app.py

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

st.set_page_config(layout="wide")

@st.cache_resource
def init_conn():
        uri = st.secrets['mongo_uri']
        client = pymongo.MongoClient(uri, retryWrites=True, serverSelectionTimeoutMS=500000)
        db = client["MLB_Database"]

        return db
    
db = init_conn()

game_format = {'Win%': '{:.2%}','First Inning Lead Percentage': '{:.2%}', 'Top Score': '{:.2%}',
              'Fifth Inning Lead Percentage': '{:.2%}', '8+ Runs': '{:.2%}', 'LevX': '{:.2%}'}

player_roo_format = {'Top_finish': '{:.2%}','Top_5_finish': '{:.2%}', 'Top_10_finish': '{:.2%}', '20+%': '{:.2%}', '2x%': '{:.2%}', '3x%': '{:.2%}',
                   '4x%': '{:.2%}'}

dk_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
fd_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
dk_sd_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']
fd_sd_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']

@st.cache_resource(ttl = 60)
def init_baselines():
    collection = db["Player_Range_Of_Outcomes"] 
    cursor = collection.find()
    player_frame = pd.DataFrame(cursor)

    roo_data = player_frame.drop(columns=['_id'])
    roo_data['Salary'] = roo_data['Salary'].astype(int)
    
    dk_roo = roo_data[roo_data['Site'] == 'Draftkings']
    dk_id_map = dict(zip(dk_roo['Player'], dk_roo['player_ID']))
    fd_roo = roo_data[roo_data['Site'] == 'Fanduel']
    fd_id_map = dict(zip(fd_roo['Player'], fd_roo['player_ID']))

    collection = db["Player_SD_Range_Of_Outcomes"] 
    cursor = collection.find()
    player_frame = pd.DataFrame(cursor)

    sd_roo_data = player_frame.drop(columns=['_id'])
    sd_roo_data['Salary'] = sd_roo_data['Salary'].astype(int)
    sd_roo_data = sd_roo_data.rename(columns={'Own': 'Own%'})

    collection = db["Scoring_Percentages"] 
    cursor = collection.find()
    team_frame = pd.DataFrame(cursor)
    scoring_percentages = team_frame.drop(columns=['_id'])
    scoring_percentages = scoring_percentages[['Names', 'Avg First Inning', 'First Inning Lead Percentage', 'Avg Fifth Inning', 'Fifth Inning Lead Percentage', 'Avg Score', '8+ runs', 'Win Percentage',
    'DK Main Slate', 'DK Secondary Slate', 'DK Turbo Slate', 'FD Main Slate', 'FD Secondary Slate', 'FD Turbo Slate', 'DK Main Top Score', 'FD Main Top Score', 'DK Secondary Top Score', 'FD Secondary Top Score',
    'DK Turbo Top Score', 'FD Turbo Top Score']]
    scoring_percentages['8+ runs'] = scoring_percentages['8+ runs'].replace('%', '', regex=True).astype(float)
    scoring_percentages['Win Percentage'] = scoring_percentages['Win Percentage'].replace('%', '', regex=True).astype(float)
    scoring_percentages['DK Main Top Score'] = scoring_percentages['DK Main Top Score'].replace('', np.nan).astype(float)
    scoring_percentages['FD Main Top Score'] = scoring_percentages['FD Main Top Score'].replace('', np.nan).astype(float)
    scoring_percentages['DK Secondary Top Score'] = scoring_percentages['DK Secondary Top Score'].replace('', np.nan).astype(float)
    scoring_percentages['FD Secondary Top Score'] = scoring_percentages['FD Secondary Top Score'].replace('', np.nan).astype(float)
    scoring_percentages['DK Turbo Top Score'] = scoring_percentages['DK Turbo Top Score'].replace('', np.nan).astype(float)
    scoring_percentages['FD Turbo Top Score'] = scoring_percentages['FD Turbo Top Score'].replace('', np.nan).astype(float)
    
    return roo_data, sd_roo_data, scoring_percentages, dk_roo, fd_roo, dk_id_map, fd_id_map

@st.cache_data(ttl = 60)
def init_DK_lineups(type_var, slate_var):  
    
    if type_var == 'Regular':
        if slate_var == 'Main':
            collection = db['DK_MLB_name_map']
            cursor = collection.find()
            raw_data = pd.DataFrame(list(cursor))
            names_dict = dict(zip(raw_data['key'], raw_data['value']))

            collection = db['DK_MLB_seed_frame']
            cursor = collection.find().limit(10000)

            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', 'Own']]
            dict_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
            # Map names
            raw_display[dict_columns] = raw_display[dict_columns].apply(lambda x: x.map(names_dict))
        elif slate_var == 'Secondary':
            collection = db['DK_MLB_Secondary_name_map']
            cursor = collection.find()
            raw_data = pd.DataFrame(list(cursor))
            names_dict = dict(zip(raw_data['key'], raw_data['value']))
            
            collection = db['DK_MLB_Secondary_seed_frame']
            cursor = collection.find().limit(10000)

            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', 'Own']]
            dict_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
            # Map names
            raw_display[dict_columns] = raw_display[dict_columns].apply(lambda x: x.map(names_dict))
        elif slate_var == 'Auxiliary':
            collection = db['DK_MLB_Turbo_name_map']
            cursor = collection.find()
            raw_data = pd.DataFrame(list(cursor))
            names_dict = dict(zip(raw_data['key'], raw_data['value']))
            
            collection = db['DK_MLB_Turbo_seed_frame']
            cursor = collection.find().limit(10000)

            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', 'Own']]
            dict_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
            # Map names
            raw_display[dict_columns] = raw_display[dict_columns].apply(lambda x: x.map(names_dict))
    elif type_var == 'Showdown':
        if slate_var == 'Main':
            collection = db['DK_MLB_SD1_seed_frame']
            cursor = collection.find().limit(10000)

            raw_display = pd.DataFrame(list(cursor))
            raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
        elif slate_var == 'Secondary':
            collection = db['DK_MLB_SD2_seed_frame']
            cursor = collection.find().limit(10000)

            raw_display = pd.DataFrame(list(cursor))
            raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
        elif slate_var == 'Auxiliary':
            collection = db['DK_MLB_SD3_seed_frame']
            cursor = collection.find().limit(10000)

            raw_display = pd.DataFrame(list(cursor))
            raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]

    DK_seed = raw_display.to_numpy()

    return DK_seed

@st.cache_data(ttl = 60)
def init_FD_lineups(type_var,slate_var):  
        
        if type_var == 'Regular':
            if slate_var == 'Main':
                collection = db['FD_MLB_name_map']
                cursor = collection.find()
                raw_data = pd.DataFrame(list(cursor))
                names_dict = dict(zip(raw_data['key'], raw_data['value']))

                collection = db['FD_MLB_seed_frame']
                cursor = collection.find().limit(10000)

                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', 'Own']]
                dict_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
                # Map names
                raw_display[dict_columns] = raw_display[dict_columns].apply(lambda x: x.map(names_dict))
            elif slate_var == 'Secondary':
                collection = db['FD_MLB_Secondary_name_map']
                cursor = collection.find()
                raw_data = pd.DataFrame(list(cursor))
                names_dict = dict(zip(raw_data['key'], raw_data['value']))

                collection = db['FD_MLB_Secondary_seed_frame']
                cursor = collection.find().limit(10000)

                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', 'Own']]
                dict_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
                # Map names
                raw_display[dict_columns] = raw_display[dict_columns].apply(lambda x: x.map(names_dict))
            elif slate_var == 'Auxiliary':
                collection = db['FD_MLB_Turbo_name_map']
                cursor = collection.find()
                raw_data = pd.DataFrame(list(cursor))
                names_dict = dict(zip(raw_data['key'], raw_data['value']))

                collection = db['FD_MLB_Turbo_seed_frame']
                cursor = collection.find().limit(10000)
            
                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', 'Own']]
                dict_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
                # Map names
                raw_display[dict_columns] = raw_display[dict_columns].apply(lambda x: x.map(names_dict))

        elif type_var == 'Showdown':
            if slate_var == 'Main':
                collection = db['FD_MLB_SD1_seed_frame']
                cursor = collection.find().limit(10000)

                raw_display = pd.DataFrame(list(cursor))
                raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
            elif slate_var == 'Secondary':
                collection = db['FD_MLB_SD2_seed_frame']
                cursor = collection.find().limit(10000)

                raw_display = pd.DataFrame(list(cursor))
                raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
            elif slate_var == 'Auxiliary':
                collection = db['FD_MLB_SD3_seed_frame']
                cursor = collection.find().limit(10000)
            
                raw_display = pd.DataFrame(list(cursor))
                raw_display = raw_display[['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
    
        FD_seed = raw_display.to_numpy()

        return FD_seed

@st.cache_data
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')

col1, col2 = st.columns([1, 9])
with col1:
    if st.button("Load/Reset Data", key='reset'):
        st.cache_data.clear()
        roo_data, sd_roo_data, scoring_percentages, dk_roo, fd_roo, dk_id_map, fd_id_map = init_baselines()
        hold_display = roo_data
        dk_lineups = init_DK_lineups('Regular', 'Main')
        fd_lineups = init_FD_lineups('Regular', 'Main')
        for key in st.session_state.keys():
            del st.session_state[key]
with col2:
    with st.container():
        col1, col2 = st.columns([3, 3])
        with col1:
            view_var = st.selectbox("Select view", ["Simple", "Advanced"], key='view_var')
        with col2:
            site_var = st.selectbox("What site do you want to view?", ('Draftkings', 'Fanduel'), key='site_var')
        

tab1, tab2, tab3 = st.tabs(["Scoring Percentages", "Player ROO", "Optimals"])

roo_data, sd_roo_data, scoring_percentages, dk_roo, fd_roo, dk_id_map, fd_id_map = init_baselines()
hold_display = roo_data

with tab1:
    st.header("Scoring Percentages")
    with st.expander("Info and Filters"):
        with st.container():
            slate_var1 = st.radio("Which data are you loading?", ('Main Slate', 'Secondary Slate', 'Turbo Slate'), key='slate_var1')
            own_var1 = st.radio("How would you like to display team ownership?", ('Sum', 'Average'), key='own_var1')
    
    if site_var == 'Draftkings':
        if slate_var1 == 'Main Slate':
            scoring_percentages = scoring_percentages[scoring_percentages['DK Main Slate'] == 1]
        elif slate_var1 == 'Secondary Slate':
            scoring_percentages = scoring_percentages[scoring_percentages['DK Secondary Slate'] == 1]
        elif slate_var1 == 'Turbo Slate':
            scoring_percentages = scoring_percentages[scoring_percentages['DK Turbo Slate'] == 1]
    elif site_var == 'Fanduel':
        if slate_var1 == 'Main Slate':
            scoring_percentages = scoring_percentages[scoring_percentages['FD Main Slate'] == 1]
        elif slate_var1 == 'Secondary Slate':
            scoring_percentages = scoring_percentages[scoring_percentages['FD Secondary Slate'] == 1]
        elif slate_var1 == 'Turbo Slate':
            scoring_percentages = scoring_percentages[scoring_percentages['FD Turbo Slate'] == 1]

    dk_hitters_only = dk_roo[dk_roo['pos_group'] != 'Pitchers']
    if slate_var1 == 'Main Slate':
        dk_hitters_only = dk_hitters_only[dk_hitters_only['Slate'] == 'main_slate']
    elif slate_var1 == 'Secondary Slate':
        dk_hitters_only = dk_hitters_only[dk_hitters_only['Slate'] == 'secondary_slate']
    elif slate_var1 == 'Turbo Slate':
        dk_hitters_only = dk_hitters_only[dk_hitters_only['Slate'] == 'turbo_slate']
    dk_hitters_only = dk_hitters_only.replace('CWS', 'CHW')
    dk_team_ownership = dk_hitters_only.groupby('Team')['Own%'].sum().reset_index()
    fd_hitters_only = fd_roo[fd_roo['pos_group'] != 'Pitchers']
    if slate_var1 == 'Main Slate':
        fd_hitters_only = fd_hitters_only[fd_hitters_only['Slate'] == 'main_slate']
    elif slate_var1 == 'Secondary Slate':
        fd_hitters_only = fd_hitters_only[fd_hitters_only['Slate'] == 'secondary_slate']
    elif slate_var1 == 'Turbo Slate':
        fd_hitters_only = fd_hitters_only[fd_hitters_only['Slate'] == 'turbo_slate']
    fd_hitters_only = fd_hitters_only.replace('CWS', 'CHW')
    fd_team_ownership = fd_hitters_only.groupby('Team')['Own%'].sum().reset_index()
    scoring_percentages = scoring_percentages.merge(dk_team_ownership, left_on='Names', right_on='Team', how='left')
    scoring_percentages.rename(columns={'Own%': 'DK Own%'}, inplace=True)
    scoring_percentages.drop('Team', axis=1, inplace=True)
    scoring_percentages = scoring_percentages.merge(fd_team_ownership, left_on='Names', right_on='Team', how='left')
    scoring_percentages.rename(columns={'Own%': 'FD Own%'}, inplace=True)
    scoring_percentages.drop('Team', axis=1, inplace=True)
    if site_var == 'Draftkings':
        if slate_var1 == 'Main Slate':
            scoring_percentages['DK LevX'] = scoring_percentages['DK Main Top Score'].rank(pct=True).astype(float) - scoring_percentages['DK Own%'].rank(pct=True).astype(float)
            scoring_percentages = scoring_percentages.rename(columns={'DK Main Top Score': 'Top Score'})
            scoring_percentages = scoring_percentages.drop(['DK Main Slate', 'DK Secondary Slate', 'DK Turbo Slate', 'FD Main Slate', 'FD Secondary Slate', 'FD Turbo Slate', 'FD Main Top Score', 'DK Secondary Top Score', 'FD Secondary Top Score', 'DK Turbo Top Score', 'FD Turbo Top Score'], axis=1)
        elif slate_var1 == 'Secondary Slate':
            scoring_percentages['DK LevX'] = scoring_percentages['DK Secondary Top Score'].rank(pct=True).astype(float) - scoring_percentages['DK Own%'].rank(pct=True).astype(float)
            scoring_percentages = scoring_percentages.rename(columns={'DK Secondary Top Score': 'Top Score'})
            scoring_percentages = scoring_percentages.drop(['DK Main Slate', 'DK Secondary Slate', 'DK Turbo Slate', 'FD Main Slate', 'FD Secondary Slate', 'FD Turbo Slate', 'FD Main Top Score', 'DK Main Top Score', 'FD Secondary Top Score', 'DK Turbo Top Score', 'FD Turbo Top Score'], axis=1)
        elif slate_var1 == 'Turbo Slate':
            scoring_percentages['DK LevX'] = scoring_percentages['DK Turbo Top Score'].rank(pct=True).astype(float) - scoring_percentages['DK Own%'].rank(pct=True).astype(float)
            scoring_percentages = scoring_percentages.rename(columns={'DK Turbo Top Score': 'Top Score'})
            scoring_percentages = scoring_percentages.drop(['DK Main Slate', 'DK Secondary Slate', 'DK Turbo Slate', 'FD Main Slate', 'FD Secondary Slate', 'FD Turbo Slate', 'FD Main Top Score', 'DK Main Top Score', 'FD Secondary Top Score', 'DK Secondary Top Score', 'FD Turbo Top Score'], axis=1)
    elif site_var == 'Fanduel':
        if slate_var1 == 'Main Slate':
            scoring_percentages['FD LevX'] = scoring_percentages['FD Main Top Score'].rank(pct=True).astype(float) - scoring_percentages['FD Own%'].rank(pct=True).astype(float)
            scoring_percentages = scoring_percentages.rename(columns={'FD Main Top Score': 'Top Score'})
            scoring_percentages = scoring_percentages.drop(['DK Main Slate', 'DK Secondary Slate', 'DK Turbo Slate', 'FD Main Slate', 'FD Secondary Slate', 'FD Turbo Slate', 'DK Main Top Score', 'DK Secondary Top Score', 'FD Secondary Top Score', 'DK Turbo Top Score', 'FD Turbo Top Score'], axis=1)
        elif slate_var1 == 'Secondary Slate':
            scoring_percentages['FD LevX'] = scoring_percentages['FD Secondary Top Score'].rank(pct=True).astype(float) - scoring_percentages['FD Own%'].rank(pct=True).astype(float)
            scoring_percentages = scoring_percentages.rename(columns={'FD Secondary Top Score': 'Top Score'})
            scoring_percentages = scoring_percentages.drop(['DK Main Slate', 'DK Secondary Slate', 'DK Turbo Slate', 'FD Main Slate', 'FD Secondary Slate', 'FD Turbo Slate', 'FD Main Top Score', 'DK Main Top Score', 'DK Secondary Top Score', 'DK Turbo Top Score', 'FD Turbo Top Score'], axis=1)
        elif slate_var1 == 'Turbo Slate':
            scoring_percentages['FD LevX'] = scoring_percentages['FD Turbo Top Score'].rank(pct=True).astype(float) - scoring_percentages['FD Own%'].rank(pct=True).astype(float)
            scoring_percentages = scoring_percentages.rename(columns={'FD Turbo Top Score': 'Top Score'})
            scoring_percentages = scoring_percentages.drop(['DK Main Slate', 'DK Secondary Slate', 'DK Turbo Slate', 'FD Main Slate', 'FD Secondary Slate', 'FD Turbo Slate', 'FD Main Top Score', 'DK Main Top Score', 'FD Secondary Top Score', 'DK Secondary Top Score', 'DK Turbo Top Score'], axis=1)
    scoring_percentages = scoring_percentages.sort_values(by='8+ runs', ascending=False)
    if site_var == 'Draftkings':
        scoring_percentages = scoring_percentages.rename(columns={'DK LevX': 'LevX', 'DK Own%': 'Own%', 'Avg Score': 'Runs', 'Win Percentage': 'Win%', '8+ runs': '8+ Runs'})
        scoring_percentages = scoring_percentages.drop(['FD Own%'], axis=1)
    elif site_var == 'Fanduel':
        scoring_percentages = scoring_percentages.rename(columns={'FD LevX': 'LevX', 'FD Own%': 'Own%', 'Avg Score': 'Runs', 'Win Percentage': 'Win%', '8+ runs': '8+ Runs'})
        scoring_percentages = scoring_percentages.drop(['DK Own%'], axis=1)
    
    if view_var == "Simple":
        scoring_percentages = scoring_percentages[['Names', 'Runs', '8+ Runs', 'Win%', 'LevX', 'Own%']]
        scoring_percentages = scoring_percentages.set_index('Names', drop=True)
        st.dataframe(scoring_percentages.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(game_format, precision=2), height=750, use_container_width = True)
    elif view_var == "Advanced":
        scoring_percentages = scoring_percentages.set_index('Names', drop=True)
        st.dataframe(scoring_percentages.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(game_format, precision=2), height=750, use_container_width = True)

with tab2:
    st.header("Player ROO")
    with st.expander("Info and Filters"):
        with st.container():
            slate_type_var2 = st.radio("Which slate type are you loading?", ('Regular', 'Showdown'), key='slate_type_var2')
            slate_var2 = st.radio("Which slate data are you loading?", ('Main', 'Secondary', 'Auxiliary'), key='slate_var2')
            group_var2 = st.radio("Which position group would you like to view?", ('All', 'Pitchers', 'Hitters'), key='group_var2')
            team_var2 = st.selectbox("Which team would you like to view?",  ['All', 'Specific'], key='team_var2')
            if team_var2 == 'Specific':
                team_select2 = st.multiselect("Select your team(s)", roo_data['Team'].unique(), key='team_select2')
            else:
                team_select2 = None
            pos_var2 = st.selectbox("Which position(s) would you like to view?",  ['All', 'Specific'], key='pos_var2')
            if pos_var2 == 'Specific':
                pos_select2 = st.multiselect("Select your position(s)", roo_data['Position'].unique(), key='pos_select2')
            else:
                pos_select2 = None
    if slate_type_var2 == 'Regular':
        if site_var == 'Draftkings':
        
            player_roo_raw = dk_roo.copy()

            if group_var2 == 'All':
                pass
            elif group_var2 == 'Pitchers':
                player_roo_raw = player_roo_raw[player_roo_raw['pos_group'] == 'Pitchers']
            elif group_var2 == 'Hitters':
                player_roo_raw = player_roo_raw[player_roo_raw['pos_group'] == 'Hitters']

        elif site_var == 'Fanduel':
            
            player_roo_raw = fd_roo.copy()

            if group_var2 == 'All':
                pass
            elif group_var2 == 'Pitchers':
                player_roo_raw = player_roo_raw[player_roo_raw['pos_group'] == 'Pitchers']
            elif group_var2 == 'Hitters':
                player_roo_raw = player_roo_raw[player_roo_raw['pos_group'] == 'Hitters']
        
        if slate_var2 == 'Main':
            player_roo_raw = player_roo_raw[player_roo_raw['Slate'] == 'main_slate']
        elif slate_var2 == 'Secondary':
            player_roo_raw = player_roo_raw[player_roo_raw['Slate'] == 'secondary_slate']
        elif slate_var2 == 'Auxiliary':
            player_roo_raw = player_roo_raw[player_roo_raw['Slate'] == 'turbo_slate']
            
    elif slate_type_var2 == 'Showdown':
        player_roo_raw = sd_roo_data.copy()
        if site_var == 'Draftkings':
            player_roo_raw['Site'] = 'Draftkings'
        elif site_var == 'Fanduel':
            player_roo_raw['Site'] = 'Fanduel'
    
    if team_select2:
        player_roo_raw = player_roo_raw[player_roo_raw['Team'].isin(team_select2)]
    if pos_select2:
        position_mask = player_roo_raw['Position'].apply(lambda x: any(pos in x for pos in pos_select2))
        player_roo_raw = player_roo_raw[position_mask]
    
    player_roo_disp = player_roo_raw
    
    if slate_type_var2 == 'Regular':
        player_roo_disp = player_roo_disp.drop(columns=['Site', 'Slate', 'pos_group', 'timestamp', 'player_ID'])
    elif slate_type_var2 == 'Showdown':
        player_roo_disp = player_roo_disp.drop(columns=['site', 'slate', 'version', 'timestamp'])
    
    player_roo_disp = player_roo_disp.drop_duplicates(subset=['Player'])

    if view_var == "Simple":
        try:
            player_roo_disp = player_roo_disp[['Player', 'Position', 'Team', 'Salary', 'Median', 'Ceiling', 'Own%']]
            player_roo_disp = player_roo_disp.set_index('Player', drop=True)
            st.dataframe(player_roo_disp.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(player_roo_format, precision=2), height=750, use_container_width = True)
        except:
            player_roo_disp = player_roo_disp.set_index('Player', drop=True)
            st.dataframe(player_roo_disp.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(player_roo_format, precision=2), height=750, use_container_width = True)
            
    elif view_var == "Advanced":
        try:
            player_roo_disp = player_roo_disp.set_index('Player', drop=True)
            st.dataframe(player_roo_disp.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(player_roo_format, precision=2), height=750, use_container_width = True)
        except:
            player_roo_disp = player_roo_disp.set_index('Player', drop=True)
            st.dataframe(player_roo_disp.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(player_roo_format, precision=2), height=750, use_container_width = True)

with tab3:
    st.header("Optimals")
    with st.expander("Info and Filters"):
        col1, col2, col3 = st.columns(3)
        with col1:
            slate_type_var3 = st.radio("Which slate type are you loading?", ('Regular', 'Showdown'), key='slate_type_var3')
            if slate_type_var3 == 'Regular':
                raw_baselines = roo_data
            elif slate_type_var3 == 'Showdown':
                raw_baselines = sd_roo_data
            slate_var3 = st.radio("Which slate data are you loading?", ('Main', 'Secondary', 'Auxiliary'), key='slate_var3')
            if slate_type_var3 == 'Regular':
                if site_var == 'Draftkings':
                    dk_lineups = init_DK_lineups(slate_type_var3, slate_var3)
                elif site_var == 'Fanduel':
                    fd_lineups = init_FD_lineups(slate_type_var3, slate_var3)
            elif slate_type_var3 == 'Showdown':
                if site_var == 'Draftkings':
                    dk_lineups = init_DK_lineups(slate_type_var3, slate_var3)
                elif site_var == 'Fanduel':
                    fd_lineups = init_FD_lineups(slate_type_var3, slate_var3)
        with col2:
            lineup_num_var = st.number_input("How many lineups do you want to display?", min_value=1, max_value=1000, value=150, step=1)
            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 = raw_baselines['Player'].unique())
            elif player_var1 == 'Full Slate':
                    player_var2 = raw_baselines.Player.values.tolist()
        with col3:
            if site_var == 'Draftkings':
                salary_min_var = st.number_input("Minimum salary used", min_value = 0, max_value = 50000, value = 49000, step = 100, key = 'salary_min_var')
                salary_max_var = st.number_input("Maximum salary used", min_value = 0, max_value = 50000, value = 50000, step = 100, key = 'salary_max_var')
            elif site_var == 'Fanduel':
                salary_min_var = st.number_input("Minimum salary used", min_value = 0, max_value = 35000, value = 34000, step = 100, key = 'salary_min_var')
                salary_max_var = st.number_input("Maximum salary used", min_value = 0, max_value = 35000, value = 35000, step = 100, key = 'salary_max_var')
        
        
        if site_var == 'Draftkings':
            if slate_type_var3 == 'Regular':
                ROO_slice = raw_baselines[raw_baselines['Site'] == 'Draftkings']
                player_salaries = dict(zip(ROO_slice['Player'], ROO_slice['Salary']))
                column_names = dk_columns
            elif slate_type_var3 == 'Showdown':
                player_salaries = dict(zip(raw_baselines['Player'], raw_baselines['Salary']))
                column_names = dk_sd_columns
            # Get the minimum and maximum ownership values from dk_lineups
            min_own = np.min(dk_lineups[:,12])
            max_own = np.max(dk_lineups[:,12])
            
                    
        elif site_var == 'Fanduel':
            raw_baselines = hold_display
            if slate_type_var3 == 'Regular':
                ROO_slice = raw_baselines[raw_baselines['Site'] == 'Fanduel']
                player_salaries = dict(zip(ROO_slice['Player'], ROO_slice['Salary']))
                column_names = fd_columns
            elif slate_type_var3 == 'Showdown':
                player_salaries = dict(zip(raw_baselines['Player'], raw_baselines['Salary']))
                column_names = fd_sd_columns
            # Get the minimum and maximum ownership values from dk_lineups
            min_own = np.min(fd_lineups[:,11])
            max_own = np.max(fd_lineups[:,11])

        if st.button("Prepare full data export", key='data_export'):
            name_export = pd.DataFrame(st.session_state.working_seed.copy(), columns=column_names)
            data_export = pd.DataFrame(st.session_state.working_seed.copy(), columns=column_names)
            if site_var == 'Draftkings':
                if slate_type_var3 == 'Regular':
                    map_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
                elif slate_type_var3 == 'Showdown':
                    map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']
                for col_idx in map_columns:
                    data_export[col_idx] = data_export[col_idx].map(dk_id_map)
            elif site_var == 'Fanduel':
                if slate_type_var3 == 'Regular':
                    map_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
                elif slate_type_var3 == 'Showdown':
                    map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4']
                for col_idx in map_columns:
                    data_export[col_idx] = data_export[col_idx].map(fd_id_map)
            st.download_button(
                label="Export optimals set (IDs)",
                data=convert_df(data_export),
                file_name='MLB_optimals_export.csv',
                mime='text/csv',
            )
            st.download_button(
                label="Export optimals set (Names)",
                data=convert_df(name_export),
                file_name='MLB_optimals_export.csv',
                mime='text/csv',
            )
        
    if site_var == 'Draftkings':
        if 'working_seed' in st.session_state:
            st.session_state.working_seed = st.session_state.working_seed
            if player_var1 == 'Specific Players':
                st.session_state.working_seed = st.session_state.working_seed[np.equal.outer(st.session_state.working_seed, player_var2).any(axis=1).all(axis=1)]
            elif player_var1 == 'Full Slate':
                st.session_state.working_seed = dk_lineups.copy()
            st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:lineup_num_var], 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
            if player_var1 == 'Specific Players':
                st.session_state.working_seed = st.session_state.working_seed[np.equal.outer(st.session_state.working_seed, player_var2).any(axis=1).all(axis=1)]
            elif player_var1 == 'Full Slate':
                st.session_state.working_seed = dk_lineups.copy()
            st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:lineup_num_var], columns=column_names)
        
    elif site_var == 'Fanduel':
        if 'working_seed' in st.session_state:
            st.session_state.working_seed = st.session_state.working_seed
            if player_var1 == 'Specific Players':
                st.session_state.working_seed = st.session_state.working_seed[np.equal.outer(st.session_state.working_seed, player_var2).any(axis=1).all(axis=1)]
            elif player_var1 == 'Full Slate':
                st.session_state.working_seed = fd_lineups.copy()
            st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:lineup_num_var], 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
            if player_var1 == 'Specific Players':
                st.session_state.working_seed = st.session_state.working_seed[np.equal.outer(st.session_state.working_seed, player_var2).any(axis=1).all(axis=1)]
            elif player_var1 == 'Full Slate':
                st.session_state.working_seed = fd_lineups.copy()
            st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:lineup_num_var], columns=column_names)
    st.session_state.data_export_display = st.session_state.data_export_display[st.session_state.data_export_display['salary'] >= salary_min_var]
    st.session_state.data_export_display = st.session_state.data_export_display[st.session_state.data_export_display['salary'] <= salary_max_var]
    export_file = st.session_state.data_export_display.copy()
    name_export = st.session_state.data_export_display.copy()
    if site_var == 'Draftkings':
        if slate_type_var3 == 'Regular':
            map_columns = ['SP1', 'SP2', 'C', '1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3']
        elif slate_type_var3 == 'Showdown':
            map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4', 'FLEX5']
        for col_idx in map_columns:
            export_file[col_idx] = export_file[col_idx].map(dk_id_map)
    elif site_var == 'Fanduel':
        if slate_type_var3 == 'Regular':
            map_columns = ['P', 'C_1B', '2B', '3B', 'SS', 'OF1', 'OF2', 'OF3', 'UTIL']
        elif slate_type_var3 == 'Showdown':
            map_columns = ['CPT', 'FLEX1', 'FLEX2', 'FLEX3', 'FLEX4']
        for col_idx in map_columns:
            export_file[col_idx] = export_file[col_idx].map(fd_id_map)
            
    with st.container():
        if st.button("Reset Optimals", key='reset3'):
            for key in st.session_state.keys():
                del st.session_state[key]
            if site_var == 'Draftkings':
                st.session_state.working_seed = dk_lineups.copy()
            elif site_var == 'Fanduel':
                st.session_state.working_seed = fd_lineups.copy()
        if 'data_export_display' in st.session_state:
            st.dataframe(st.session_state.data_export_display.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(precision=2), height=500, use_container_width = True)
        st.download_button(
            label="Export display optimals (IDs)",
            data=convert_df(export_file),
            file_name='MLB_display_optimals.csv',
            mime='text/csv',
        )
        st.download_button(
            label="Export display optimals (Names)",
            data=convert_df(name_export),
            file_name='MLB_display_optimals.csv',
            mime='text/csv',
        )
    
    with st.container():
        if slate_type_var3 == 'Regular':
            if 'working_seed' in st.session_state:
                # Create a new dataframe with summary statistics
                if site_var == 'Draftkings':
                    summary_df = pd.DataFrame({
                        'Metric': ['Min', 'Average', 'Max', 'STDdev'],
                        'Salary': [
                            np.min(st.session_state.working_seed[:,10]),
                            np.mean(st.session_state.working_seed[:,10]),
                            np.max(st.session_state.working_seed[:,10]),
                            np.std(st.session_state.working_seed[:,10])
                        ],
                        'Proj': [
                            np.min(st.session_state.working_seed[:,11]),
                            np.mean(st.session_state.working_seed[:,11]),
                            np.max(st.session_state.working_seed[:,11]),
                            np.std(st.session_state.working_seed[:,11])
                        ],
                        'Own': [
                            np.min(st.session_state.working_seed[:,16]),
                            np.mean(st.session_state.working_seed[:,16]),
                            np.max(st.session_state.working_seed[:,16]),
                            np.std(st.session_state.working_seed[:,16])
                        ]
                    })
                elif site_var == 'Fanduel':
                    summary_df = pd.DataFrame({
                        'Metric': ['Min', 'Average', 'Max', 'STDdev'],
                        'Salary': [
                            np.min(st.session_state.working_seed[:,9]),
                            np.mean(st.session_state.working_seed[:,9]),
                            np.max(st.session_state.working_seed[:,9]),
                            np.std(st.session_state.working_seed[:,9])
                        ],
                        'Proj': [
                            np.min(st.session_state.working_seed[:,10]),
                            np.mean(st.session_state.working_seed[:,10]),
                            np.max(st.session_state.working_seed[:,10]),
                            np.std(st.session_state.working_seed[:,10])
                        ],
                        'Own': [
                            np.min(st.session_state.working_seed[:,15]),
                            np.mean(st.session_state.working_seed[:,15]),
                            np.max(st.session_state.working_seed[:,15]),
                            np.std(st.session_state.working_seed[:,15])
                        ]
                    })

                # Set the index of the summary dataframe as the "Metric" column
                summary_df = summary_df.set_index('Metric')

                # Display the summary dataframe
                st.subheader("Optimal Statistics")
                st.dataframe(summary_df.style.format({
                    'Salary': '{:.2f}',
                    'Proj': '{:.2f}',
                    'Own': '{:.2f}'
                }).background_gradient(cmap='RdYlGn', axis=0, subset=['Salary', 'Proj', 'Own']), use_container_width=True)

    with st.container():
        tab1, tab2 = st.tabs(["Display Frequency", "Seed Frame Frequency"])
        with tab1:
            if 'data_export_display' in st.session_state:
                if site_var == 'Draftkings':
                    if slate_type_var3 == 'Regular':
                        player_columns = st.session_state.data_export_display.iloc[:, :10]
                    elif slate_type_var3 == 'Showdown':
                        player_columns = st.session_state.data_export_display.iloc[:, :6]
                elif site_var == 'Fanduel':
                    if slate_type_var3 == 'Regular':
                        player_columns = st.session_state.data_export_display.iloc[:, :9]
                    elif slate_type_var3 == 'Showdown':
                        player_columns = st.session_state.data_export_display.iloc[:, :5]
                
                # Flatten the DataFrame and count unique values
                value_counts = player_columns.values.flatten().tolist()
                value_counts = pd.Series(value_counts).value_counts()
                
                percentages = (value_counts / lineup_num_var * 100).round(2)
                
                # Create a DataFrame with the results
                summary_df = pd.DataFrame({
                    'Player': value_counts.index,
                    'Frequency': value_counts.values,
                    'Percentage': percentages.values
                })
                
                # Sort by frequency in descending order
                summary_df['Salary'] = summary_df['Player'].map(player_salaries)
                summary_df = summary_df[['Player', 'Salary', 'Frequency', 'Percentage']]
                summary_df = summary_df.sort_values('Frequency', ascending=False)
                summary_df = summary_df.set_index('Player')
                
                # Display the table
                st.write("Player Frequency Table:")
                st.dataframe(summary_df.style.format({'Percentage': '{:.2f}%'}), height=500, use_container_width=True)
            
                st.download_button(
                    label="Export player frequency",
                    data=convert_df_to_csv(summary_df),
                    file_name='MLB_player_frequency.csv',
                    mime='text/csv',
                )
        with tab2:
            if 'working_seed' in st.session_state:
                if site_var == 'Draftkings':
                    if slate_type_var3 == 'Regular':
                        player_columns = st.session_state.working_seed[:, :10]
                    elif slate_type_var3 == 'Showdown':
                        player_columns = st.session_state.working_seed[:, :7]
                elif site_var == 'Fanduel':
                    if slate_type_var3 == 'Regular':
                        player_columns = st.session_state.working_seed[:, :9]
                    elif slate_type_var3 == 'Showdown':
                        player_columns = st.session_state.working_seed[:, :6]
                
                # Flatten the DataFrame and count unique values
                value_counts = player_columns.flatten().tolist()
                value_counts = pd.Series(value_counts).value_counts()
                
                percentages = (value_counts / len(st.session_state.working_seed) * 100).round(2)
                # Create a DataFrame with the results
                summary_df = pd.DataFrame({
                    'Player': value_counts.index,
                    'Frequency': value_counts.values,
                    'Percentage': percentages.values
                })
                
                # Sort by frequency in descending order
                summary_df['Salary'] = summary_df['Player'].map(player_salaries)
                summary_df = summary_df[['Player', 'Salary', 'Frequency', 'Percentage']]
                summary_df = summary_df.sort_values('Frequency', ascending=False)
                summary_df = summary_df.set_index('Player')
                
                # Display the table
                st.write("Seed Frame Frequency Table:")
                st.dataframe(summary_df.style.format({'Percentage': '{:.2f}%'}), height=500, use_container_width=True)
            
                st.download_button(
                    label="Export seed frame frequency",
                    data=convert_df_to_csv(summary_df),
                    file_name='MLB_seed_frame_frequency.csv',
                    mime='text/csv',
                )