File size: 22,329 Bytes
a35b524 c7e2afa 4390bf0 a35b524 5dc36a5 8c72f5c 5dc36a5 8c72f5c f978f29 5dc36a5 8c72f5c 5dc36a5 606905f 5dc36a5 8c72f5c 606905f 5dc36a5 dd908a8 039bb05 dd908a8 1fe4ec0 dd908a8 1fe4ec0 039bb05 dd908a8 bd90e32 a35b524 c283108 dd908a8 c283108 a35b524 9a6e753 a35b524 c283108 dd908a8 c283108 a35b524 c283108 dd908a8 c283108 a35b524 9a6e753 bd90e32 8b35df7 bd90e32 c283108 dd908a8 c283108 bd90e32 8b35df7 bd90e32 8b35df7 bd90e32 8b35df7 bd90e32 c283108 dd908a8 c283108 bd90e32 a35b524 58073a4 a35b524 5dc36a5 50fa4f0 c283108 dd908a8 c283108 a35b524 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 |
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. Optimized for speed using vectorized operations.
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 binary vector (1 if player is present, 0 if not)
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.iterrows()):
for val in row.values:
if isinstance(val, str) and str(val).strip() != '' and str(val) in player_to_id:
binary_matrix[i, player_to_id[str(val)]] = 1
# Vectorized Jaccard distance calculation
# Use matrix operations to compute all pairwise distances at once
similarity_scores = np.zeros(n_rows)
# Compute intersection and union matrices
# intersection[i,j] = number of players in common between row i and row j
# union[i,j] = total number of unique players between row i and row j
intersection_matrix = np.dot(binary_matrix, binary_matrix.T)
# For union, we need: |A ∪ B| = |A| + |B| - |A ∩ B|
row_sums = np.sum(binary_matrix, axis=1)
union_matrix = row_sums[:, np.newaxis] + row_sums - intersection_matrix
# Calculate Jaccard distance: 1 - (intersection / union)
# Avoid division by zero
with np.errstate(divide='ignore', invalid='ignore'):
jaccard_similarity = np.divide(intersection_matrix, union_matrix,
out=np.zeros_like(intersection_matrix, dtype=float),
where=union_matrix != 0)
# Convert similarity to distance and calculate average distance for each row
jaccard_distance = 1 - jaccard_similarity
# For each row, calculate average distance to all other rows
# Exclude self-comparison (diagonal elements)
np.fill_diagonal(jaccard_distance, 0)
row_counts = n_rows - 1 # Exclude self
similarity_scores = np.sum(jaccard_distance, axis=1) / row_counts
# Normalize to 0-1 scale where 1 = most unique/different
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 |