app.py

import streamlit as st
import numpy as np
import pandas as pd
import streamlit as st
import gspread
import pymongo

st.set_page_config(layout="wide")

@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": st.secrets['model_sheets_connect_pk'],
          "private_key": "-----BEGIN PRIVATE KEY-----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\nF/j9eUXfXjAlb042MphoF3ZC\n-----END PRIVATE KEY-----\n",
          "client_email": "[email protected]",
          "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"
        }
        
        credentials2 = {
          "type": "service_account",
          "project_id": "sheets-api-connect-378620",
          "private_key_id": st.secrets['sheets_api_connect_pk'],
          "private_key": "-----BEGIN PRIVATE KEY-----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\nJuElxA33rFEjbgbzdyrE768=\n-----END PRIVATE KEY-----\n",
          "client_email": "gspread-connection@sheets-api-connect-378620.iam.gserviceaccount.com",
          "client_id": "106625872877651920064",
          "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%40sheets-api-connect-378620.iam.gserviceaccount.com"
        }

        uri = st.secrets['mongo_uri']
        client = pymongo.MongoClient(uri, retryWrites=True, serverSelectionTimeoutMS=500000)
        db = client["NBA_DFS"]
     
        NBA_Data = st.secrets['NBA_Data']

        gc = gspread.service_account_from_dict(credentials)
        gc2 = gspread.service_account_from_dict(credentials2)

        return gc, gc2, db, NBA_Data
    
gcservice_account, gcservice_account2, db, NBA_Data = init_conn()

dk_columns = ['PG', 'SG', 'SF', 'PF', 'C', 'G', 'F', 'FLEX', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
fd_columns = ['PG1', 'PG2', 'SG1', 'SG2', 'SF1', 'SF2', 'PF1', 'PF2', 'C1', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']

@st.cache_data(ttl=300)
def load_overall_stats():
    try:
        sh = gcservice_account.open_by_url(NBA_Data)
    except:
        sh = gcservice_account2.open_by_url(NBA_Data)  
    
    worksheet = sh.worksheet('DK_Build_Up')
    raw_display = pd.DataFrame(worksheet.get_all_records())
    raw_display.rename(columns={"Name": "Player", "Nickname": "Player", "Fantasy": "Median"}, inplace = True)
    raw_display.replace("", 'Welp', inplace=True)
    raw_display = raw_display.loc[raw_display['Player'] != 'Welp']
    raw_display = raw_display.loc[raw_display['Salary'] > 0]
    raw_display = raw_display.loc[raw_display['Median'] > 0]
    raw_display = raw_display.apply(pd.to_numeric, errors='ignore')
    dk_raw = raw_display.sort_values(by='Median', ascending=False)
    
    worksheet = sh.worksheet('FD_Build_Up')
    raw_display = pd.DataFrame(worksheet.get_all_records())
    raw_display.rename(columns={"Name": "Player", "Nickname": "Player", "Fantasy": "Median"}, inplace = True)
    raw_display.replace("", 'Welp', inplace=True)
    raw_display = raw_display.loc[raw_display['Player'] != 'Welp']
    raw_display = raw_display.loc[raw_display['Median'] > 0]
    raw_display = raw_display.apply(pd.to_numeric, errors='ignore')
    fd_raw = raw_display.sort_values(by='Median', ascending=False)
    
    worksheet = sh.worksheet('Secondary_DK_Build')
    raw_display = pd.DataFrame(worksheet.get_all_records())
    raw_display.rename(columns={"Name": "Player", "Nickname": "Player", "Fantasy": "Median"}, inplace = True)
    raw_display.replace("", 'Welp', inplace=True)
    raw_display = raw_display.loc[raw_display['Player'] != 'Welp']
    raw_display = raw_display.loc[raw_display['Median'] > 0]
    raw_display = raw_display.apply(pd.to_numeric, errors='ignore')
    dk_raw_sec = raw_display.sort_values(by='Median', ascending=False)
    
    worksheet = sh.worksheet('Secondary_FD_Build')
    raw_display = pd.DataFrame(worksheet.get_all_records())
    raw_display.rename(columns={"Name": "Player", "Nickname": "Player", "Fantasy": "Median"}, inplace = True)
    raw_display.replace("", 'Welp', inplace=True)
    raw_display = raw_display.loc[raw_display['Player'] != 'Welp']
    raw_display = raw_display.loc[raw_display['Median'] > 0]
    raw_display = raw_display.apply(pd.to_numeric, errors='ignore')
    fd_raw_sec = raw_display.sort_values(by='Median', ascending=False)

    worksheet = sh.worksheet('Player_Level_ROO')
    raw_display = pd.DataFrame(worksheet.get_all_records())
    raw_display.replace("", 'Welp', inplace=True)
    raw_display = raw_display.loc[raw_display['Player'] != 'Welp']
    raw_display = raw_display.loc[raw_display['Median'] > 0]
    raw_display = raw_display.apply(pd.to_numeric, errors='ignore')
    roo_raw = raw_display.sort_values(by='Median', ascending=False)

    timestamp = raw_display['timestamp'].values[0]

    return dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, timestamp

@st.cache_data(ttl = 300)
def init_DK_lineups():  
    
        collection = db["DK_NBA_seed_frame"] 
        cursor = collection.find()
    
        raw_display = pd.DataFrame(list(cursor))
        raw_display = raw_display[['PG', 'SG', 'SF', 'PF', 'C', 'G', 'F', 'FLEX', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
        DK_seed = raw_display.head(10000).to_numpy()

        return DK_seed

@st.cache_data(ttl = 300)
def init_FD_lineups():  
    
        collection = db["FD_NBA_seed_frame"] 
        cursor = collection.find()
    
        raw_display = pd.DataFrame(list(cursor))
        raw_display = raw_display[['PG1', 'PG2', 'SG1', 'SG2', 'SF1', 'SF2', 'PF1', 'PF2', 'C1', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
        FD_seed = raw_display.head(10000).to_numpy()

        return FD_seed

def convert_df_to_csv(df):
    return df.to_csv().encode('utf-8')

@st.cache_data
def convert_df(array):
    array = pd.DataFrame(array, columns=column_names)
    return array.to_csv().encode('utf-8')

dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, timestamp = load_overall_stats()
dk_lineups = init_DK_lineups()
fd_lineups = init_FD_lineups()
t_stamp = f"Last Update: " + str(timestamp) + f" CST"

tab1, tab2 = st.tabs(['Range of Outcomes', 'Optimals'])

with tab1:

    col1, col2 = st.columns([1, 9])

    with col1:
        st.info(t_stamp)
        if st.button("Load/Reset Data", key='reset1'):
            st.cache_data.clear()
            dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, timestamp = load_overall_stats()
            dk_lineups = init_DK_lineups()
            fd_lineups = init_FD_lineups()
            t_stamp = f"Last Update: " + str(timestamp) + f" CST"
            for key in st.session_state.keys():
                del st.session_state[key]
        site_var2 = st.radio("What table would you like to display?", ('Draftkings', 'Fanduel'), key='site_var2')
        if site_var2 == 'Draftkings':
            site_baselines = roo_raw[roo_raw['site'] == 'Draftkings']
        elif site_var2 == 'Fanduel':
            site_baselines = roo_raw[roo_raw['site'] == 'Fanduel']
        slate_split = st.radio("Are you viewing the main slate or the secondary slate?", ('Main Slate', 'Secondary'), key='slate_split')
        if slate_split == 'Main Slate':
            raw_baselines = site_baselines[site_baselines['slate'] == 'Main Slate']
        elif slate_split == 'Secondary':
            raw_baselines = site_baselines[site_baselines['slate'] == 'Secondary']
        split_var2 = st.radio("Are you running the full slate or certain games?", ('Full Slate Run', 'Specific Games'), key='split_var2')
        if split_var2 == 'Specific Games':
            team_var2 = st.multiselect('Which teams would you like to include in the ROO?', options = raw_baselines['Team'].unique(), key='team_var2')
        elif split_var2 == 'Full Slate Run':
            team_var2 = raw_baselines.Team.values.tolist()
        pos_var2 = st.selectbox('View specific position?', options = ['All', 'PG', 'SG', 'SF', 'PF', 'C'], key='pos_var2')

    with col2:
        display_container_1 = st.empty()
        display_dl_container_1 = st.empty()
        display_proj = raw_baselines[raw_baselines['Team'].isin(team_var2)]
        display_proj = display_proj.drop(columns=['site', 'version', 'slate', 'timestamp'])
        
        st.session_state.display_proj = display_proj
            
        with display_container_1:
            display_container = st.empty()
            if 'display_proj' in st.session_state:
                if pos_var2 == 'All':
                    st.session_state.display_proj = st.session_state.display_proj
                elif pos_var2 != 'All':
                    st.session_state.display_proj = st.session_state.display_proj[st.session_state.display_proj['Position'].str.contains(pos_var2)]
                st.dataframe(st.session_state.display_proj.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(precision=2), height=1000, use_container_width = True)
        
        with display_dl_container_1:
                display_dl_container = st.empty()
                if 'display_proj' in st.session_state:
                    st.download_button(
                                label="Export Tables",
                                data=convert_df_to_csv(st.session_state.display_proj),
                                file_name='NBA_ROO_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()
            dk_raw, fd_raw, dk_raw_sec, fd_raw_sec, roo_raw, timestamp = load_overall_stats()
            dk_lineups = init_DK_lineups()
            fd_lineups = init_FD_lineups()
            t_stamp = f"Last Update: " + str(timestamp) + f" CST"
            for key in st.session_state.keys():
                del st.session_state[key]
              
        slate_var1 = st.radio("Which data are you loading?", ('Main Slate', 'Just the Main Slate'))
        site_var1 = st.radio("What site are you working with?", ('Draftkings', 'Fanduel'))
        if site_var1 == 'Draftkings':
            raw_baselines = dk_raw
            # Get the minimum and maximum ownership values from dk_lineups
            min_own = np.min(dk_lineups[:,14].values)
            max_own = np.max(dk_lineups[:,14].values)
            column_names = dk_columns
            
            player_var1 = st.radio("Do you want a frame with specific Players?", ('Full Slate', 'Specific Players'), key='player_var1')
            if player_var1 == 'Specific Players':
                    player_var2 = st.multiselect('Which players do you want?', options = dk_raw['Player'].unique())
            elif player_var1 == 'Full Slate':
                    player_var2 = dk_raw.Player.values.tolist()
            
            own_var_low, own_var_high = st.slider("Select ownership range", 
                                  min_value=float(min_own), 
                                  max_value=float(max_own), 
                                  value=(float(min_own), float(max_own)), 
                                  step=10)
                    
        elif site_var1 == 'Fanduel':
            raw_baselines = fd_raw
            min_own = np.min(fd_lineups[:,15].values)
            max_own = np.max(fd_lineups[:,15].values)
            column_names = fd_columns
            
            player_var1 = st.radio("Do you want a frame with specific Players?", ('Full Slate', 'Specific Players'), key='player_var1')
            if player_var1 == 'Specific Players':
                    player_var2 = st.multiselect('Which players do you want?', options = fd_raw['Player'].unique())
            elif player_var1 == 'Full Slate':
                    player_var2 = fd_raw.Player.values.tolist()
            
            own_var_low, own_var_high = st.slider("Select ownership range", 
                                  min_value=float(min_own), 
                                  max_value=float(max_own), 
                                  value=(float(min_own), float(max_own)), 
                                  step=10)
                    
        

        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='NBA_optimals_export.csv',
                    mime='text/csv',
                )
            
    with col2:
        if site_var1 == 'Draftkings':
            if 'working_seed' in st.session_state:
                st.session_state.working_seed = st.session_state.working_seed
                st.session_state.working_seed = st.session_state.working_seed[st.session_state.working_seed['Own'] >= own_var_low]
                st.session_state.working_seed = st.session_state.working_seed[st.session_state.working_seed['Own'] <= own_var_high]
                # Create a mask to check if any column contains a player from player_var2
                player_mask = st.session_state.working_seed.apply(lambda row: any(player in str(cell) for player in player_var2 for cell in row), axis=1)
                
                # Apply the mask to filter the DataFrame
                st.session_state.working_seed = st.session_state.working_seed[player_mask]
                st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:151], columns=column_names)
            elif 'working_seed' not in st.session_state:
                st.session_state.working_seed = dk_lineups.copy()
                st.session_state.working_seed = st.session_state.working_seed
                st.session_state.working_seed = st.session_state.working_seed[st.session_state.working_seed['Own'] >= own_var_low]
                st.session_state.working_seed = st.session_state.working_seed[st.session_state.working_seed['Own'] <= own_var_high]
                # Create a mask to check if any column contains a player from player_var2
                player_mask = st.session_state.working_seed.apply(lambda row: any(player in str(cell) for player in player_var2 for cell in row), axis=1)
                
                # Apply the mask to filter the DataFrame
                st.session_state.working_seed = st.session_state.working_seed[player_mask]
                st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:151], columns=column_names)
            
        elif site_var1 == 'Fanduel':
            if 'working_seed' in st.session_state:
                st.session_state.working_seed = st.session_state.working_seed
                st.session_state.working_seed = st.session_state.working_seed[st.session_state.working_seed['Own'] >= own_var_low]
                st.session_state.working_seed = st.session_state.working_seed[st.session_state.working_seed['Own'] <= own_var_high]
                # Create a mask to check if any column contains a player from player_var2
                player_mask = st.session_state.working_seed.apply(lambda row: any(player in str(cell) for player in player_var2 for cell in row), axis=1)
                
                # Apply the mask to filter the DataFrame
                st.session_state.working_seed = st.session_state.working_seed[player_mask]
                st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:151], columns=column_names)
            elif 'working_seed' not in st.session_state:
                st.session_state.working_seed = fd_lineups.copy()
                st.session_state.working_seed = st.session_state.working_seed
                st.session_state.working_seed = st.session_state.working_seed[st.session_state.working_seed['Own'] >= own_var_low]
                st.session_state.working_seed = st.session_state.working_seed[st.session_state.working_seed['Own'] <= own_var_high]
                # Create a mask to check if any column contains a player from player_var2
                player_mask = st.session_state.working_seed.apply(lambda row: any(player in str(cell) for player in player_var2 for cell in row), axis=1)
                
                # Apply the mask to filter the DataFrame
                st.session_state.working_seed = st.session_state.working_seed[player_mask]
                st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:151], columns=column_names)
                
        with st.container():
            if 'data_export_display' in st.session_state:
                st.dataframe(st.session_state.data_export_display.style.format(precision=2), use_container_width = True)