src/sim_func_hold/showdown_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 = 599)
def init_DK_SD_seed_frames(slate, split):
    if slate == 'Main Slate':
        collection = db[f"DK_NFL_SD_seed_frame"] 
    elif slate == 'Secondary Slate':
        collection = db[f"DK_NFL_Secondary_SD_seed_frame"] 
    elif slate == 'Auxiliary Slate':
        collection = db[f"DK_NFL_Auxiliary_SD_seed_frame"] 

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

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

    return DK_seed

@st.cache_data(ttl = 599)
def init_FD_SD_seed_frames(slate, split):
    if slate == 'Main Slate':
        collection = db[f"FD_NFL_SD_seed_frame"] 
    elif slate == 'Secondary Slate':
        collection = db[f"FD_NFL_Secondary_SD_seed_frame"] 
    elif slate == 'Auxiliary Slate':
        collection = db[f"FD_NFL_Auxiliary_SD_seed_frame"] 

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

    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(ttl = 599)
def init_SD_baselines(slate_var):
    collection = db['DK_SD_NFL_ROO'] 
    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[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '2x%', '3x%', '4x%',
                                'Own', 'Small_Field_Own', 'Large_Field_Own', 'Cash_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
    raw_display['Small_Field_Own'] = raw_display['Large_Field_Own']
    raw_display['small_CPT_Own_raw'] = (raw_display['Small_Field_Own'] / 2) * ((100 - (100-raw_display['Small_Field_Own']))/100)
    small_cpt_own_var = 300 / raw_display['small_CPT_Own_raw'].sum()
    raw_display['small_CPT_Own'] = raw_display['small_CPT_Own_raw'] * small_cpt_own_var
    raw_display['cpt_Median'] = raw_display['Median'] * 1.25
    raw_display['STDev'] = raw_display['Median'] / 4
    raw_display['CPT_STDev'] = raw_display['cpt_Median'] / 4
    
    dk_raw = raw_display.dropna(subset=['Median'])
    
    collection = db['FD_SD_NFL_ROO'] 
    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[['Player', 'Position', 'Team', 'Opp', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '2x%', '3x%', '4x%',
                                'Own', 'Small_Field_Own', 'Large_Field_Own', 'Cash_Field_Own', 'CPT_Own', 'LevX', 'version', 'slate', 'timestamp', 'player_id', 'site']]
    raw_display['Small_Field_Own'] = raw_display['Large_Field_Own']
    raw_display['small_CPT_Own_raw'] = (raw_display['Small_Field_Own'] / 2) * ((100 - (100-raw_display['Small_Field_Own']))/100)
    small_cpt_own_var = 300 / raw_display['small_CPT_Own_raw'].sum()
    raw_display['small_CPT_Own'] = raw_display['small_CPT_Own_raw'] * small_cpt_own_var
    raw_display['cpt_Median'] = raw_display['Median'] * 1.25
    raw_display['STDev'] = raw_display['Median'] / 4
    raw_display['CPT_STDev'] = raw_display['cpt_Median'] / 4
    
    fd_raw = raw_display.dropna(subset=['Median'])

    return dk_raw, fd_raw

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

@st.cache_data
def calculate_SD_value_frequencies(np_array):
    unique, counts = np.unique(np_array[:, :6], 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_SD_contest(Sim_size, seed_frame, maps_dict, Contest_Size):
    SimVar = 1
    Sim_Winners = []
    
    # Pre-vectorize functions
    vec_projection_map = np.vectorize(maps_dict['Projection_map'].__getitem__)
    vec_cpt_projection_map = np.vectorize(maps_dict['cpt_projection_map'].__getitem__)
    vec_stdev_map = np.vectorize(maps_dict['STDev_map'].__getitem__)
    vec_cpt_stdev_map = np.vectorize(maps_dict['cpt_STDev_map'].__getitem__)
    
    st.write('Simulating contest on frames')
    
    while SimVar <= Sim_size:
        fp_random = seed_frame[np.random.choice(seed_frame.shape[0], Contest_Size)]
            
        sample_arrays1 = np.c_[
            fp_random,
            np.sum(np.random.normal(
                loc=np.concatenate([
                    vec_cpt_projection_map(fp_random[:, 0:1]),  # Apply cpt_projection_map to first column
                    vec_projection_map(fp_random[:, 1:-7])  # Apply original projection to remaining columns
                ], axis=1),
                scale=np.concatenate([
                    vec_cpt_stdev_map(fp_random[:, 0:1]),  # Apply cpt_projection_map to first column
                    vec_stdev_map(fp_random[:, 1:-7])  # Apply original projection to remaining columns
                ], axis=1)),
            axis=1)
        ]

        sample_arrays = sample_arrays1

        final_array = sample_arrays[sample_arrays[:, 7].argsort()[::-1]]
        best_lineup = final_array[final_array[:, -1].argsort(kind='stable')[::-1][:1]]
        Sim_Winners.append(best_lineup)
        SimVar += 1
        
    return Sim_Winners