R中的XGBoost预测R中的罕见事件（不平衡数据）

Question

我正在尝试在R中使用xgboost来预测二进制结果。正值“1”仅占整体记录的3％。

我正在使用xgtree，但是，我不知道如何设置参数让模型识别“1”是正值。

你们有什么见解吗？

setDT(train) setDT(train)

#check missing values
table(is.na(train))
sapply(train, function(x) sum(is.na(x))/length(x))*100
table(is.na(test))
sapply(test, function(x) sum(is.na(x))/length(x))*100

#set all missing value as "Missing"
train[is.na(train)] <- -1
test[is.na(test)] <- -1




#using one hot encoding
labels <- as.factor(train$sd_app_install)
ts_label <- as.factor(test$sd_app_install)
new_tr <- model.matrix(~.+0,data = train[,-c("sd_app_install"),with=F])
new_ts <- model.matrix(~.+0,data = test[,-c("sd_app_install"),with=F])

#convert factor to numeric
labels <- as.numeric(labels)-1
ts_label <- as.numeric(ts_label)-1

#preparing matrix
dtrain <- xgb.DMatrix(data = new_tr,label = labels)
dtest <- xgb.DMatrix(data = new_ts,label=ts_label)

#default parameters
params <- list(
  booster = "gbtree",
  objective = "binary:logistic",
  eta=0.1,
  gamma=6,
  max_depth=10,
  min_child_weight=3.78,
  subsample=0.69,
  colsample_bytree= 0.933,
  scale_pos_weight = 32.3
)

xgbcv <- xgb.cv(params = params
                ,data = dtrain
                ,nrounds = 300
                ,nfold = 5
                ,showsd = T
                ,stratified = T
                ,print_every_n = 10
                ,early_stopping_rounds = 20
                ,maximize = F
)
##best iteration = 79

#first default - model training
xgb1 <- xgb.train(
  params = params
  ,data = dtrain
  ,nrounds = 300
  ,watchlist = list(val=dtest,train=dtrain)
  ,print_every_n = 10
  ,early_stop_round = 10
  ,maximize = F
  ,eval_metric = "auc"
)

谢谢， 拉尼娅