global_func/predict_dupes.py

import streamlit as st
import numpy as np
import pandas as pd
import time
from fuzzywuzzy import process
import math
from difflib import SequenceMatcher

def calculate_weighted_ownership(row_ownerships):
    """
    Calculate weighted ownership based on the formula:
    (AVERAGE of (each value's average with overall average)) * count - (max - min)
    
    Args:
        row_ownerships: Series containing ownership values in percentage form (e.g., 24.2213 for 24.2213%)
        
    Returns:
        float: Calculated weighted ownership value
    """
    # Drop NaN values and convert percentages to decimals
    row_ownerships = row_ownerships.dropna() / 100
    
    # Get the mean of all ownership values
    row_mean = row_ownerships.mean()
    
    # Calculate average of each value with the overall mean
    value_means = [(val + row_mean) / 2 for val in row_ownerships]
    
    # Take average of all those means
    avg_of_means = sum(value_means) / len(row_ownerships)
    
    # Multiply by count of values
    weighted = avg_of_means * (len(row_ownerships) * 1)
    
    # Subtract (max - min)
    weighted = weighted - (row_ownerships.max() - row_ownerships.min())
    
    # Convert back to percentage form to match input format
    return weighted * 10000

def calculate_player_similarity_score(portfolio, player_columns):
    """
    Calculate a similarity score that measures how different each row is from all other rows
    based on actual player selection. Converts players to numeric IDs for faster comparison.
    Higher scores indicate more unique/different lineups.
    
    Args:
        portfolio: DataFrame containing the portfolio data
        player_columns: List of column names containing player names
        
    Returns:
        Series: Similarity scores for each row
    """
    # Extract player data
    player_data = portfolio[player_columns].fillna('')
    
    # Get all unique players and create a mapping to numeric IDs
    all_players = set()
    for col in player_columns:
        unique_vals = player_data[col].unique()
        for val in unique_vals:
            if isinstance(val, str) and val.strip() != '':
                all_players.add(val)
    
    # Create player ID mapping
    player_to_id = {player: idx for idx, player in enumerate(sorted(all_players))}
    
    # Convert each row to a list of player IDs
    row_ids = []
    for _, row in player_data.iterrows():
        # Get player IDs for this row, sorted for consistency
        player_ids = sorted([player_to_id[str(val)] for val in row.values 
                           if isinstance(val, str) and str(val).strip() != '' and str(val) in player_to_id])
        row_ids.append(player_ids)
    
    # Calculate similarity scores using Jaccard distance on player ID sets
    similarity_scores = []
    
    for i in range(len(portfolio)):
        distances = []
        for j in range(len(portfolio)):
            if i != j:
                # Convert to sets for Jaccard calculation
                set_i = set(row_ids[i])
                set_j = set(row_ids[j])
                
                # Calculate Jaccard distance
                if len(set_i) == 0 and len(set_j) == 0:
                    # Both lineups are empty
                    distance = 0.0
                elif len(set_i) == 0 or len(set_j) == 0:
                    # One lineup is empty, other is not
                    distance = 1.0
                else:
                    # Jaccard distance = 1 - (intersection / union)
                    intersection = len(set_i & set_j)
                    union = len(set_i | set_j)
                    distance = 1 - (intersection / union)
                
                distances.append(distance)
        
        # Average distance to all other lineups
        avg_distance = np.mean(distances) if distances else 0
        similarity_scores.append(avg_distance)
    
    # Normalize to 0-1 scale where 1 = most unique/different
    similarity_scores = np.array(similarity_scores)
    if similarity_scores.max() > similarity_scores.min():
        similarity_scores = (similarity_scores - similarity_scores.min()) / (similarity_scores.max() - similarity_scores.min())
    
    return similarity_scores

def predict_dupes(portfolio, maps_dict, site_var, type_var, Contest_Size, strength_var, sport_var):
    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
    max_ownership = max(maps_dict['own_map'].values()) / 100
    average_ownership = np.mean(list(maps_dict['own_map'].values())) / 100
    if site_var == 'Fanduel':
        if type_var == 'Showdown':
            dup_count_columns = ['CPT_Own_percent_rank', 'FLEX1_Own_percent_rank', 'FLEX2_Own_percent_rank', 'FLEX3_Own_percent_rank', 'FLEX4_Own_percent_rank']
            own_columns = ['CPT_Own', 'FLEX1_Own', 'FLEX2_Own', 'FLEX3_Own', 'FLEX4_Own']
            calc_columns = ['own_product', 'own_average', 'own_sum', 'avg_own_rank', 'dupes_calc', 'low_own_count', 'own_ratio', 'Ref_Proj', 'Max_Proj', 'Min_Proj', 'Avg_Ref', 'own_ratio']
            # Get the original player columns (first 5 columns excluding salary, median, Own)
            player_columns = [col for col in portfolio.columns[:5] if col not in ['salary', 'median', 'Own']]
            
            flex_ownerships = pd.concat([
                portfolio.iloc[:,1].map(maps_dict['own_map']),
                portfolio.iloc[:,2].map(maps_dict['own_map']),
                portfolio.iloc[:,3].map(maps_dict['own_map']),
                portfolio.iloc[:,4].map(maps_dict['own_map'])
            ])
            flex_rank = flex_ownerships.rank(pct=True)
            
            # 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'] = portfolio.iloc[:,1].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
            portfolio['FLEX2_Own_percent_rank'] = portfolio.iloc[:,2].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
            portfolio['FLEX3_Own_percent_rank'] = portfolio.iloc[:,3].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
            portfolio['FLEX4_Own_percent_rank'] = portfolio.iloc[:,4].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])

            portfolio['CPT_Own'] = portfolio.iloc[:,0].map(maps_dict['cpt_own_map']) / 100
            portfolio['FLEX1_Own'] = portfolio.iloc[:,1].map(maps_dict['own_map']) / 100
            portfolio['FLEX2_Own'] = portfolio.iloc[:,2].map(maps_dict['own_map']) / 100
            portfolio['FLEX3_Own'] = portfolio.iloc[:,3].map(maps_dict['own_map']) / 100
            portfolio['FLEX4_Own'] = portfolio.iloc[:,4].map(maps_dict['own_map']) / 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
            portfolio['dupes_calc'] = (portfolio['own_product'] * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (60000 - portfolio['Own'])) / 100) - ((60000 - portfolio['salary']) / 100)
            portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier
            
            # Round and handle negative values
            portfolio['Dupes'] = np.where(
                np.round(portfolio['dupes_calc'], 0) <= 0,
                0, 
                np.round(portfolio['dupes_calc'], 0) - 1
            )
        elif type_var == 'Classic':
            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', 'own_ratio', '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']) / 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'] - (60000 - portfolio['Own'])) / 100) - ((60000 - portfolio['salary']) / 100)
            portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier
            # Round and handle negative values
            portfolio['Dupes'] = np.where(
                np.round(portfolio['dupes_calc'], 0) <= 0,
                0, 
                np.round(portfolio['dupes_calc'], 0) - 1
            )

    elif site_var == 'Draftkings':
        if type_var == 'Showdown':
            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']]
            
            flex_ownerships = pd.concat([
                portfolio.iloc[:,1].map(maps_dict['own_map']),
                portfolio.iloc[:,2].map(maps_dict['own_map']),
                portfolio.iloc[:,3].map(maps_dict['own_map']),
                portfolio.iloc[:,4].map(maps_dict['own_map']),
                portfolio.iloc[:,5].map(maps_dict['own_map'])
            ])
            flex_rank = flex_ownerships.rank(pct=True)
            
            # 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'] = portfolio.iloc[:,1].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
            portfolio['FLEX2_Own_percent_rank'] = portfolio.iloc[:,2].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
            portfolio['FLEX3_Own_percent_rank'] = portfolio.iloc[:,3].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
            portfolio['FLEX4_Own_percent_rank'] = portfolio.iloc[:,4].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
            portfolio['FLEX5_Own_percent_rank'] = portfolio.iloc[:,5].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])

            portfolio['CPT_Own'] = portfolio.iloc[:,0].map(maps_dict['cpt_own_map']) / 100
            portfolio['FLEX1_Own'] = portfolio.iloc[:,1].map(maps_dict['own_map']) / 100
            portfolio['FLEX2_Own'] = portfolio.iloc[:,2].map(maps_dict['own_map']) / 100
            portfolio['FLEX3_Own'] = portfolio.iloc[:,3].map(maps_dict['own_map']) / 100
            portfolio['FLEX4_Own'] = portfolio.iloc[:,4].map(maps_dict['own_map']) / 100
            portfolio['FLEX5_Own'] = portfolio.iloc[:,5].map(maps_dict['own_map']) / 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
            portfolio['dupes_calc'] = (portfolio['own_product'] * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (50000 - portfolio['Own'])) / 100) - ((50000 - portfolio['salary']) / 100)
            portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier

            # Round and handle negative values
            portfolio['Dupes'] = np.where(
                np.round(portfolio['dupes_calc'], 0) <= 0,
                0, 
                np.round(portfolio['dupes_calc'], 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']]
                
                flex_ownerships = pd.concat([
                    portfolio.iloc[:,1].map(maps_dict['own_map']),
                    portfolio.iloc[:,2].map(maps_dict['own_map']),
                    portfolio.iloc[:,3].map(maps_dict['own_map']),
                    portfolio.iloc[:,4].map(maps_dict['own_map']),
                    portfolio.iloc[:,5].map(maps_dict['own_map'])
                ])
                flex_rank = flex_ownerships.rank(pct=True)
                
                # 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'] = portfolio.iloc[:,1].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
                portfolio['FLEX2_Own_percent_rank'] = portfolio.iloc[:,2].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
                portfolio['FLEX3_Own_percent_rank'] = portfolio.iloc[:,3].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
                portfolio['FLEX4_Own_percent_rank'] = portfolio.iloc[:,4].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])
                portfolio['FLEX5_Own_percent_rank'] = portfolio.iloc[:,5].map(maps_dict['own_map']).map(lambda x: flex_rank[flex_ownerships == x].iloc[0])

                portfolio['CPT_Own'] = portfolio.iloc[:,0].map(maps_dict['cpt_own_map']) / 100
                portfolio['FLEX1_Own'] = portfolio.iloc[:,1].map(maps_dict['own_map']) / 100
                portfolio['FLEX2_Own'] = portfolio.iloc[:,2].map(maps_dict['own_map']) / 100
                portfolio['FLEX3_Own'] = portfolio.iloc[:,3].map(maps_dict['own_map']) / 100
                portfolio['FLEX4_Own'] = portfolio.iloc[:,4].map(maps_dict['own_map']) / 100
                portfolio['FLEX5_Own'] = portfolio.iloc[:,5].map(maps_dict['own_map']) / 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
                portfolio['dupes_calc'] = (portfolio['own_product'] * portfolio['avg_own_rank']) * Contest_Size + ((portfolio['salary'] - (50000 - portfolio['Own'])) / 100) - ((50000 - portfolio['salary']) / 100)
                portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier

                # Round and handle negative values
                portfolio['Dupes'] = np.where(
                    np.round(portfolio['dupes_calc'], 0) <= 0,
                    0, 
                    np.round(portfolio['dupes_calc'], 0) - 1
                )
            elif sport_var != 'CS2':
                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']) / 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'] - (50000 - portfolio['Own'])) / 100) - ((50000 - portfolio['salary']) / 100)
                portfolio['dupes_calc'] = portfolio['dupes_calc'] * dupes_multiplier
                # Round and handle negative values
                portfolio['Dupes'] = np.where(
                    np.round(portfolio['dupes_calc'], 0) <= 0,
                    0, 
                    np.round(portfolio['dupes_calc'], 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()  # Get scalar value
    if type_var == 'Classic':
        if sport_var == 'CS2':
            own_ratio_nerf = 2
        elif sport_var != 'CS2':
            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) / ((10 * (row['median'] / percentile_cut_scalar)) / 2) < .0005 
        else (row['own_ratio'] - own_ratio_nerf) / ((10 * (row['median'] / percentile_cut_scalar)) / 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['Win%'] = portfolio['Win%'] * (1 - portfolio['Finish_percentile'])
    
    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, 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['Similarity Score'] = calculate_player_similarity_score(portfolio, player_columns)
    
    portfolio = portfolio.drop(columns=dup_count_columns)
    portfolio = portfolio.drop(columns=own_columns)
    portfolio = portfolio.drop(columns=calc_columns)

    return portfolio