src/sim_func_hold/regular_functions.py

import streamlit as st
import pandas as pd
import numpy as np
from pymongo import MongoClient
from database import db

@st.cache_data(ttl = 600)
def init_DK_seed_frames(slate_var, sharp_split):

    
    if slate_var == 'Main Slate':
        collection = db['DK_NBA_name_map']
        cursor = collection.find()
        raw_data = pd.DataFrame(list(cursor))
        names_dict = dict(zip(raw_data['key'], raw_data['value']))
        collection = db[f"DK_NBA_seed_frame_Main Slate"] 
    elif slate_var == 'Secondary Slate':
        collection = db['DK_NBA_Secondary_name_map']
        cursor = collection.find()
        raw_data = pd.DataFrame(list(cursor))
        names_dict = dict(zip(raw_data['key'], raw_data['value']))
        collection = db[f"DK_NBA_seed_frame_Secondary Slate"] 
    elif slate_var == 'Late Slate':
        collection = db['DK_NBA_Late_name_map']
        cursor = collection.find()
        raw_data = pd.DataFrame(list(cursor))
        names_dict = dict(zip(raw_data['key'], raw_data['value']))
        collection = db[f"DK_NBA_seed_frame_Late Slate"] 

    cursor = collection.find().limit(sharp_split)

    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']]
    dict_columns = ['PG', 'SG', 'SF', 'PF', 'C', 'G', 'F', 'FLEX']
    for col in dict_columns:
        raw_display[col] = raw_display[col].map(names_dict)
    DK_seed = raw_display.to_numpy()

    return DK_seed

@st.cache_data(ttl = 599)
def init_FD_seed_frames(slate_var, sharp_split):

    if slate_var == 'Main Slate':
        collection = db['FD_NBA_name_map']
        cursor = collection.find()
        raw_data = pd.DataFrame(list(cursor))
        names_dict = dict(zip(raw_data['key'], raw_data['value']))
        collection = db[f"FD_NBA_seed_frame_Main Slate"] 
        cursor = collection.find().limit(sharp_split)
    elif slate_var == 'Secondary Slate':
        collection = db['FD_NBA_Secondary_name_map']
        cursor = collection.find()
        raw_data = pd.DataFrame(list(cursor))
        names_dict = dict(zip(raw_data['key'], raw_data['value']))
        collection = db[f"FD_NBA_seed_frame_Secondary Slate"] 
        cursor = collection.find().limit(sharp_split)
    elif slate_var == 'Late Slate':
        collection = db['FD_NBA_Late_name_map']
        cursor = collection.find()
        raw_data = pd.DataFrame(list(cursor))
        names_dict = dict(zip(raw_data['key'], raw_data['value']))
        collection = db[f"FD_NBA_seed_frame_Late Slate"] 
        cursor = collection.find().limit(sharp_split)

    raw_display = pd.DataFrame(list(cursor))
    raw_display = raw_display[['PG1', 'PG2', 'SG1', 'SG2', 'SF1', 'SF2', 'PF1', 'PF2', 'C', 'salary', 'proj', 'Team', 'Team_count', 'Secondary', 'Secondary_count', 'Own']]
    dict_columns = ['PG1', 'PG2', 'SG1', 'SG2', 'SF1', 'SF2', 'PF1', 'PF2', 'C']
    for col in dict_columns:
        raw_display[col] = raw_display[col].map(names_dict)
    FD_seed = raw_display.to_numpy()

    return FD_seed

@st.cache_data(ttl = 599)
def init_baselines(slate_var):
    collection = db["Player_Range_Of_Outcomes"] 
    cursor = collection.find()

    raw_display = pd.DataFrame(list(cursor))
    raw_display = raw_display[raw_display['slate'] == slate_var]
    raw_display = raw_display[raw_display['version'] == 'overall']
    raw_display = raw_display.rename(columns={'player_id': 'player_ID'})
    dk_raw = raw_display[raw_display['site'] == 'Draftkings']
    dk_raw = raw_display[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '4x%', '5x%', '6x%', 'GPP%',
                          'Own', 'Small_Own', 'Large_Own', 'Cash_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_ID', 'site']]
    dk_raw['STDev'] = (dk_raw['Ceiling'] - dk_raw['Floor']) / 4

    fd_raw = raw_display[raw_display['site'] == 'Fanduel']
    fd_raw = fd_raw[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '4x%', '5x%', '6x%', 'GPP%',
                          'Own', 'Small_Own', 'Large_Own', 'Cash_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_ID', 'site']]
    fd_raw['STDev'] = (fd_raw['Ceiling'] - fd_raw['Floor']) / 4

    return dk_raw, fd_raw

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

@st.cache_data
def calculate_DK_value_frequencies(np_array):
    unique, counts = np.unique(np_array[:, :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 calculate_FD_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 sim_contest(site_var, Sim_size, seed_frame, maps_dict, Contest_Size):
    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)]
            
        sample_arrays1 = np.c_[
            fp_random, 
            np.sum(np.random.normal(
                loc=vec_projection_map(fp_random[:, :-7]),
                scale=vec_stdev_map(fp_random[:, :-7])),
            axis=1)
        ]

        sample_arrays = sample_arrays1

        if site_var == 'Draftkings':
            final_array = sample_arrays[sample_arrays[:, 9].argsort()[::-1]]
        elif site_var == 'Fanduel':
            final_array = sample_arrays[sample_arrays[:, 10].argsort()[::-1]]
        best_lineup = final_array[final_array[:, -1].argsort(kind='stable')[::-1][:1]]
        Sim_Winners.append(best_lineup)
        SimVar += 1
        
    return Sim_Winners