.session_state.Sim_Winner_Display = Sim_Winner_Frame.copy()