插入符号中的用户定义的 summaryFunction，logloss [英] user defined summaryFunction in caret, logloss

问题描述

使用 caret 包时，我无法使以下用户定义的汇总函数正常工作.它应该计算 logloss，但我一直发现找不到 logloss.下面是一个可重现的示例:

Using the caret package, I am having trouble getting the following user defined summary function to work. It is supposed to calculate the logloss, but I keep getting that logloss is not found. Below, a reproducible example:

data <- data.frame('target' = sample(c('Y','N'),100,replace = T), 'X1' = runif(100), 'X2' = runif(100))

log.loss2 <- function(data, lev = NULL, model = NULL) {
  logloss = -sum(data$obs*log(data$Y) + (1-data$obs)*log(1-data$Y))/length(data$obs)
  names(logloss) <- c('LL')
  logloss
}

fitControl <- trainControl(method="cv",number=1, classProbs = T, summaryFunction = log.loss2)

my.grid <- expand.grid(.decay = c(0.05), .size = c(2))

fit.nnet2 <- train(target ~., data = data,
                  method = "nnet", maxit = 500, metric = 'LL',
                  tuneGrid = my.grid, verbose = T)

推荐答案

错误是由于您没有在调用 train 时包含 trControl = fitControl .然而，这会给你带来另一个错误，这是由于 data$obs 和 data$pred 是因素 - 需要转换为数字，这给 1 或 2，减去 1 得到所需的 0 和 1

The error was due to the fact you did not include trControl = fitControl in the call to train. However that would bring you to another error that is due to the fact data$obs and data$pred are factors - one needs to convert to numeric which gives 1 or 2, subtracting 1 gives desired 0 and 1

log.loss2 <- function(data, lev = NULL, model = NULL) {
  data$pred <- as.numeric(data$pred)-1
  data$obs <- as.numeric(data$obs)-1 
  logloss = -sum(data$obs*log(data$Y) + (1-data$obs)*log(1-data$Y))/length(data$obs)
  names(logloss) <- c('LL')
  logloss
}

fitControl <- trainControl(method="cv",number=1, classProbs = T, summaryFunction = log.loss2)

fit.nnet2 <- train(target ~., data = data,
                   method = "nnet", maxit = 500, metric = "LL" ,
                   tuneGrid = my.grid, verbose = T, trControl = fitControl,
                   maximize = FALSE)
#output
Neural Network 

100 samples
  2 predictor
  2 classes: 'N', 'Y' 

No pre-processing
Resampling: Cross-Validated (1 fold) 
Summary of sample sizes: 0 
Resampling results:

  LL       
  0.6931472

Tuning parameter 'size' was held constant at a value of 2
Tuning parameter 'decay' was held constant at a value of 0.05

需要注意的几点:

此损失函数仅适用于包含 N/Y 作为类的数据，因为概率定义为 data$Y，这是一种更好的方法是找到类的名称并使用它.此外，截断概率值的良好做法是因为 log(0) 不是一个好主意:

this loss function will work only with data containing N/Y as classes because probability is defined as data$Y, a better approach is to find the name of the class and use that. Additionally its good practice to truncate the probability values since log(0) is not a good idea:

LogLoss <- function (data, lev = NULL, model = NULL) 
  { 
    obs <- data[, "obs"]
    cls <- levels(obs) #find class names
    probs <- data[, cls[2]] #use second class name
    probs <- pmax(pmin(as.numeric(probs), 1 - 1e-15), 1e-15) #bound probability
    logPreds <- log(probs)        
    log1Preds <- log(1 - probs)
    real <- (as.numeric(data$obs) - 1)
    out <- c(mean(real * logPreds + (1 - real) * log1Preds)) * -1
    names(out) <- c("LogLoss")
    out
  }

这篇关于插入符号中的用户定义的 summaryFunction，logloss的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！