Submit

#############################################################

model_data = data_higgs_0_cleaned_scaled
label = as.integer(model_data$Label) -1
drop = c(ncol(model_data),ncol(model_data)-1,ncol(model_data)-2)
bst_0 <- xgboost(data = data.matrix(model_data[,-drop]), label = label,
                 max.depth =9, 
                 eta = 0.01, 
                 nround = 624,
                 nthread = 4, 
                 objective = "binary:logistic")



model_data = data_higgs_1_cleaned_scaled
label = as.integer(model_data$Label) -1
drop = c(ncol(model_data),ncol(model_data)-1,ncol(model_data)-2)
bst_1 <- xgboost(data = data.matrix(model_data[,-drop]), label = label,
                 max.depth =9, 
                 eta = 0.01, 
                 nround = 652,
                 nthread = 4, 
                 objective = "binary:logistic")



model_data = data_higgs_2_cleaned_scaled
label = as.integer(model_data$Label) -1
drop = c(ncol(model_data),ncol(model_data)-1,ncol(model_data)-2)
bst_2 <- xgboost(data = data.matrix(model_data[,-drop]), label = label,
                 max.depth =9, 
                 eta = 0.01, 
                 nround = 1104,
                 nthread = 4, 
                 objective = "binary:logistic")


#############################################################

AMS <- function(real,pred,weight)
{
  pred_s_ind = which(pred==1)                          # Index of s in prediction
  real_s_ind = which(real==1)                          # Index of s in actual
  real_b_ind = which(real==0)# Index of b in actual
  s = sum(weight[intersect(pred_s_ind,real_s_ind)])      # True positive rate
  b = sum(weight[intersect(pred_s_ind,real_b_ind)])      # False positive rate
  b_tau = 10                                             # Regulator weight
  ans = sqrt(2*((s+b+b_tau)*log(1+s/(b+b_tau))-s))
  return(ans)
}




thresh = seq(0.04,0.13,0.001)
E= E_s = E_b = aMS = rep(0,length(thresh))

for (i in  (1:length(thresh))){
  
  model_data = data_higgs_0_cleaned_scaled
  label = as.integer(model_data$Label) -1
  pred_0 = predict(bst_0, data.matrix(model_data[,-drop]))
  pred_0 = as.integer(pred_0 + thresh[i])

  model_data = data_higgs_1_cleaned_scaled
  label = as.integer(model_data$Label) -1
  pred_1 = predict(bst_1, data.matrix(model_data[,-drop]))
  pred_1 = as.integer(pred_1 +thresh[i])

  model_data = data_higgs_2_cleaned_scaled
  label = as.integer(model_data$Label) -1
  pred_2 = predict(bst_2, data.matrix(model_data[,-drop]))
  pred_2 = as.integer(pred_2 +thresh[i])



  pred_undef = rep(0,nrow(data_higgs_undefined))

  pred     = rbind(c(pred_undef,pred_0,pred_1,pred_2))
  response = rbind(c(data_higgs_undefined$Label,
                   data_higgs_0_cleaned$Label,
                   data_higgs_1_cleaned$Label,
                   data_higgs_2_cleaned$Label))
  response = as.integer(response) -1
  weight   = rbind(c(data_higgs_undefined$Weight,
                   data_higgs_0_cleaned$Weight,
                   data_higgs_1_cleaned$Weight,
                   data_higgs_2_cleaned$Weight))

  error = 1-sum(response == pred)/length(response)
  ams = AMS(response,pred,weight)
  pred_b_ind = which(pred==0) 
  pred_s_ind = which(pred==1)                          
  real_s_ind = which(response==1)                          
  real_b_ind = which(response==0) 
  class_error_s = 1- length(intersect(pred_s_ind,real_s_ind))/length(real_s_ind)
  class_error_b = 1- length(intersect(pred_b_ind,real_b_ind))/length(real_b_ind)


  E[i] =error
  E_s[i] =class_error_s
  E_b[i]= class_error_b
  aMS[i] =ams
  print(ams)
}

plot(thresh,aMS)









t0 = 0.15
t1 = 0.15
t2 = 0.15



model_data = data.submission_higgs_0_cleaned_scaled
label = as.integer(model_data$Label) -1
drop = c(ncol(model_data))
pred_0 = predict(bst_0, data.matrix(model_data[,-drop]))
pred_0 = as.integer(pred_0 + t0)

model_data =  data.submission_higgs_1_cleaned_scaled
label = as.integer(model_data$Label) -1
drop = c(ncol(model_data))
pred_1 = predict(bst_1, data.matrix(model_data[,-drop]))
pred_1 = as.integer(pred_1 + t1)

model_data =  data.submission_higgs_2_cleaned_scaled
label = as.integer(model_data$Label) -1
drop = c(ncol(model_data))
pred_2 = predict(bst_2, data.matrix(model_data[,-drop]))
pred_2 = as.integer(pred_2 + t2)



pred_undef = rep(0,nrow(data.submission_higgs_undefined))
pred       = rbind(c(pred_undef,pred_0,pred_1,pred_2))
EventId    = rbind(c(data.submission_higgs_undefined$EventId,
                   data.submission_higgs_0_cleaned_scaled$EventId,
                   data.submission_higgs_1_cleaned_scaled$EventId,
                   data.submission_higgs_2_cleaned_scaled$EventId))


df = as.data.frame(cbind(c(EventId),c(1:length(pred)),c(pred)))
names(df)[1] = "EventId"
names(df)[2] = "RankOrder"
names(df)[3] = "Class"
df$EventId = as.integer(df$EventId)
df$RankOrder= as.integer(df$RankOrder)
df$Class = ifelse(df$Class==0,"b","s")
write.csv(df, file = "submission.csv",row.names=FALSE,quote=FALSE)