from numpy import nan as np_nan from numpy import where as np_where from numpy import random as np_random from numpy import zeros as np_zeros from numpy import array as np_array from pandas import concat as pd_concat from pandas import merge as pd_merge from pandas import DataFrame def DK_NBA_ROO_Build(projections_file, floor_var, ceiling_var, std_var, distribution_type): total_sims = 1000 projects_raw = projections_file.copy() projects_raw = projects_raw.replace("", np_nan) dk_df = projects_raw.sort_values(by='Median', ascending=False) basic_own_df = dk_df.copy() basic_own_df['name_team'] = basic_own_df['Player'] + basic_own_df['Position'] def calculate_ownership(df): # Filter the dataframe based on the position frame = df.copy() # Calculate Small Field Own% frame['Base Own%'] = np_where( (frame['Own'] - frame['Own'].mean() >= 0), frame['Own'] * (5 * (frame['Own'] - (frame['Own'].mean() / 1.5)) / 100) + frame['Own'].mean(), frame['Own'] ) frame['Base Own%'] = np_where( frame['Base Own%'] > 85, 85, frame['Base Own%'] ) # Calculate Small Field Own% frame['Small Field Own%'] = np_where( (frame['Own'] - frame['Own'].mean() >= 0), frame['Own'] * (6 * (frame['Own'] - frame['Own'].mean()) / 100) + frame['Own'].mean(), frame['Own'] ) frame['Small Field Own%'] = np_where( frame['Small Field Own%'] > 85, 85, frame['Small Field Own%'] ) # Calculate Large Field Own% frame['Large Field Own%'] = np_where( (frame['Own'] - frame['Own'].mean() >= 0), frame['Own'] * (2.5 * (frame['Own'] - frame['Own'].mean()) / 100) + frame['Own'].mean(), frame['Own'] ) frame['Large Field Own%'] = np_where( frame['Large Field Own%'] > 85, 85, frame['Large Field Own%'] ) # Calculate Cash Own% frame['Cash Own%'] = np_where( (frame['Own'] - frame['Own'].mean() >= 0), frame['Own'] * (8 * (frame['Own'] - frame['Own'].mean()) / 100) + frame['Own'].mean(), frame['Own'] ) frame['Cash Own%'] = np_where( frame['Cash Own%'] > 85, 85, frame['Cash Own%'] ) return frame # Apply the function to each dataframe basic_own_df = calculate_ownership(basic_own_df) own_norm_var_reg = 800 / basic_own_df['Own'].sum() own_norm_var_small = 800 / basic_own_df['Small Field Own%'].sum() own_norm_var_large = 800 / basic_own_df['Large Field Own%'].sum() own_norm_var_cash = 800 / basic_own_df['Cash Own%'].sum() basic_own_df['Own'] = basic_own_df['Own'] * own_norm_var_reg basic_own_df['Small_Own'] = basic_own_df['Small Field Own%'] * own_norm_var_small basic_own_df['Large_Own'] = basic_own_df['Large Field Own%'] * own_norm_var_large basic_own_df['Cash_Own'] = basic_own_df['Cash Own%'] * own_norm_var_cash basic_own_df['Own'] = np_where(basic_own_df['Own'] > 90, 90, basic_own_df['Own']) # Apply the function to each dataframe basic_own_df = calculate_ownership(basic_own_df) own_norm_var_reg = 800 / basic_own_df['Own'].sum() own_norm_var_small = 800 / basic_own_df['Small Field Own%'].sum() own_norm_var_large = 800 / basic_own_df['Large Field Own%'].sum() own_norm_var_cash = 800 / basic_own_df['Cash Own%'].sum() basic_own_df['Own'] = basic_own_df['Own'] * own_norm_var_reg basic_own_df['Small_Own'] = basic_own_df['Small Field Own%'] * own_norm_var_small basic_own_df['Large_Own'] = basic_own_df['Large Field Own%'] * own_norm_var_large basic_own_df['Cash_Own'] = basic_own_df['Cash Own%'] * own_norm_var_cash own_dict = dict(zip(basic_own_df.Player, basic_own_df.Own)) small_own_dict = dict(zip(basic_own_df.Player, basic_own_df['Small Field Own%'])) large_own_dict = dict(zip(basic_own_df.Player, basic_own_df['Large Field Own%'])) cash_own_dict = dict(zip(basic_own_df.Player, basic_own_df['Cash Own%'])) team_dict = dict(zip(basic_own_df.name_team, basic_own_df.Team)) opp_dict = dict(zip(basic_own_df.Player, basic_own_df.Opp)) min_dict = dict(zip(basic_own_df.Player, basic_own_df.Minutes)) flex_file = basic_own_df[['Player', 'Position', 'Salary', 'Median', 'Minutes']] flex_file = flex_file.rename(columns={"Agg": "Median"}) flex_file['Floor'] = (flex_file['Median'] * floor_var) + (flex_file['Minutes'] * .25) flex_file['Ceiling'] = flex_file['Median'] + (5 * ceiling_var) + (flex_file['Minutes'] * .25) flex_file['STD'] = (flex_file['Median'] / std_var) flex_file = flex_file[['Player', 'Position', 'Salary', 'Floor', 'Median', 'Ceiling', 'STD']] flex_file = flex_file.reset_index(drop=True) hold_file = flex_file.copy() overall_file = flex_file.copy() salary_file = flex_file.copy() try: overall_floor_gpu = np_array(overall_file['Floor']) overall_ceiling_gpu = np_array(overall_file['Ceiling']) overall_median_gpu = np_array(overall_file['Median']) overall_std_gpu = np_array(overall_file['STD']) overall_salary_gpu = np_array(overall_file['Salary']) data_shape = (len(overall_file['Player']), total_sims) # Example: 1000 rows salary_array = np_zeros(data_shape) sim_array = np_zeros(data_shape) for x in range(0, total_sims): result_gpu = overall_salary_gpu salary_array[:, x] = result_gpu cupy_array = salary_array salary_file = salary_file.reset_index(drop=True) salary_cupy = DataFrame(cupy_array, columns=list(range(0, total_sims))) salary_check_file = pd_concat([salary_file, salary_cupy], axis=1) except: for x in range(0,total_sims): salary_file[x] = salary_file['Salary'] salary_check_file = salary_file.copy() salary_file=salary_check_file.drop(['Player', 'Position', 'Salary', 'Floor', 'Median', 'Ceiling', 'STD'], axis=1) salary_file = salary_file.div(1000) try: for x in range(0, total_sims): if distribution_type == 'normal': # Normal distribution (existing logic) result_gpu = np_random.normal(overall_median_gpu, overall_std_gpu) elif distribution_type == 'poisson': # Poisson distribution - using median as lambda result_gpu = np_random.poisson(overall_median_gpu) elif distribution_type == 'bimodal': # Bimodal distribution - mixture of two normal distributions # First peak centered at 80% of median, second at 120% of median if np_random.random() < 0.5: result_gpu = np_random.normal(overall_floor_gpu, overall_std_gpu) else: result_gpu = np_random.normal(overall_ceiling_gpu, overall_std_gpu) else: raise ValueError("Invalid distribution type. Must be 'normal', 'poisson', or 'bimodal'") sim_array[:, x] = result_gpu add_array = sim_array overall_file = overall_file.reset_index(drop=True) df2 = DataFrame(add_array, columns=list(range(0, total_sims))) check_file = pd_concat([overall_file, df2], axis=1) except: for x in range(0,total_sims): if distribution_type == 'normal': overall_file[x] = np_random.normal(overall_file['Median'], overall_file['STD']) elif distribution_type == 'poisson': overall_file[x] = np_random.poisson(overall_file['Median']) elif distribution_type == 'bimodal': # Bimodal distribution fallback if np_random.random() < 0.5: overall_file[x] = np_random.normal(overall_file['Median'] * 0.8, overall_file['STD']) else: overall_file[x] = np_random.normal(overall_file['Median'] * 1.2, overall_file['STD']) check_file = overall_file.copy() overall_file=check_file.drop(['Player', 'Position', 'Salary', 'Floor', 'Median', 'Ceiling', 'STD'], axis=1) players_only = hold_file[['Player']] raw_lineups_file = players_only for x in range(0,total_sims): maps_dict = {'proj_map':dict(zip(hold_file.Player,overall_file[x]))} raw_lineups_file[x] = sum([raw_lineups_file['Player'].map(maps_dict['proj_map'])]) players_only[x] = raw_lineups_file[x].rank(ascending=False) players_only=players_only.drop(['Player'], axis=1) salary_4x_check = (overall_file - (salary_file*4)) salary_5x_check = (overall_file - (salary_file*5)) salary_6x_check = (overall_file - (salary_file*6)) gpp_check = (overall_file - ((salary_file*5)+10)) players_only['Average_Rank'] = players_only.mean(axis=1) players_only['Top_finish'] = players_only[players_only == 1].count(axis=1)/total_sims players_only['Top_5_finish'] = players_only[players_only <= 5].count(axis=1)/total_sims players_only['Top_10_finish'] = players_only[players_only <= 10].count(axis=1)/total_sims players_only['20+%'] = overall_file[overall_file >= 20].count(axis=1)/float(total_sims) players_only['4x%'] = salary_4x_check[salary_4x_check >= 1].count(axis=1)/float(total_sims) players_only['5x%'] = salary_5x_check[salary_5x_check >= 1].count(axis=1)/float(total_sims) players_only['6x%'] = salary_6x_check[salary_6x_check >= 1].count(axis=1)/float(total_sims) players_only['GPP%'] = gpp_check[gpp_check >= 1].count(axis=1)/float(total_sims) players_only['Player'] = hold_file[['Player']] final_outcomes = players_only[['Player', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '4x%', '5x%', '6x%', 'GPP%']] final_Proj = pd_merge(hold_file, final_outcomes, on="Player") final_Proj = final_Proj[['Player', 'Position', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '4x%', '5x%', '6x%', 'GPP%']] final_Proj['name_team'] = final_Proj['Player'] + final_Proj['Position'] final_Proj['Own'] = final_Proj['Player'].map(own_dict) final_Proj['Small_Own'] = final_Proj['Player'].map(small_own_dict) final_Proj['Large_Own'] = final_Proj['Player'].map(large_own_dict) final_Proj['Cash_Own'] = final_Proj['Player'].map(cash_own_dict) final_Proj['Minutes Proj'] = final_Proj['Player'].map(min_dict) final_Proj['Team'] = final_Proj['name_team'].map(team_dict) final_Proj['Opp'] = final_Proj['Player'].map(opp_dict) final_Proj = final_Proj[['Player', 'Minutes Proj', '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']] final_Proj = final_Proj.sort_values(by='Median', ascending=False) return final_Proj.copy() def FD_NBA_ROO_Build(projections_file, floor_var, ceiling_var, std_var, distribution_type): total_sims = 1000 projects_raw = projections_file.copy() fd_df = projects_raw.sort_values(by='Median', ascending=False) basic_own_df = fd_df.copy() basic_own_df['name_team'] = basic_own_df['Player'] + basic_own_df['Position'] def calculate_ownership(df): # Filter the dataframe based on the position frame = df.copy() # Calculate Small Field Own% frame['Base Own%'] = np_where( (frame['Own'] - frame['Own'].mean() >= 0), frame['Own'] * (5 * (frame['Own'] - (frame['Own'].mean() / 1.5)) / 100) + frame['Own'].mean(), frame['Own'] ) frame['Base Own%'] = np_where( frame['Base Own%'] > 85, 85, frame['Base Own%'] ) # Calculate Small Field Own% frame['Small Field Own%'] = np_where( (frame['Own'] - frame['Own'].mean() >= 0), frame['Own'] * (6 * (frame['Own'] - frame['Own'].mean()) / 100) + frame['Own'].mean(), frame['Own'] ) frame['Small Field Own%'] = np_where( frame['Small Field Own%'] > 85, 85, frame['Small Field Own%'] ) # Calculate Large Field Own% frame['Large Field Own%'] = np_where( (frame['Own'] - frame['Own'].mean() >= 0), frame['Own'] * (2.5 * (frame['Own'] - frame['Own'].mean()) / 100) + frame['Own'].mean(), frame['Own'] ) frame['Large Field Own%'] = np_where( frame['Large Field Own%'] > 85, 85, frame['Large Field Own%'] ) # Calculate Cash Own% frame['Cash Own%'] = np_where( (frame['Own'] - frame['Own'].mean() >= 0), frame['Own'] * (8 * (frame['Own'] - frame['Own'].mean()) / 100) + frame['Own'].mean(), frame['Own'] ) frame['Cash Own%'] = np_where( frame['Cash Own%'] > 85, 85, frame['Cash Own%'] ) return frame # Apply the function to each dataframe basic_own_df = calculate_ownership(basic_own_df) own_norm_var_reg = 900 / basic_own_df['Own'].sum() own_norm_var_small = 900 / basic_own_df['Small Field Own%'].sum() own_norm_var_large = 900 / basic_own_df['Large Field Own%'].sum() own_norm_var_cash = 900 / basic_own_df['Cash Own%'].sum() basic_own_df['Own'] = basic_own_df['Own'] * own_norm_var_reg basic_own_df['Small_Own'] = basic_own_df['Small Field Own%'] * own_norm_var_small basic_own_df['Large_Own'] = basic_own_df['Large Field Own%'] * own_norm_var_large basic_own_df['Cash_Own'] = basic_own_df['Cash Own%'] * own_norm_var_cash basic_own_df['Own'] = np_where(basic_own_df['Own'] > 90, 90, basic_own_df['Own']) # Apply the function to each dataframe basic_own_df = calculate_ownership(basic_own_df) own_norm_var_reg = 900 / basic_own_df['Own'].sum() own_norm_var_small = 900 / basic_own_df['Small Field Own%'].sum() own_norm_var_large = 900 / basic_own_df['Large Field Own%'].sum() own_norm_var_cash = 900 / basic_own_df['Cash Own%'].sum() basic_own_df['Own'] = basic_own_df['Own'] * own_norm_var_reg basic_own_df['Small_Own'] = basic_own_df['Small Field Own%'] * own_norm_var_small basic_own_df['Large_Own'] = basic_own_df['Large Field Own%'] * own_norm_var_large basic_own_df['Cash_Own'] = basic_own_df['Cash Own%'] * own_norm_var_cash own_dict = dict(zip(basic_own_df.Player, basic_own_df.Own)) small_own_dict = dict(zip(basic_own_df.Player, basic_own_df['Small Field Own%'])) large_own_dict = dict(zip(basic_own_df.Player, basic_own_df['Large Field Own%'])) cash_own_dict = dict(zip(basic_own_df.Player, basic_own_df['Cash Own%'])) team_dict = dict(zip(basic_own_df.name_team, basic_own_df.Team)) opp_dict = dict(zip(basic_own_df.Player, basic_own_df.Opp)) min_dict = dict(zip(basic_own_df.Player, basic_own_df.Minutes)) flex_file = basic_own_df[['Player', 'Position', 'Salary', 'Median', 'Minutes']] flex_file = flex_file.rename(columns={"Agg": "Median"}) flex_file['Floor'] = (flex_file['Median'] * floor_var) + (flex_file['Minutes'] * .25) flex_file['Ceiling'] = flex_file['Median'] + (5 * ceiling_var) + (flex_file['Minutes'] * .25) flex_file['STD'] = (flex_file['Median'] / std_var) flex_file = flex_file[['Player', 'Position', 'Salary', 'Floor', 'Median', 'Ceiling', 'STD']] flex_file = flex_file.reset_index(drop=True) hold_file = flex_file.copy() overall_file = flex_file.copy() salary_file = flex_file.copy() try: overall_floor_gpu = np_array(overall_file['Floor']) overall_ceiling_gpu = np_array(overall_file['Ceiling']) overall_median_gpu = np_array(overall_file['Median']) overall_std_gpu = np_array(overall_file['STD']) overall_salary_gpu = np_array(overall_file['Salary']) data_shape = (len(overall_file['Player']), total_sims) # Example: 1000 rows salary_array = np_zeros(data_shape) sim_array = np_zeros(data_shape) for x in range(0, total_sims): result_gpu = overall_salary_gpu salary_array[:, x] = result_gpu cupy_array = salary_array salary_file = salary_file.reset_index(drop=True) salary_cupy = DataFrame(cupy_array, columns=list(range(0, total_sims))) salary_check_file = pd_concat([salary_file, salary_cupy], axis=1) except: for x in range(0,total_sims): salary_file[x] = salary_file['Salary'] salary_check_file = salary_file.copy() salary_file=salary_check_file.drop(['Player', 'Position', 'Salary', 'Floor', 'Median', 'Ceiling', 'STD'], axis=1) salary_file = salary_file.div(1000) try: for x in range(0, total_sims): if distribution_type == 'normal': # Normal distribution (existing logic) result_gpu = np_random.normal(overall_median_gpu, overall_std_gpu) elif distribution_type == 'poisson': # Poisson distribution - using median as lambda result_gpu = np_random.poisson(overall_median_gpu) elif distribution_type == 'bimodal': # Bimodal distribution - mixture of two normal distributions # First peak centered at 80% of median, second at 120% of median if np_random.random() < 0.5: result_gpu = np_random.normal(overall_floor_gpu, overall_std_gpu) else: result_gpu = np_random.normal(overall_ceiling_gpu, overall_std_gpu) else: raise ValueError("Invalid distribution type. Must be 'normal', 'poisson', or 'bimodal'") sim_array[:, x] = result_gpu add_array = sim_array overall_file = overall_file.reset_index(drop=True) df2 = DataFrame(add_array, columns=list(range(0, total_sims))) check_file = pd_concat([overall_file, df2], axis=1) except: for x in range(0,total_sims): if distribution_type == 'normal': overall_file[x] = np_random.normal(overall_file['Median'], overall_file['STD']) elif distribution_type == 'poisson': overall_file[x] = np_random.poisson(overall_file['Median']) elif distribution_type == 'bimodal': # Bimodal distribution fallback if np_random.random() < 0.5: overall_file[x] = np_random.normal(overall_file['Median'] * 0.8, overall_file['STD']) else: overall_file[x] = np_random.normal(overall_file['Median'] * 1.2, overall_file['STD']) check_file = overall_file.copy() overall_file=check_file.drop(['Player', 'Position', 'Salary', 'Floor', 'Median', 'Ceiling', 'STD'], axis=1) players_only = hold_file[['Player']] raw_lineups_file = players_only for x in range(0,total_sims): maps_dict = {'proj_map':dict(zip(hold_file.Player,overall_file[x]))} raw_lineups_file[x] = sum([raw_lineups_file['Player'].map(maps_dict['proj_map'])]) players_only[x] = raw_lineups_file[x].rank(ascending=False) players_only=players_only.drop(['Player'], axis=1) salary_4x_check = (overall_file - (salary_file*4)) salary_5x_check = (overall_file - (salary_file*5)) salary_6x_check = (overall_file - (salary_file*6)) gpp_check = (overall_file - ((salary_file*5)+10)) players_only['Average_Rank'] = players_only.mean(axis=1) players_only['Top_finish'] = players_only[players_only == 1].count(axis=1)/total_sims players_only['Top_5_finish'] = players_only[players_only <= 5].count(axis=1)/total_sims players_only['Top_10_finish'] = players_only[players_only <= 10].count(axis=1)/total_sims players_only['20+%'] = overall_file[overall_file >= 20].count(axis=1)/float(total_sims) players_only['4x%'] = salary_4x_check[salary_4x_check >= 1].count(axis=1)/float(total_sims) players_only['5x%'] = salary_5x_check[salary_5x_check >= 1].count(axis=1)/float(total_sims) players_only['6x%'] = salary_6x_check[salary_6x_check >= 1].count(axis=1)/float(total_sims) players_only['GPP%'] = gpp_check[gpp_check >= 1].count(axis=1)/float(total_sims) players_only['Player'] = hold_file[['Player']] final_outcomes = players_only[['Player', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '4x%', '5x%', '6x%', 'GPP%']] final_Proj = pd_merge(hold_file, final_outcomes, on="Player") final_Proj = final_Proj[['Player', 'Position', 'Salary', 'Floor', 'Median', 'Ceiling', 'Top_finish', 'Top_5_finish', 'Top_10_finish', '20+%', '4x%', '5x%', '6x%', 'GPP%']] final_Proj['name_team'] = final_Proj['Player'] + final_Proj['Position'] final_Proj['Own'] = final_Proj['Player'].map(own_dict) final_Proj['Small_Own'] = final_Proj['Player'].map(small_own_dict) final_Proj['Large_Own'] = final_Proj['Player'].map(large_own_dict) final_Proj['Cash_Own'] = final_Proj['Player'].map(cash_own_dict) final_Proj['Minutes Proj'] = final_Proj['Player'].map(min_dict) final_Proj['Team'] = final_Proj['name_team'].map(team_dict) final_Proj['Opp'] = final_Proj['Player'].map(opp_dict) final_Proj = final_Proj[['Player', 'Minutes Proj', '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']] final_Proj['Salary'] = final_Proj['Salary'].astype(int) final_Proj = final_Proj.sort_values(by='Median', ascending=False) return final_Proj.copy()