Initial Commit

app.py

@@ -0,0 +1,762 @@
+import streamlit as st
+st.set_page_config(layout="wide")
+import numpy as np
+import pandas as pd
+import pymongo
+
+@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()
+
+percentages_format = {'Exposure': '{:.2%}'}
+freq_format = {'Exposure': '{:.2%}', 'Proj Own': '{:.2%}', 'Edge': '{:.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']
+
+st.markdown("""
+<style>
+    /* Tab styling */
+    .stTabs [data-baseweb="tab-list"] {
+        gap: 8px;
+        padding: 4px;
+    }
+    .stTabs [data-baseweb="tab"] {
+        height: 50px;
+        white-space: pre-wrap;
+        background-color: #FFD700;
+        color: white;
+        border-radius: 10px;
+        gap: 1px;
+        padding: 10px 20px;
+        font-weight: bold;
+        transition: all 0.3s ease;
+    }
+    .stTabs [aria-selected="true"] {
+        background-color: #DAA520;
+        color: white;
+    }
+    .stTabs [data-baseweb="tab"]:hover {
+        background-color: #DAA520;
+        cursor: pointer;
+    }
+</style>""", unsafe_allow_html=True)
+
+@st.cache_data(ttl = 60)
+def init_DK_seed_frames(sharp_split):  
+        
+        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']))
+
+        # Get the valid players from the Range of Outcomes collection
+        collection = db["Player_Range_Of_Outcomes"]
+        cursor = collection.find({"site": "Draftkings", "slate": "Main Slate"})
+        valid_players = set(pd.DataFrame(list(cursor))['Player'].unique())
+    
+        collection = db["DK_MLB_seed_frame"] 
+        cursor = collection.find().limit(sharp_split)
+    
+        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))
+        
+        # Validate lineups against valid players
+        raw_display = validate_lineup_players(raw_display, valid_players, dict_columns)
+        
+        # Remove any remaining NaN values
+        raw_display = raw_display.dropna()
+        DK_seed = raw_display.to_numpy()
+
+        return DK_seed
+
+@st.cache_data(ttl = 60)
+def init_DK_secondary_seed_frames(sharp_split):  
+        
+        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']))
+
+        # Get the valid players from the Range of Outcomes collection
+        collection = db["Player_Range_Of_Outcomes"]
+        cursor = collection.find({"site": "Draftkings", "slate": "Secondary Slate"})
+        valid_players = set(pd.DataFrame(list(cursor))['Player'].unique())
+    
+        collection = db["DK_MLB_secondary_seed_frame"] 
+        cursor = collection.find().limit(sharp_split)
+    
+        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))
+        
+        # Validate lineups against valid players
+        raw_display = validate_lineup_players(raw_display, valid_players, dict_columns)
+        
+        # Remove any remaining NaN values
+        raw_display = raw_display.dropna()
+        DK_seed = raw_display.to_numpy()
+
+        return DK_seed
+
+@st.cache_data(ttl = 60)
+def init_FD_seed_frames(sharp_split):  
+    
+        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']))
+
+        # Get the valid players from the Range of Outcomes collection
+        collection = db["Player_Range_Of_Outcomes"]
+        cursor = collection.find({"site": "Fanduel", "slate": "Main Slate"})
+        valid_players = set(pd.DataFrame(list(cursor))['Player'].unique())
+    
+        collection = db["FD_MLB_seed_frame"] 
+        cursor = collection.find().limit(sharp_split)
+    
+        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))
+        
+        # Validate lineups against valid players
+        raw_display = validate_lineup_players(raw_display, valid_players, dict_columns)
+        
+        # Remove any remaining NaN values
+        raw_display = raw_display.dropna()
+        FD_seed = raw_display.to_numpy()
+
+        return FD_seed
+
+@st.cache_data(ttl = 60)
+def init_FD_secondary_seed_frames(sharp_split):  
+    
+        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']))
+
+        # Get the valid players from the Range of Outcomes collection
+        collection = db["Player_Range_Of_Outcomes"]
+        cursor = collection.find({"site": "Fanduel", "slate": "Secondary Slate"})
+        valid_players = set(pd.DataFrame(list(cursor))['Player'].unique())
+    
+        collection = db["FD_MLB_secondary_seed_frame"] 
+        cursor = collection.find().limit(sharp_split)
+    
+        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))
+        
+        # Validate lineups against valid players
+        raw_display = validate_lineup_players(raw_display, valid_players, dict_columns)
+        
+        # Remove any remaining NaN values
+        raw_display = raw_display.dropna()
+        FD_seed = raw_display.to_numpy()
+
+        return FD_seed
+
+@st.cache_data(ttl = 599)
+def init_baselines():
+    collection = db["Player_Range_Of_Outcomes"] 
+    cursor = collection.find()
+
+    load_display = pd.DataFrame(list(cursor))
+
+    load_display.replace('', np.nan, inplace=True)
+    load_display.rename(columns={"Fantasy": "Median", 'Name': 'Player', 'player_ID': 'player_id'}, inplace = True)
+    load_display = load_display[load_display['Median'] > 0]
+
+    dk_roo_raw = load_display[load_display['site'] == 'Draftkings']
+    dk_roo_raw = dk_roo_raw[dk_roo_raw['slate'] == 'Main Slate']
+    dk_roo_raw['STDev'] = dk_roo_raw['Median'] / 3
+    dk_raw = dk_roo_raw.dropna(subset=['Median'])
+
+    fd_roo_raw = load_display[load_display['site'] == 'Fanduel']
+    fd_roo_raw = fd_roo_raw[fd_roo_raw['slate'] == 'Main Slate']
+    fd_roo_raw['STDev'] = fd_roo_raw['Median'] / 3
+    fd_raw = fd_roo_raw.dropna(subset=['Median'])
+
+    dk_secondary_roo_raw = load_display[load_display['site'] == 'Draftkings']
+    dk_secondary_roo_raw = dk_secondary_roo_raw[dk_secondary_roo_raw['slate'] == 'Secondary Slate']
+    dk_secondary_roo_raw['STDev'] = dk_secondary_roo_raw['Median'] / 3
+    dk_secondary = dk_secondary_roo_raw.dropna(subset=['Median'])
+
+    fd_secondary_roo_raw = load_display[load_display['site'] == 'Fanduel']
+    fd_secondary_roo_raw = fd_secondary_roo_raw[fd_secondary_roo_raw['slate'] == 'Secondary Slate']
+    fd_secondary_roo_raw['STDev'] = fd_secondary_roo_raw['Median'] / 3
+    fd_secondary = fd_secondary_roo_raw.dropna(subset=['Median'])
+
+    teams_playing_count = len(dk_raw.Team.unique())
+
+    return dk_raw, fd_raw, dk_secondary, fd_secondary, teams_playing_count
+
+@st.cache_data
+def validate_lineup_players(df, valid_players, player_columns):
+    """
+    Validates that all players in specified columns exist in valid_players set
+    
+    Args:
+        df: DataFrame containing lineups
+        valid_players: Set of valid player names
+        player_columns: List of columns containing player names
+    
+    Returns:
+        DataFrame with only valid lineups
+    """
+    valid_rows = df[player_columns].apply(lambda x: x.isin(valid_players)).all(axis=1)
+    return df[valid_rows]
+
+@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, Contest_Size, teams_playing_count, site):
+    SimVar = 1
+    Sim_Winners = []
+    fp_array = seed_frame.copy()
+    # 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)]
+
+        if site == 'Draftkings':    
+            # Calculate stack multipliers first
+            stack_multiplier = np.ones(fp_random.shape[0])  # Start with no bonus
+            stack_multiplier += np.minimum(0.10, np.where(fp_random[:, 12] == 4, 0.025 * (teams_playing_count - 8), 0))
+            stack_multiplier += np.minimum(0.15, np.where(fp_random[:, 12] >= 5, 0.025 * (teams_playing_count - 12), 0))
+        elif site == 'Fanduel':
+             # Calculate stack multipliers first
+            stack_multiplier = np.ones(fp_random.shape[0])  # Start with no bonus
+            stack_multiplier += np.minimum(0.10, np.where(fp_random[:, 11] == 4, 0.025 * (teams_playing_count - 8), 0))
+            stack_multiplier += np.minimum(0.15, np.where(fp_random[:, 11] >= 5, 0.025 * (teams_playing_count - 12), 0))
+        
+        # Apply multipliers to both loc and scale in the normal distribution
+        base_projections = np.sum(np.random.normal(
+            loc=vec_projection_map(fp_random[:, :-7]) * stack_multiplier[:, np.newaxis],
+            scale=vec_stdev_map(fp_random[:, :-7]) * stack_multiplier[:, np.newaxis]),
+        axis=1)
+        
+        final_projections = base_projections
+
+        sample_arrays = np.c_[fp_random, final_projections]
+        if site == 'Draftkings':
+            final_array = sample_arrays[sample_arrays[:, 10].argsort()[::-1]]
+        elif site == 'Fanduel':
+            final_array = sample_arrays[sample_arrays[:, 9].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, teams_playing_count = init_baselines()
+dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_id))
+fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_id))
+
+tab1, tab2 = st.tabs(['Contest Sims', 'Data Export'])
+            
+with tab1:
+    with st.expander("Info and Filters"):
+        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_seed = init_DK_seed_frames(10000)
+              FD_seed = init_FD_seed_frames(10000)
+              dk_raw, fd_raw, teams_playing_count = init_baselines()
+              dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_id))
+              fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_id))
+
+        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')
+            
+        contest_var1 = st.selectbox("What contest size are you simulating?", ('Small', 'Medium', 'Large', 'Custom'))
+        if contest_var1 == 'Small':
+            Contest_Size = 1000
+        elif contest_var1 == 'Medium':
+            Contest_Size = 5000
+        elif contest_var1 == 'Large':
+            Contest_Size = 10000
+        elif contest_var1 == 'Custom':
+            Contest_Size = st.number_input("Insert contest size", value=100, placeholder="Type a number under 10,000...")
+        strength_var1 = st.selectbox("How sharp is the field in the contest?", ('Very', 'Above Average', 'Average', 'Below Average', 'Not Very'))
+        if strength_var1 == 'Not Very':
+            sharp_split = 500000
+        elif strength_var1 == 'Below Average':
+            sharp_split = 250000
+        elif strength_var1 == 'Average':
+            sharp_split = 100000
+        elif strength_var1 == 'Above Average':
+            sharp_split = 50000
+        elif strength_var1 == 'Very':
+            sharp_split = 10000
+
+    if st.button("Run Contest Sim"):
+        if 'working_seed' in st.session_state:
+            st.session_state.maps_dict = {
+                    'Projection_map':dict(zip(raw_baselines.Player,raw_baselines.Median)),
+                    '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'])),
+                    'Team_map':dict(zip(raw_baselines.Player,raw_baselines.Team)),
+                    'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev))
+                    }
+            Sim_Winners = sim_contest(1000, st.session_state.working_seed, st.session_state.maps_dict, Contest_Size, teams_playing_count, sim_site_var1)
+            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, 'Own': 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)
+            
+            # Data Copying
+            st.session_state.Sim_Winner_Export = Sim_Winner_Frame.copy()
+            for col in st.session_state.Sim_Winner_Export.iloc[:, 0:9].columns:
+                st.session_state.Sim_Winner_Export[col] = st.session_state.Sim_Winner_Export[col].map(dk_id_dict)
+            st.session_state.Sim_Winner_Export = st.session_state.Sim_Winner_Export.drop_duplicates(subset=['Team', 'Secondary', 'salary', 'unique_id'])
+            
+            # Data Copying
+            st.session_state.Sim_Winner_Display = Sim_Winner_Frame.copy()
+            
+        else:
+            if sim_site_var1 == 'Draftkings':
+                if sim_slate_var1 == 'Main Slate':
+                    st.session_state.working_seed = init_DK_seed_frames(sharp_split)
+                    dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_id))
+                    raw_baselines = dk_raw
+                    column_names = dk_columns
+            elif sim_site_var1 == 'Fanduel':
+                if sim_slate_var1 == 'Main Slate':
+                    st.session_state.working_seed = init_FD_seed_frames(sharp_split)
+                    fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_id))
+                    raw_baselines = fd_raw
+                    column_names = fd_columns
+
+            st.session_state.maps_dict = {
+                    'Projection_map':dict(zip(raw_baselines.Player,raw_baselines.Median)),
+                    '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'])),
+                    'Team_map':dict(zip(raw_baselines.Player,raw_baselines.Team)),
+                    'STDev_map':dict(zip(raw_baselines.Player,raw_baselines.STDev))
+                    }
+            Sim_Winners = sim_contest(1000, st.session_state.working_seed, st.session_state.maps_dict, Contest_Size, teams_playing_count, sim_site_var1)
+            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, 'Own': 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)
+            
+            # Data Copying
+            st.session_state.Sim_Winner_Export = Sim_Winner_Frame.copy()
+            for col in st.session_state.Sim_Winner_Export.iloc[:, 0:9].columns:
+                st.session_state.Sim_Winner_Export[col] = st.session_state.Sim_Winner_Export[col].map(dk_id_dict)
+            st.session_state.Sim_Winner_Export = st.session_state.Sim_Winner_Export.drop_duplicates(subset=['Team', 'Secondary', 'salary', 'unique_id'])
+            
+            # Data Copying
+            st.session_state.Sim_Winner_Display = Sim_Winner_Frame.copy()
+            st.session_state.freq_copy = st.session_state.Sim_Winner_Display
+            
+        if sim_site_var1 == 'Draftkings':
+            freq_working = pd.DataFrame(np.column_stack(np.unique(st.session_state.freq_copy.iloc[:,0:10].values, return_counts=True)),
+                                            columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
+        elif sim_site_var1 == 'Fanduel':
+            freq_working = pd.DataFrame(np.column_stack(np.unique(st.session_state.freq_copy.iloc[:,0:9].values, return_counts=True)),
+                                            columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
+        freq_working['Freq'] = freq_working['Freq'].astype(int)
+        freq_working['Position'] = freq_working['Player'].map(st.session_state.maps_dict['Pos_map'])
+        freq_working['Salary'] = freq_working['Player'].map(st.session_state.maps_dict['Salary_map'])
+        freq_working['Proj Own'] = freq_working['Player'].map(st.session_state.maps_dict['Own_map']) / 100
+        freq_working['Exposure'] = freq_working['Freq']/(1000)
+        freq_working['Edge'] = freq_working['Exposure'] - freq_working['Proj Own']
+        freq_working['Team'] = freq_working['Player'].map(st.session_state.maps_dict['Team_map'])
+        st.session_state.player_freq = freq_working.copy()
+
+        if sim_site_var1 == 'Draftkings':
+            sp_working = pd.DataFrame(np.column_stack(np.unique(st.session_state.freq_copy.iloc[:,0:2].values, return_counts=True)),
+                                            columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
+        elif sim_site_var1 == 'Fanduel':
+            sp_working = pd.DataFrame(np.column_stack(np.unique(st.session_state.freq_copy.iloc[:,0:1].values, return_counts=True)),
+                                            columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
+        sp_working['Freq'] = sp_working['Freq'].astype(int)
+        sp_working['Position'] = sp_working['Player'].map(st.session_state.maps_dict['Pos_map'])
+        sp_working['Salary'] = sp_working['Player'].map(st.session_state.maps_dict['Salary_map'])
+        sp_working['Proj Own'] = sp_working['Player'].map(st.session_state.maps_dict['Own_map']) / 100
+        sp_working['Exposure'] = sp_working['Freq']/(1000)
+        sp_working['Edge'] = sp_working['Exposure'] - sp_working['Proj Own']
+        sp_working['Team'] = sp_working['Player'].map(st.session_state.maps_dict['Team_map'])
+        st.session_state.sp_freq = sp_working.copy()
+
+        if sim_site_var1 == 'Draftkings':
+            team_working = pd.DataFrame(np.column_stack(np.unique(st.session_state.freq_copy.iloc[:,12:13].values, return_counts=True)),
+                                            columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
+        elif sim_site_var1 == 'Fanduel':
+            team_working = pd.DataFrame(np.column_stack(np.unique(st.session_state.freq_copy.iloc[:,11:12].values, return_counts=True)),
+                                            columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
+        team_working['Freq'] = team_working['Freq'].astype(int)
+        team_working['Exposure'] = team_working['Freq']/(1000)
+        st.session_state.team_freq = team_working.copy()
+
+        if sim_site_var1 == 'Draftkings':
+            stack_working = pd.DataFrame(np.column_stack(np.unique(st.session_state.freq_copy.iloc[:,13:14].values, return_counts=True)),
+                                            columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
+        elif sim_site_var1 == 'Fanduel':
+            stack_working = pd.DataFrame(np.column_stack(np.unique(st.session_state.freq_copy.iloc[:,12:13].values, return_counts=True)),
+                                            columns=['Player','Freq']).sort_values('Freq', ascending=False).reset_index(drop=True)
+        stack_working['Freq'] = stack_working['Freq'].astype(int)
+        stack_working['Exposure'] = stack_working['Freq']/(1000)
+        st.session_state.stack_freq = stack_working.copy()
+            
+        with st.container():
+            if st.button("Reset Sim", key='reset_sim'):
+                for key in st.session_state.keys():
+                    del st.session_state[key]
+            if 'player_freq' in st.session_state: 
+                player_split_var2 = st.radio("Are you wanting to isolate any lineups with specific players?", ('Full Players', 'Specific Players'), key='player_split_var2')
+                if player_split_var2 == 'Specific Players':
+                          find_var2 = st.multiselect('Which players must be included in the lineups?', options = st.session_state.player_freq['Player'].unique())
+                elif player_split_var2 == 'Full Players':
+                          find_var2 = st.session_state.player_freq.Player.values.tolist()
+    
+                if player_split_var2 == 'Specific Players':
+                          st.session_state.Sim_Winner_Display = st.session_state.Sim_Winner_Frame[np.equal.outer(st.session_state.Sim_Winner_Frame.to_numpy(), find_var2).any(axis=1).all(axis=1)]
+                if player_split_var2 == 'Full Players':
+                          st.session_state.Sim_Winner_Display = st.session_state.Sim_Winner_Frame
+            if 'Sim_Winner_Display' in st.session_state:
+                st.dataframe(st.session_state.Sim_Winner_Display.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(precision=2), use_container_width = True)
+            if 'Sim_Winner_Export' in st.session_state:
+                st.download_button(
+                     
+                    label="Export Full Frame",
+                    data=st.session_state.Sim_Winner_Export.to_csv().encode('utf-8'),
+                    file_name='MLB_consim_export.csv',
+                    mime='text/csv',
+                )  
+        tab1, tab2 = st.tabs(['Winning Frame Statistics', 'Stack Type Statistics'])
+        
+        with tab1:
+            if 'Sim_Winner_Display' in st.session_state:
+                # Create a new dataframe with summary statistics
+                summary_df = pd.DataFrame({
+                    'Metric': ['Min', 'Average', 'Max', 'STDdev'],
+                    'Salary': [
+                        st.session_state.Sim_Winner_Display['salary'].min(),
+                        st.session_state.Sim_Winner_Display['salary'].mean(),
+                        st.session_state.Sim_Winner_Display['salary'].max(),
+                        st.session_state.Sim_Winner_Display['salary'].std()
+                    ],
+                    'Proj': [
+                        st.session_state.Sim_Winner_Display['proj'].min(),
+                        st.session_state.Sim_Winner_Display['proj'].mean(),
+                        st.session_state.Sim_Winner_Display['proj'].max(),
+                        st.session_state.Sim_Winner_Display['proj'].std()
+                    ],
+                    'Own': [
+                        st.session_state.Sim_Winner_Display['Own'].min(),
+                        st.session_state.Sim_Winner_Display['Own'].mean(),
+                        st.session_state.Sim_Winner_Display['Own'].max(),
+                        st.session_state.Sim_Winner_Display['Own'].std()
+                    ],
+                    'Fantasy': [
+                        st.session_state.Sim_Winner_Display['Fantasy'].min(),
+                        st.session_state.Sim_Winner_Display['Fantasy'].mean(),
+                        st.session_state.Sim_Winner_Display['Fantasy'].max(),
+                        st.session_state.Sim_Winner_Display['Fantasy'].std()
+                    ],
+                    'GPP_Proj': [
+                        st.session_state.Sim_Winner_Display['GPP_Proj'].min(),
+                        st.session_state.Sim_Winner_Display['GPP_Proj'].mean(),
+                        st.session_state.Sim_Winner_Display['GPP_Proj'].max(),
+                        st.session_state.Sim_Winner_Display['GPP_Proj'].std()
+                    ]
+                })
+
+                # Set the index of the summary dataframe as the "Metric" column
+                summary_df = summary_df.set_index('Metric')
+
+                # Display the summary dataframe
+                st.subheader("Winning Frame Statistics")
+                st.dataframe(summary_df.style.format({
+                    'Salary': '{:.2f}',
+                    'Proj': '{:.2f}',
+                    'Own': '{:.2f}',
+                    'Fantasy': '{:.2f}',
+                    'GPP_Proj': '{:.2f}'
+                }).background_gradient(cmap='RdYlGn', axis=0, subset=['Salary', 'Proj', 'Own', 'Fantasy', 'GPP_Proj']), use_container_width=True)
+
+        with tab2:
+            if 'Sim_Winner_Display' in st.session_state:
+                # Apply position mapping to FLEX column
+                stack_counts = st.session_state.freq_copy['Team_count'].value_counts()
+                
+                # Calculate average statistics for each stack size
+                stack_stats = st.session_state.freq_copy.groupby('Team_count').agg({
+                    'proj': 'mean',
+                    'Own': 'mean',
+                    'Fantasy': 'mean',
+                    'GPP_Proj': 'mean'
+                })
+                
+                # Combine counts and average statistics
+                stack_summary = pd.concat([stack_counts, stack_stats], axis=1)
+                stack_summary.columns = ['Count', 'Avg Proj', 'Avg Own', 'Avg Fantasy', 'Avg GPP_Proj']
+                stack_summary = stack_summary.reset_index()
+                stack_summary.columns = ['Stack Size', 'Count', 'Avg Proj', 'Avg Own', 'Avg Fantasy', 'Avg GPP_Proj']
+                stack_summary = stack_summary.sort_values(by='Stack Size', ascending=True)
+                stack_summary = stack_summary.set_index('Stack Size')
+                
+                # Display the summary dataframe
+                st.subheader("Stack Type Statistics")
+                st.dataframe(stack_summary.style.format({
+                    'Count': '{:.0f}',
+                    'Avg Proj': '{:.2f}',
+                    'Avg Own': '{:.2f}',
+                    'Avg Fantasy': '{:.2f}',
+                    'Avg GPP_Proj': '{:.2f}'
+                }).background_gradient(cmap='RdYlGn', axis=0, subset=['Count', 'Avg Proj', 'Avg Own', 'Avg Fantasy', 'Avg GPP_Proj']), use_container_width=True)
+            else:
+                st.write("Simulation data or position mapping not available.")
+                
+            
+        with st.container():
+            tab1, tab2, tab3, tab4 = st.tabs(['Overall Exposures', 'SP Exposures', 'Team Exposures', 'Stack Size Exposures'])
+            with tab1:
+                if 'player_freq' in st.session_state:
+                    
+                    st.dataframe(st.session_state.player_freq.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(freq_format, precision=2), use_container_width = True)
+                    st.download_button(
+                        label="Export Exposures",
+                        data=st.session_state.player_freq.to_csv().encode('utf-8'),
+                        file_name='player_freq_export.csv',
+                        mime='text/csv',
+                        key='overall'
+                    )
+            with tab2:
+                if 'sp_freq' in st.session_state:
+                    
+                    st.dataframe(st.session_state.sp_freq.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(freq_format, precision=2), use_container_width = True)
+                    st.download_button(
+                        label="Export Exposures",
+                        data=st.session_state.sp_freq.to_csv().encode('utf-8'),
+                        file_name='sp_freq.csv',
+                        mime='text/csv',
+                        key='sp'
+                    )
+            with tab3:
+                if 'team_freq' in st.session_state:
+                    
+                    st.dataframe(st.session_state.team_freq.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(percentages_format, precision=2), use_container_width = True)
+                    st.download_button(
+                        label="Export Exposures",
+                        data=st.session_state.team_freq.to_csv().encode('utf-8'),
+                        file_name='team_freq.csv',
+                        mime='text/csv',
+                        key='team'
+                    )
+            with tab4:
+                if 'stack_freq' in st.session_state:
+                    
+                    st.dataframe(st.session_state.stack_freq.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(percentages_format, precision=2), use_container_width = True)
+                    st.download_button(
+                        label="Export Exposures",
+                        data=st.session_state.stack_freq.to_csv().encode('utf-8'),
+                        file_name='stack_freq.csv',
+                        mime='text/csv',
+                        key='stack'
+                    )
+
+with tab2:
+    with st.expander("Info and Filters"):
+        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_seed = init_DK_seed_frames(10000)
+                FD_seed = init_FD_seed_frames(10000)
+                dk_raw, fd_raw, teams_playing_count = init_baselines()
+                dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_id))
+                fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_id))
+                
+        slate_var1 = st.radio("Which data are you loading?", ('Main Slate', 'Secondary Slate'))
+        site_var1 = st.radio("What site are you working with?", ('Draftkings', 'Fanduel'))
+        sharp_split_var = st.number_input("How many lineups do you want?", value=10000, max_value=500000, min_value=10000, step=10000)
+        lineup_num_var = st.number_input("How many lineups do you want to display?", min_value=1, max_value=500, value=10, step=1)
+
+        if site_var1 == 'Draftkings':
+            
+            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]
+            
+            raw_baselines = dk_raw
+            column_names = dk_columns
+                    
+        elif site_var1 == 'Fanduel':
+            
+            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 = [5, 4, 3, 2, 1, 0])
+            elif stack_var1 == 'Full Slate':
+                    stack_var2 = [5, 4, 3, 2, 1, 0]
+            
+            raw_baselines = fd_raw
+            column_names = fd_columns
+        
+
+        if st.button("Prepare data export", key='data_export'):
+                if 'working_seed' in st.session_state:
+                    st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 11], team_var2)]
+                    st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 10], stack_var2)]
+                    st.session_state.data_export_display = st.session_state.working_seed[0:lineup_num_var]
+                elif 'working_seed' not in st.session_state:
+                    if site_var1 == 'Draftkings':
+                        if slate_var1 == 'Main Slate':
+                            st.session_state.working_seed = init_DK_seed_frames(sharp_split_var)
+
+                            dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_id))
+                            raw_baselines = dk_raw
+                            column_names = dk_columns
+                        elif slate_var1 == 'Secondary Slate':
+                            st.session_state.working_seed = init_DK_secondary_seed_frames(sharp_split_var)
+
+                            dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_id))
+                            raw_baselines = dk_raw
+                            column_names = dk_columns
+                
+                    elif site_var1 == 'Fanduel':
+                        if slate_var1 == 'Main Slate':
+                            st.session_state.working_seed = init_FD_seed_frames(sharp_split_var)
+
+                            fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_id))
+                            raw_baselines = fd_raw
+                            column_names = fd_columns
+                        elif slate_var1 == 'Secondary Slate':
+                            st.session_state.working_seed = init_FD_secondary_seed_frames(sharp_split_var)
+
+                            fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_id))
+                            raw_baselines = fd_raw
+                            column_names = fd_columns
+                    st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 11], team_var2)]
+                    st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 10], stack_var2)]
+                    st.session_state.data_export_display = st.session_state.working_seed[0:lineup_num_var]
+                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',
+                )
+                for key in st.session_state.keys():
+                    del st.session_state[key]
+            
+    if st.button("Load Data", key='load_data'):
+        if site_var1 == 'Draftkings':
+            if 'working_seed' in st.session_state:
+                st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 11], team_var2)]
+                st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 10], stack_var2)]
+                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:
+                if slate_var1 == 'Main Slate':
+                    st.session_state.working_seed = init_DK_seed_frames(sharp_split_var)
+                    dk_id_dict = dict(zip(dk_raw.Player, dk_raw.player_id))
+
+                    raw_baselines = dk_raw
+                    column_names = dk_columns
+            
+                st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 11], team_var2)]
+                st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 10], stack_var2)]
+                st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:lineup_num_var], columns=column_names)
+            
+        elif site_var1 == 'Fanduel':
+            if 'working_seed' in st.session_state:
+                st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 11], team_var2)]
+                st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 10], stack_var2)]
+                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:
+                if slate_var1 == 'Main Slate':
+                    st.session_state.working_seed = init_FD_seed_frames(sharp_split_var)
+                    fd_id_dict = dict(zip(fd_raw.Player, fd_raw.player_id))
+                    
+                    raw_baselines = fd_raw
+                    column_names = fd_columns
+                st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 11], team_var2)]
+                st.session_state.working_seed = st.session_state.working_seed[np.isin(st.session_state.working_seed[:, 10], stack_var2)]
+                st.session_state.data_export_display = pd.DataFrame(st.session_state.working_seed[0:lineup_num_var], columns=column_names)
+            
+    with st.container():
+        if 'data_export_display' in st.session_state:
+            st.dataframe(st.session_state.data_export_display.style.format(freq_format, precision=2), use_container_width = True)

app.yaml

@@ -0,0 +1,10 @@
+runtime: python
+env: flex
+
+runtime_config:
+  python_version: 3
+
+entrypoint: streamlit run streamlit-app.py --server.port $PORT
+
+automatic_scaling:
+  max_num_instances: 1000

requirements.txt

@@ -0,0 +1,10 @@
+streamlit
+gspread
+openpyxl
+matplotlib
+pymongo
+pulp
+docker
+plotly
+scipy
+polars