global_func/predict_dupes.py

import streamlit as st
import numpy as np
import pandas as pd
import time
import math
from difflib import SequenceMatcher
import scipy.stats

def calculate_weighted_ownership_vectorized(ownership_array):
    """
    Vectorized version of calculate_weighted_ownership using NumPy operations.
    
    Args:
        ownership_array: 2D array of ownership values (rows x players)
        
    Returns:
        array: Calculated weighted ownership values for each row
    """
    # Convert percentages to decimals and handle NaN values
    ownership_array = np.where(np.isnan(ownership_array), 0, ownership_array) / 100
    
    # Calculate row means
    row_means = np.mean(ownership_array, axis=1, keepdims=True)
    
    # Calculate average of each value with the overall mean
    value_means = (ownership_array + row_means) / 2
    
    # Take average of all those means
    avg_of_means = np.mean(value_means, axis=1)
    
    # Multiply by count of values
    weighted = avg_of_means * ownership_array.shape[1]
    
    # Subtract (max - min) for each row
    row_max = np.max(ownership_array, axis=1)
    row_min = np.min(ownership_array, axis=1)
    weighted = weighted - (row_max - row_min)
    
    # Convert back to percentage form
    return weighted * 10000

def calculate_flex_ranks_efficient(portfolio, start_col, end_col, maps_dict, map_key='own_map'):
    """Memory-efficient replacement for pd.concat + rank operations"""
    n_rows = len(portfolio)
    n_cols = end_col - start_col
    
    # Pre-allocate result arrays
    all_values = np.zeros(n_rows * n_cols, dtype=np.float32)
    
    # Fill values column by column
    for i, col_idx in enumerate(range(start_col, end_col)):
        start_idx = i * n_rows
        end_idx = (i + 1) * n_rows
        all_values[start_idx:end_idx] = portfolio.iloc[:, col_idx].map(maps_dict[map_key]).values
    
    # Calculate percentile ranks efficiently
    ranks = scipy.stats.rankdata(all_values, method='average') / len(all_values)
    
    # Reshape back to individual column ranks
    result_ranks = {}
    for i in range(n_cols):
        start_idx = i * n_rows
        end_idx = (i + 1) * n_rows
        result_ranks[i] = ranks[start_idx:end_idx]
    
    return result_ranks

def calculate_weighted_ownership_wrapper(row_ownerships):
    """
    Wrapper function for the original calculate_weighted_ownership to work with Pandas .apply()
    
    Args:
        row_ownerships: Series containing ownership values in percentage form
        
    Returns:
        float: Calculated weighted ownership value
    """
    # Convert Series to 2D array for vectorized function
    ownership_array = row_ownerships.values.reshape(1, -1)
    return calculate_weighted_ownership_vectorized(ownership_array)[0]

def calculate_player_similarity_score_chunked(portfolio, player_columns, chunk_size=1000):
    """
    Memory-efficient version that processes similarities in chunks
    """
    # Same setup as before
    player_data = portfolio[player_columns].astype(str).fillna('').values
    
    all_players = set()
    for row in player_data:
        for val in row:
            if isinstance(val, str) and val.strip() != '':
                all_players.add(val)
    
    player_to_id = {player: idx for idx, player in enumerate(sorted(all_players))}
    
    n_players = len(all_players)
    n_rows = len(portfolio)
    binary_matrix = np.zeros((n_rows, n_players), dtype=np.int8)
    
    for i, row in enumerate(player_data):
        for val in row:
            if isinstance(val, str) and str(val).strip() != '' and str(val) in player_to_id:
                binary_matrix[i, player_to_id[str(val)]] = 1
    
    # Process similarities in chunks to avoid massive matrices
    similarity_scores = np.zeros(n_rows)
    
    for i in range(0, n_rows, chunk_size):
        end_i = min(i + chunk_size, n_rows)
        chunk_binary = binary_matrix[i:end_i]
        
        # Calculate similarities for this chunk only
        intersection = np.dot(chunk_binary, binary_matrix.T)
        chunk_row_sums = np.sum(chunk_binary, axis=1)
        all_row_sums = np.sum(binary_matrix, axis=1)
        
        union = chunk_row_sums[:, np.newaxis] + all_row_sums - intersection
        
        with np.errstate(divide='ignore', invalid='ignore'):
            jaccard_sim = np.divide(intersection, union, 
                                  out=np.zeros_like(intersection, dtype=float), 
                                  where=union != 0)
        
        jaccard_dist = 1 - jaccard_sim
        
        # Exclude self-comparison and calculate average
        for j in range(len(jaccard_dist)):
            actual_idx = i + j
            jaccard_dist[j, actual_idx] = 0  # Exclude self
            
        similarity_scores[i:end_i] = np.sum(jaccard_dist, axis=1) / (n_rows - 1)
    
    # Normalize
    score_range = similarity_scores.max() - similarity_scores.min()
    if score_range > 0:
        similarity_scores = (similarity_scores - similarity_scores.min()) / score_range
    
    return similarity_scores

# Keep the original function for backward compatibility
def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, strength_var, sport_var, max_salary):
    if strength_var == 'Weak':
        dupes_multiplier = .75
        percentile_multiplier = .90
    elif strength_var == 'Average':
        dupes_multiplier = 1.00
        percentile_multiplier = 1.00
    elif strength_var == 'Sharp':
        dupes_multiplier = 1.25
        percentile_multiplier = 1.10
    
    if sport_var == 'NFL':
        own_baseline = 180
    else:
        own_baseline = 120
    max_ownership = max(maps_dict['own_map'].values()) / 100
    average_ownership = np.mean(list(maps_dict['own_map'].values())) / 100

    if type_var == 'Showdown':
        if sport_var == 'GOLF':
            dup_count_columns = ['FLEX1_Own_percent_rank', 'FLEX2_Own_percent_rank', 'FLEX3_Own_percent_rank', 'FLEX4_Own_percent_rank', 'FLEX5_Own_percent_rank', 'FLEX6_Own_percent_rank']
            own_columns = ['FLEX1_Own', 'FLEX2_Own', 'FLEX3_Own', 'FLEX4_Own', 'FLEX5_Own', 'FLEX6_Own']
        else:
            dup_count_columns = ['CPT_Own_percent_rank', 'FLEX1_Own_percent_rank', 'FLEX2_Own_percent_rank', 'FLEX3_Own_percent_rank', 'FLEX4_Own_percent_rank', 'FLEX5_Own_percent_rank']
            own_columns = ['CPT_Own', 'FLEX1_Own', 'FLEX2_Own', 'FLEX3_Own', 'FLEX4_Own', 'FLEX5_Own']
        calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
        # Get the original player columns (first 6 columns excluding salary, median, Own)
        player_columns = [col for col in portfolio.columns[:6] if col not in ['salary', 'median', 'Own']]
        n_rows = len(portfolio)
        
        # Assign ranks back to individual columns using the same rank scale
        if sport_var == 'GOLF':
            flex_ranks = calculate_flex_ranks_efficient(portfolio, 1, 7, maps_dict)

            portfolio['FLEX1_Own_percent_rank'] = flex_ranks[0]
            portfolio['FLEX2_Own_percent_rank'] = flex_ranks[1]  
            portfolio['FLEX3_Own_percent_rank'] = flex_ranks[2]
            portfolio['FLEX4_Own_percent_rank'] = flex_ranks[3]
            portfolio['FLEX5_Own_percent_rank'] = flex_ranks[4]
            portfolio['FLEX6_Own_percent_rank'] = flex_ranks[5]

            portfolio['FLEX1_Own'] = portfolio.iloc[:,0].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX2_Own'] = portfolio.iloc[:,1].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX3_Own'] = portfolio.iloc[:,2].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX4_Own'] = portfolio.iloc[:,3].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX5_Own'] = portfolio.iloc[:,4].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX6_Own'] = portfolio.iloc[:,5].map(maps_dict['own_map']).astype('float32') / 100
        else:
            flex_ranks = calculate_flex_ranks_efficient(portfolio, 1, 6, maps_dict)
            
            portfolio['CPT_Own_percent_rank'] = portfolio.iloc[:,0].map(maps_dict['cpt_own_map']).rank(pct=True)
            portfolio['FLEX1_Own_percent_rank'] = flex_ranks[0]
            portfolio['FLEX2_Own_percent_rank'] = flex_ranks[1]  
            portfolio['FLEX3_Own_percent_rank'] = flex_ranks[2]
            portfolio['FLEX4_Own_percent_rank'] = flex_ranks[3]
            portfolio['FLEX5_Own_percent_rank'] = flex_ranks[4]

            portfolio['CPT_Own'] = portfolio.iloc[:,0].map(maps_dict['cpt_own_map']).astype('float32') / 100
            portfolio['FLEX1_Own'] = portfolio.iloc[:,1].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX2_Own'] = portfolio.iloc[:,2].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX3_Own'] = portfolio.iloc[:,3].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX4_Own'] = portfolio.iloc[:,4].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX5_Own'] = portfolio.iloc[:,5].map(maps_dict['own_map']).astype('float32') / 100

        portfolio['own_product'] = (portfolio[own_columns].product(axis=1))
        portfolio['own_average'] = (portfolio['Own'].max() * .33) / 100
        portfolio['own_sum'] = portfolio[own_columns].sum(axis=1)
        portfolio['avg_own_rank'] = portfolio[dup_count_columns].mean(axis=1)
        
        # Calculate dupes formula (in progress still)
        portfolio['dupes_calc'] = ((portfolio['own_product'] + ((portfolio['CPT_Own_percent_rank'] - .50) / 1000) + ((portfolio['Own'] / 6) / (max_salary / 2))) * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (max_salary - portfolio['Own'])) / 100) - ((max_salary - portfolio['salary']) / 100)
        portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier * (portfolio['Own'] / (own_baseline + (Contest_Size / 1000)))
        portfolio['dupes_calc'] = ((((portfolio['salary'] / (max_salary * 0.98)) - 1)*(max_salary / 10000)) + 1) * portfolio['dupes_calc']
        portfolio['dupes_calc'] = portfolio['dupes_calc'] * ((portfolio['CPT_Own_percent_rank'] + .50) / (portfolio['Own'] / 110))
        
        # Round and handle negative values
        portfolio['Dupes'] = np.where(
            portfolio['salary'] == max_salary,
            portfolio['dupes_calc'] + (portfolio['dupes_calc'] * .10), 
            portfolio['dupes_calc']
        )
        portfolio['Dupes'] = np.where(
            np.round(portfolio['Dupes'], 0) <= 0,
            0, 
            np.round(portfolio['Dupes'], 0) - 1
        )
    elif type_var == 'Classic':
        if sport_var == 'CS2':
            dup_count_columns = ['CPT_Own_percent_rank', 'FLEX1_Own_percent_rank', 'FLEX2_Own_percent_rank', 'FLEX3_Own_percent_rank', 'FLEX4_Own_percent_rank', 'FLEX5_Own_percent_rank']
            own_columns = ['CPT_Own', 'FLEX1_Own', 'FLEX2_Own', 'FLEX3_Own', 'FLEX4_Own', 'FLEX5_Own']
            calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
            # Get the original player columns (first 6 columns excluding salary, median, Own)
            player_columns = [col for col in portfolio.columns[:6] if col not in ['salary', 'median', 'Own']]

            n_rows = len(portfolio)

            flex_ranks = calculate_flex_ranks_efficient(portfolio, 1, 6, maps_dict)

            # Assign ranks back to individual columns using the same rank scale
            portfolio['CPT_Own_percent_rank'] = portfolio.iloc[:,0].map(maps_dict['cpt_own_map']).rank(pct=True)
            portfolio['FLEX1_Own_percent_rank'] = flex_ranks[0]
            portfolio['FLEX2_Own_percent_rank'] = flex_ranks[1]  
            portfolio['FLEX3_Own_percent_rank'] = flex_ranks[2]
            portfolio['FLEX4_Own_percent_rank'] = flex_ranks[3]
            portfolio['FLEX5_Own_percent_rank'] = flex_ranks[4]

            portfolio['CPT_Own'] = portfolio.iloc[:,0].map(maps_dict['cpt_own_map']).astype('float32') / 100
            portfolio['FLEX1_Own'] = portfolio.iloc[:,1].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX2_Own'] = portfolio.iloc[:,2].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX3_Own'] = portfolio.iloc[:,3].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX4_Own'] = portfolio.iloc[:,4].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['FLEX5_Own'] = portfolio.iloc[:,5].map(maps_dict['own_map']).astype('float32') / 100

            portfolio['own_product'] = (portfolio[own_columns].product(axis=1)) * max(Contest_Size / 10000, 1)
            portfolio['own_average'] = (portfolio['Own'].max() * .33) / 100
            portfolio['own_sum'] = portfolio[own_columns].sum(axis=1)
            portfolio['avg_own_rank'] = portfolio[dup_count_columns].mean(axis=1)
            
            # Calculate dupes formula
            portfolio['dupes_calc'] = ((portfolio['own_product'] * 10) * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (max_salary - portfolio['Own'])) / 50) - ((max_salary - portfolio['salary']) / 50)
            portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier * (portfolio['Own'] / (90 + (Contest_Size / 1000)))

            # Round and handle negative values
            portfolio['Dupes'] = np.where(
                portfolio['salary'] == max_salary,
                portfolio['dupes_calc'] + (portfolio['dupes_calc'] * .10), 
                portfolio['dupes_calc']
            )
            portfolio['Dupes'] = np.where(
                np.round(portfolio['Dupes'], 0) <= 0,
                0, 
                np.round(portfolio['Dupes'], 0) - 1
            )
        if sport_var == 'LOL':
            dup_count_columns = ['CPT_Own_percent_rank', 'TOP_Own_percent_rank', 'JNG_Own_percent_rank', 'MID_Own_percent_rank', 'ADC_Own_percent_rank', 'SUP_Own_percent_rank', 'Team_Own_percent_rank']
            own_columns = ['CPT_Own', 'TOP_Own', 'JNG_Own', 'MID_Own', 'ADC_Own', 'SUP_Own', 'Team_Own']
            calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
            # Get the original player columns (first 6 columns excluding salary, median, Own)
            player_columns = [col for col in portfolio.columns[:7] if col not in ['salary', 'median', 'Own']]
            
            n_rows = len(portfolio)

            flex_ranks = calculate_flex_ranks_efficient(portfolio, 1, 7, maps_dict)
            
            # Assign ranks back to individual columns using the same rank scale
            portfolio['CPT_Own_percent_rank'] = portfolio.iloc[:,0].map(maps_dict['cpt_own_map']).rank(pct=True)
            portfolio['TOP_Own_percent_rank'] = flex_ranks[0]
            portfolio['JNG_Own_percent_rank'] = flex_ranks[1]
            portfolio['MID_Own_percent_rank'] = flex_ranks[2]
            portfolio['ADC_Own_percent_rank'] = flex_ranks[3]
            portfolio['SUP_Own_percent_rank'] = flex_ranks[4]
            portfolio['Team_Own_percent_rank'] = flex_ranks[5]

            portfolio['CPT_Own'] = portfolio.iloc[:,0].map(maps_dict['cpt_own_map']).astype('float32') / 100
            portfolio['TOP_Own'] = portfolio.iloc[:,1].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['JNG_Own'] = portfolio.iloc[:,2].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['MID_Own'] = portfolio.iloc[:,3].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['ADC_Own'] = portfolio.iloc[:,4].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['SUP_Own'] = portfolio.iloc[:,5].map(maps_dict['own_map']).astype('float32') / 100
            portfolio['Team_Own'] = portfolio.iloc[:,6].map(maps_dict['own_map']).astype('float32') / 100

            portfolio['own_product'] = (portfolio[own_columns].product(axis=1)) * max(Contest_Size / 10000, 1)
            portfolio['own_average'] = (portfolio['Own'].max() * .33) / 100
            portfolio['own_sum'] = portfolio[own_columns].sum(axis=1)
            portfolio['avg_own_rank'] = portfolio[dup_count_columns].mean(axis=1)
            
            # Calculate dupes formula
            portfolio['dupes_calc'] = ((portfolio['own_product'] * 10) * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (max_salary - portfolio['Own'])) / 50) - ((max_salary - portfolio['salary']) / 50)
            portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier * (portfolio['Own'] / (90 + (Contest_Size / 1000)))

            # Round and handle negative values
            portfolio['Dupes'] = np.where(
                portfolio['salary'] == max_salary,
                portfolio['dupes_calc'] + (portfolio['dupes_calc'] * .10), 
                portfolio['dupes_calc']
            )
            portfolio['Dupes'] = np.where(
                np.round(portfolio['Dupes'], 0) <= 0,
                0, 
                np.round(portfolio['Dupes'], 0) - 1
            )
        elif sport_var == 'GOLF':
            num_players = len([col for col in portfolio.columns if col not in ['salary', 'median', 'Own']])
            dup_count_columns = [f'player_{i}_percent_rank' for i in range(1, num_players + 1)]
            own_columns = [f'player_{i}_own' for i in range(1, num_players + 1)]
            calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
            # Get the original player columns (first num_players columns excluding salary, median, Own)
            player_columns = [col for col in portfolio.columns[:num_players] if col not in ['salary', 'median', 'Own']]
            
            for i in range(1, num_players + 1):
                portfolio[f'player_{i}_percent_rank'] = portfolio.iloc[:,i-1].map(maps_dict['own_percent_rank'])
                portfolio[f'player_{i}_own'] = portfolio.iloc[:,i-1].map(maps_dict['own_map']).astype('float32') / 100
            
            portfolio['own_product'] = (portfolio[own_columns].product(axis=1)) * max(Contest_Size / 10000, 1)
            portfolio['own_average'] = (portfolio['Own'].max() * .33) / 100
            portfolio['own_sum'] = portfolio[own_columns].sum(axis=1)
            portfolio['avg_own_rank'] = portfolio[dup_count_columns].mean(axis=1)
            
            portfolio['dupes_calc'] = (portfolio['own_product'] * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (max_salary - portfolio['Own'])) / 100) - ((max_salary - portfolio['salary']) / 100)
            portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier * (portfolio['Own'] / (90 + (Contest_Size / 1000)))
            # Round and handle negative values
            portfolio['Dupes'] = np.where(
                portfolio['salary'] == max_salary,
                portfolio['dupes_calc'] + (portfolio['dupes_calc'] * .10), 
                portfolio['dupes_calc']
            )
            portfolio['Dupes'] = np.where(
                np.round(portfolio['Dupes'], 0) <= 0,
                0, 
                np.round(portfolio['Dupes'], 0) - 1
            )
        else:
            num_players = len([col for col in portfolio.columns if col not in ['salary', 'median', 'Own']])
            dup_count_columns = [f'player_{i}_percent_rank' for i in range(1, num_players + 1)]
            own_columns = [f'player_{i}_own' for i in range(1, num_players + 1)]
            calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
            # Get the original player columns (first num_players columns excluding salary, median, Own)
            player_columns = [col for col in portfolio.columns[:num_players] if col not in ['salary', 'median', 'Own']]
            
            for i in range(1, num_players + 1):
                portfolio[f'player_{i}_percent_rank'] = portfolio.iloc[:,i-1].map(maps_dict['own_percent_rank'])
                portfolio[f'player_{i}_own'] = portfolio.iloc[:,i-1].map(maps_dict['own_map']).astype('float32') / 100
            
            portfolio['own_product'] = (portfolio[own_columns].product(axis=1))
            portfolio['own_average'] = (portfolio['Own'].max() * .33) / 100
            portfolio['own_sum'] = portfolio[own_columns].sum(axis=1)
            portfolio['avg_own_rank'] = portfolio[dup_count_columns].mean(axis=1)
            
            portfolio['dupes_calc'] = (portfolio['own_product'] * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (max_salary - portfolio['Own'])) / 100) - ((max_salary - portfolio['salary']) / 100)
            portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier * (portfolio['Own'] / (90 + (Contest_Size / 1000)))
            # Round and handle negative values
            portfolio['Dupes'] = np.where(
                portfolio['salary'] == max_salary,
                portfolio['dupes_calc'] + (portfolio['dupes_calc'] * .10), 
                portfolio['dupes_calc']
            )
            portfolio['Dupes'] = np.where(
                np.round(portfolio['Dupes'], 0) <= 0,
                0, 
                np.round(portfolio['Dupes'], 0) - 1
            )
                

    portfolio['Dupes'] = np.round(portfolio['Dupes'], 0)
    portfolio['own_ratio'] = np.where(
        portfolio[own_columns].isin([max_ownership]).any(axis=1),
        portfolio['own_sum'] / portfolio['own_average'],
        (portfolio['own_sum'] - max_ownership) / portfolio['own_average']
    )
    percentile_cut_scalar = portfolio['median'].max()
    if type_var == 'Classic':
        if sport_var == 'CS2':
            own_ratio_nerf = 2
        elif sport_var == 'LOL':
            own_ratio_nerf = 2
        else:
            own_ratio_nerf = 1.5
    elif type_var == 'Showdown':
        own_ratio_nerf = 1.5
    portfolio['Finish_percentile'] = portfolio.apply(
        lambda row: .0005 if (row['own_ratio'] - own_ratio_nerf) / ((5 * (row['median'] / percentile_cut_scalar)) / 3) < .0005 
        else ((row['own_ratio'] - own_ratio_nerf) / ((5 * (row['median'] / percentile_cut_scalar)) / 3)) / 2, 
        axis=1
    )
    
    portfolio['Ref_Proj'] = portfolio['median'].max()
    portfolio['Max_Proj'] = portfolio['Ref_Proj'] + 10
    portfolio['Min_Proj'] = portfolio['Ref_Proj'] - 10
    portfolio['Avg_Ref'] = (portfolio['Max_Proj'] + portfolio['Min_Proj']) / 2
    portfolio['Win%'] = (((portfolio['median'] / portfolio['Avg_Ref']) - (0.1 + ((portfolio['Ref_Proj'] - portfolio['median'])/100))) / (Contest_Size / 1000)) / 10
    max_allowed_win = (1 / Contest_Size) * 5
    portfolio['Win%'] = portfolio['Win%'] / portfolio['Win%'].max() * max_allowed_win
    
    portfolio['Finish_percentile'] = portfolio['Finish_percentile'] + .005 + (.005 * (Contest_Size / 10000))
    portfolio['Finish_percentile'] = portfolio['Finish_percentile'] * percentile_multiplier * (portfolio['Own'] / (100 + (Contest_Size / 1000)))
    portfolio['Win%'] = portfolio['Win%'] * (1 - portfolio['Finish_percentile'])
    portfolio['Win%'] = portfolio['Win%'].clip(lower=0, upper=max_allowed_win)
    
    portfolio['low_own_count'] = portfolio[own_columns].apply(lambda row: (row < 0.10).sum(), axis=1)
    portfolio['Finish_percentile'] = portfolio.apply(lambda row: row['Finish_percentile'] if row['low_own_count'] <= 0 else row['Finish_percentile'] / row['low_own_count'], axis=1)
    portfolio['Lineup Edge'] = portfolio['Win%'] * ((.5 - portfolio['Finish_percentile']) * (Contest_Size / 2.5))
    portfolio['Lineup Edge'] = portfolio.apply(lambda row: row['Lineup Edge'] / (row['Dupes'] + 1) if row['Dupes'] > 0 else row['Lineup Edge'], axis=1)
    portfolio['Lineup Edge'] = portfolio['Lineup Edge'] - portfolio['Lineup Edge'].mean()
    portfolio['Weighted Own'] = portfolio[own_columns].apply(calculate_weighted_ownership_wrapper, axis=1)
    portfolio['Geomean'] = np.power((portfolio[own_columns] * 100).product(axis=1), 1 / len(own_columns))
    
    # Calculate similarity score based on actual player selection
    portfolio['Diversity'] = calculate_player_similarity_score_chunked(portfolio, player_columns)
    # check_portfolio = portfolio.copy()
    portfolio = portfolio.drop(columns=dup_count_columns)
    portfolio = portfolio.drop(columns=own_columns)
    portfolio = portfolio.drop(columns=calc_columns)
    
    int16_columns_stacks = ['Dupes', 'Size', 'salary']
    int16_columns_nstacks = ['Dupes', 'salary']
    float32_columns = ['median', 'Own', 'Finish_percentile', 'Win%', 'Lineup Edge', 'Weighted Own', 'Geomean', 'Diversity']

    try:
        portfolio[int16_columns_stacks] = portfolio[int16_columns_stacks].astype('uint16')
    except:
        pass
    try:
        portfolio[int16_columns_nstacks] = portfolio[int16_columns_nstacks].astype('uint16')
    except:
        pass
    if sport_var != 'LOL':
        try:
            portfolio[float32_columns] = portfolio[float32_columns].astype('float32')
        except:
            pass
    return portfolio