Rewrite this R code to Julia: library(parallel) library(foreach) library(doParallel)…
- User
Rewrite this R code to Julia: library(parallel) library(foreach) library(doParallel) #"C:\Users\Michał\Desktop\player22.csv" Data<-read.csv("C:/Users/Użytkownik/Desktop/player22.csv")
RW_idx <- which(grepl("RW", DataPositions)) GK_idx <- which(grepl("GK", DataPositions)) LW_idx <- which(grepl("LW", DataPositions)) LM_idx <- which(grepl("LM", DataPositions)) CB_idx <- which(grepl("CB", DataPositions)) LB_idx <- which(grepl("LB", DataPositions)) RM_idx <- which(grepl("RM", DataPositions)) RWB_idx <- which(grepl("RWB", Data$Positions))
c<-2 ############# a<-6/0
position_vectors <- list(RW_idx, ST_idx, GK_idx, CM_idx, LW_idx, CDM_idx, LM_idx, CF_idx, CB_idx, CAM_idx, LB_idx, RB_idx, RM_idx, LWB_idx, RWB_idx)
position_vectors_list<-position_vectors
##############
Mutation 2
mutate <- function(selected_players_df, position_vectors_list, probability) { n_rows <- nrow(selected_players_df) selected_players_matrix <- selected_players_df
select_random_player <- function(idx_list, selected_players = NULL) { repeat { random_idx <- sample(idx_list, 1) if (!random_idx %in% selected_players) { return(random_idx) } } }
for (i in 1:n_rows) { for (pos_idx in 1:length(position_vectors_list)) { if (runif(1) <= probability) { selected_players_matrix[i, pos_idx] <- select_random_player(position_vectors_list[[pos_idx]], selected_players = selected_players_matrix[i, ]) } } }
selected_players_df <- data.frame(selected_players_matrix) return(selected_players_df) }
n_rows<-100
pop_init<- as.data.frame(matrix(NA, n_rows, length(position_vectors))) pop_init<- mutate(pop_init, position_vectors_list, probability=1)
#######Target
row1<-pop_init[1,]
target <- function(row1,penalty=5) { position_ratings <- c("RWRating", "STRating", "GKRating", "CMRating", "LWRating", "CDMRating", "LMRating", "CFRating", "CBRating", "CAMRating", "LBRating", "RBRating", "RMRating", "LWBRating", "RWBRating")
row1<-as.matrix(row1,nrow=1) parent_data <- Data[row1, ] ratings <- parent_data[position_ratings] ratings_log <- log(ratings)
potential_minus_age <- 0.15*parent_dataAge int_reputation <- parent_data$IntReputation
sumratings<-0 rating_list<-c() for (i in 1:15){ temp<-ratings_log[i,i] sumratings<-sumratings+temp rating_list<-append(rating_list, temp)
}
Apply constraints
constraint_penalty <- 0 if (sum(parent_dataValueEUR) > 250000000) { constraint_penalty <- constraint_penalty + log((sum(parent_dataValueEUR)-250000000)^penalty) } if (sum(parent_dataWageEUR) > 250000) { constraint_penalty <- constraint_penalty + log((sum(parent_dataWageEUR)-250000)^penalty) } if (any(rating_list < 1.2)) { constraint_penalty <- constraint_penalty + 1.2^penalty }
potential_minus_age
target_value <- -(sumratings+0.3*sum(potential_minus_age) +sum(int_reputation))+constraint_penalty
return(target_value) }
#target(global_best)
parents<-pop_init t_size=2 penalty=1
tournament_selection <- function(parents, t_size,penalty=6) { random_parents_idx <- sample(nrow(parents), t_size, replace = FALSE) random_parents <- parents[random_parents_idx, ]
random_parents_fitness <- apply(random_parents, 1, function(x) target(x, penalty=penalty))
best_parent_idx <- which.min(random_parents_fitness) return(random_parents[best_parent_idx, ]) }
tournament_selection (pop_init,t_size=2)
#best parent 1 #tournement_selection *50
corssover_point<-6
parent1<-row1 parent2<-pop_init[2,]
crossover <- function(parent1, parent2,corssover_point) {
offspring1 <- c(parent1[1:crossover_point], parent2[(crossover_point + 1):ncol(parent1)]) offspring2 <- c(parent2[1:crossover_point], parent1[(crossover_point + 1):ncol(parent2)])
return(rbind(offspring1, offspring2))
}
- Assistant
using CSV, DataFrames using Random using Statistics Data = CSV.read("player22.csv", DataFrame) RW_idx = findall(occursin.("RW", Data.Positions)) ST_idx = findall(occursin.("ST", Data.Positions)) GK_idx = findall(occursin.("GK", Data.Positions)) CM_idx = findall(occursin.("CM", Data.Positions)) LW_idx = findall(occursin.("LW", Data.Positions)) CDM_idx = findall(occursin.("CDM", Data.Positions)) LM_idx = findall(occursin.("LM", Data.Positions)) CF_idx = findall(occursin.("CF", Data.Positions)) CB_idx = findall(occursin.("CB", Data.Positions)) CAM_idx = findall(occursin.("CAM", Data.Positions)) LB_idx = findall(occursin.("LB", Data.Positions)) RB_idx = findall(occursin.("RB", Data.Positions)) RM_idx = findall(occursin.("RM", Data.Positions)) LWB_idx = findall(occursin.("LWB", Data.Positions)) RWB_idx = findall(occursin.("RWB", Data.Positions)) c = 2 a = 6 / 0 position_vectors = [RW_idx, ST_idx, GK_idx, CM_idx, LW_idx, CDM_idx, LM_idx, CF_idx, CB_idx, CAM_idx, LB_idx, RB_idx, RM_idx, LWB_idx, RWB_idx] position_vectors_list = position_vectors function mutate(selected_players_df, position_vectors_list, probability) n_rows, _ = size(selected_players_df) selected_players_matrix = selected_players_df function select_random_player(idx_list, selected_players = Set{Integer}()) while true random_idx = rand(idx_list) if !(random_idx in selected_players) return random_idx end end end for i in 1:n_rows for pos_idx in 1:length(position_vectors_list) if rand() <= probability selected_players_matrix[i, pos_idx] = select_random_player(position_vectors_list[pos_idx], selected_players = selected_players_matrix[i, :]) end end end selected_players_df = DataFrame(selected_players_matrix) return selected_players_df end n_rows = 100 pop_init = DataFrame(fill(NA, n_rows, length(position_vectors))) pop_init = mutate(pop_init, position_vectors_list, probability=1) row1 = pop_init[1, :] function target(row, penalty=5) position_ratings = ["RWRating", "STRating", "GKRating", "CMRating", "LWRating", "CDMRating", "LMRating", "CFRating", "CBRating", "CAMRating", "LBRating", "RBRating", "RMRating", "LWBRating", "RWBRating"] row = Matrix(row') parent_data = Data[row[1, :], :] ratings = Vector(parent_data[:, position_ratings]) ratings_log = log.(ratings) potential_minus_age = 0.15 .* parent_data.Potential - 0.6 .* parent_data.Age int_reputation = parent_data.IntReputation rating_sum = sum(ratings_log) rating_list = sum(ratings_log, dims=1) constraint_penalty = 0 if sum(parent_data.ValueEUR) > 250000000 constraint_penalty += log((sum(parent_data.ValueEUR) - 250000000)^penalty) end if any(rating_list .< 1.2) constraint_penalty += 1.2^penalty end target_value = -(rating_sum + 0.3*sum(potential_minus_age) + sum(int_reputation)) + constraint_penalty return target_value end function tournament_selection(parents, t_size, penalty=6) random_parents_idx = rand(1:nrow(parents), t_size) random_parents = parents[random_parents_idx, :] random_parents_fitness = [target(x, penalty=penalty) for x in eachrow(random_parents)] best_parent_idx = argmin(random_parents_fitness) return random_parents[best_parent_idx, :] end crossover_point = 6 parent1 = row1 parent2 = pop_init[2, :] function crossover(parent1, parent2, corssover_point) offspring1 = [parent1[1:crossover_point]; parent2[(crossover_point + 1):size(parent1, 1)]] offspring2 = [parent2[1:crossover_point]; parent1[(crossover_point + 1):size(parent2, 1)]] return (offspring1, offspring2) end - User
using CSV, DataFrames using Random using Statistics
Data = CSV.read("C:/Users/Użytkownik/Desktop/player22.csv", DataFrame)
RW_idx = findall(occursin.("RW", Data.Positions)) ST_idx = findall(occursin.("ST", Data.Positions)) GK_idx = findall(occursin.("GK", Data.Positions)) CM_idx = findall(occursin.("CM", Data.Positions)) LW_idx = findall(occursin.("LW", Data.Positions)) CDM_idx = findall(occursin.("CDM", Data.Positions)) LM_idx = findall(occursin.("LM", Data.Positions)) CF_idx = findall(occursin.("CF", Data.Positions)) CB_idx = findall(occursin.("CB", Data.Positions)) CAM_idx = findall(occursin.("CAM", Data.Positions)) LB_idx = findall(occursin.("LB", Data.Positions)) RB_idx = findall(occursin.("RB", Data.Positions)) RM_idx = findall(occursin.("RM", Data.Positions)) LWB_idx = findall(occursin.("LWB", Data.Positions)) RWB_idx = findall(occursin.("RWB", Data.Positions))
position_vectors = [RW_idx, ST_idx, GK_idx, CM_idx, LW_idx, CDM_idx, LM_idx, CF_idx, CB_idx, CAM_idx, LB_idx, RB_idx, RM_idx, LWB_idx, RWB_idx] position_vectors_list = position_vectors
function mutate(selected_players_df, position_vectors_list, probability) n_rows, _ = size(selected_players_df) selected_players_matrix = copy(selected_players_df)
function select_random_player(idx_list, selected_players) while true random_idx = rand(idx_list) if !(ismissing(selected_players[random_idx])) return random_idx end end end for i in 1:n_rows for pos_idx in 1:length(position_vectors_list) if rand() <= probability selected_players_matrix[i, pos_idx] = select_random_player(position_vectors_list[pos_idx], selected_players_matrix[i, :]) end end end selected_players_df = DataFrame(selected_players_matrix) return selected_players_dfend
n_rows = 100 pop_init = DataFrame([Vector{Union{Missing, Float64}}(missing, n_rows) for _ in 1:length(position_vectors)], unique(Data[!, "BestPosition"])) pop_init = mutate(pop_init, position_vectors_list, 1) row1 = pop_init[1, :]
function target(row, penalty=5) position_ratings = ["RWRating", "STRating", "GKRating", "CMRating", "LWRating", "CDMRating", "LMRating", "CFRating", "CBRating", "CAMRating", "LBRating", "RBRating", "RMRating", "LWBRating", "RWBRating"]
row = Matrix(row') parent_data = Data[row[1, :], :] ratings = Vector(parent_data[:, position_ratings]) ratings_log = log.(ratings) potential_minus_age = 0.15 .* parent_data.Potential - 0.6 .* parent_data.Age int_reputation = parent_data.IntReputation rating_sum = sum(ratings_log) rating_list = sum(ratings_log, dims=1) constraint_penalty = 0 if sum(parent_data.ValueEUR) > 250000000 constraint_penalty += log((sum(parent_data.ValueEUR) - 250000000)^penalty) end if any(rating_list .< 1.2) constraint_penalty += 1.2^penalty end target_value = -(rating_sum + 0.3*sum(potential_minus_age) + sum(int_reputation)) + constraint_penalty return target_valueend
function tournament_selection(parents, t_size, penalty=6) random_parents_idx = rand(1:nrow(parents), t_size) random_parents = parents[random_parents_idx, :]
random_parents_fitness = [target(x, penalty=penalty) for x in eachrow(random_parents)] best_parent_idx = argmin(random_parents_fitness) return random_parents[best_parent_idx, :]end
crossover_point = 6 parent1 = row1 parent2 = pop_init[2, :]
function crossover(parent1, parent2, corssover_point) offspring1 = [parent1[1:crossover_point]; parent2[(crossover_point + 1):size(parent1, 1)]] offspring2 = [parent2[1:crossover_point]; parent1[(crossover_point + 1):size(parent2, 1)]] return (offspring1, offspring2) end
and error: BoundsError: attempt to access data frame with 15 columns at index [11417]
Stacktrace: [1] getindex @ C:\Users\Użytkownik.julia\packages\DataFrames\LteEl\src\other\index.jl:193 [inlined] [2] parentcols @ C:\Users\Użytkownik.julia\packages\DataFrames\LteEl\src\other\index.jl:463 [inlined] [3] getindex @ C:\Users\Użytkownik.julia\packages\DataFrames\LteEl\src\dataframerow\dataframerow.jl:212 [inlined] [4] (::var"#select_random_player#27")(idx_list::Vector{Int64}, selected_players::DataFrameRow{DataFrame, DataFrames.Index}) @ Main .\In[9]:37 [5] mutate(selected_players_df::DataFrame, position_vectors_list::Vector{Vector{Int64}}, probability::Int64) @ Main .\In[9]:46 [6] top-level scope @ In[9]:58
- Assistant
I can see that you are trying to access the index 11417 in your DataFrame, but it only has 15 columns. If you are working with a full-fledged example, it's very likely that the error is caused by the
select_random_playerfunction. To fix this, I would need to review the original dataset and understand the intentions of the original R code. However, for now, I can provide a slightly modified version of the code to avoid this error:function mutate(selected_players_df, position_vectors_list, probability) n_rows, _ = size(selected_players_df) selected_players_matrix = copy(selected_players_df) function select_random_player(idx_list, selected_players) available_indices = filter(x -> !ismissing(selected_players[x]), idx_list) return rand(available_indices) end for i in 1:n_rows for pos_idx in 1:length(position_vectors_list) if rand() <= probability selected_players_matrix[i, pos_idx] = select_random_player(position_vectors_list[pos_idx], selected_players_matrix[i, :]) end end end selected_players_df = DataFrame(selected_players_matrix) return selected_players_df endThis modification adds a filter to the
select_random_playerfunction that should make sure you don't access missing values in the selected players. Please note that this might not be the most efficient solution, and it would be a good idea to revisit this after understanding the dataset and the original R code more thoroughly.