如何基于选定的日期迭代训练预测模型GAM、MARS、...并计算该时间段内的变量重要性

如何解决如何基于选定的日期迭代训练预测模型GAM、MARS、...并计算该时间段内的变量重要性

我有一个数据表，它总是有不同数量的列和列名以及一个名为 days 的数字变量（这个变量也不同；现在/这里：50）：

library(data.table)
library(caret)

days -> 50  
## Create random data table: ##
dt.train <- data.table(date = seq(as.Date('2020-01-01'),by = '1 day',length.out = 366),"DE" = rnorm(366,35,1),"Wind" = rnorm(366,5000,2),"Solar" = rnorm(366,3,"Nuclear" = rnorm(366,100,5),"ResLoad" = rnorm(366,200,3),check.names = FALSE)

我正在建模/训练一个线性模型 (= LM)，我想在其中预测 DE 列并计算相对于 days 变量的变量重要性。请参阅以下代码片段：

## MODEL FITTING: ##
## Linear Model: ##

## Function that calculates the iteratively prediction: ##
calcPred <- function(data){
  ## Model fitting: ##
  xgbModel <- stats::lm(DE ~ .-1-date,data = data)
  ## Model training: ##
  stats::predict.lm(xgbModel,data)
}

## Function that calculates the iteratively variable importance: ##
varImportance <- function(data){
  ## Model fitting: ##
  xgbModel <- stats::lm(DE ~ .-1-date,data = data)
  
  terms <- attr(xgbModel$terms,"term.labels")
  varimp <- caret::varImp(xgbModel)
  importance <- data[,.(date,imp = t(varimp))]
} 


## Train Data PREDICTION with iteratively xgbModel: ##
dt.train <- dt.train[,c('prediction') := calcPred(.SD),by = seq_len(nrow(dt.train)) %/% days]

## Iteratively variable importance:##
dt.importance <- data.table::copy(dt.train[,c("prediction") := NULL])
dt.importance <- dt.importance[,varImportance(.SD),by = seq_len(nrow(dt.train)) %/% days]

这里发生了什么：我的模型总是训练 50 天，然后正是在这个时间段内，对这些训练 50 天进行了预测。这一直持续到我的表的结束日期。此外，varImportance() 函数给出了训练区间l（此处为每 50 天）中预测变量（所有列，不包括 date 和 DE）的可变重要性。

最初我认为我也可以将函数 calcPred() 和 varImportance() 用于广义加性模型 (= GAM) 和多元自适应回归样条 (= MARS) 或梯度提升 (= GB)，但不幸的是，这个版本只适用于 LM。

现在我想简要描述一下其他三个模型的模型拟合一般情况，但在这里我还需要您的帮助，以便最终计算 GAM、MARS 和 GB 模型以及 LM。

GAM：

## Create data-vector with dates of dt.train: ##
v.trainDate <- dt.train$date
## Delete column "date" of train data for model fitting: ##
dt.train <- dt.train[,c("date") := NULL]

## Preparation for GAM: ##
trainDataNames <- names(dt.train)
responseVar <- trainDataNames[1]
trainDataNames <- trainDataNames[trainDataNames != responseVar]
## Create right-hand side of GAM model in string/character format: ##
formulaRight <- paste('s(',trainDataNames,')',sep = '',collapse = ' + ')
## Create the whole formula for GAM model in string/character format: ##
formulaGAM <- paste(responseVar,'~',formulaRight,collapse = ' ')
## Coerce to a formula object: ##
formulaGAM <- as.formula(formulaGAM)

## MODEL FITTING: ##
## Generalized Additive Model: ##
xgbModel <- mgcv::gam(formulaGAM,data = dt.train)

## Train and Test Data PREDICTION with xgbModel: ##
dt.train$prediction <- mgcv::predict.gam(xgbModel,dt.train)

## Add date columns to dt.train and dt.test: ##
dt.train <- data.table(date = v.trainDate,dt.train)

火星：

## Create vectors with all DE values of train data set: ##
v.trainY <- dt.train$DE
## Save dates of train data in an extra vector: ##
v.trainDate <- dt.train$date
## Create train matrices for GB model fitting: ##
m.trainData <- as.matrix(dt.train[,c("date","DE") := list(NULL,NULL)])
## Model fitting with grid-search: ##: ##
hyper_grid <- expand.grid(degree = 1:3,nprune = seq(2,length.out = 10) %>% floor()
              )
              
## MODEL FITTING: ##
## Multivariate Adaptive Regression Spline: ##
xgbModel <- caret::train(x = m.trainData,y = v.trainY,method = "earth",metric = "RMSE",trControl = trainControl(method = "cv",number = 10),tuneGrid = hyper_grid
              )
              
              
## Train Data PREDICTION with xgbModel: ##
dt.train$prediction <- stats::predict(xgbModel,dt.train)

GB：

## Create vectors with all DE values of train data set: ##
v.trainY <- dt.train$DE
## Save dates of train data in an extra vector: ##
v.trainDate <- dt.train$date
## Create train matrices for GB model fitting: ##
m.trainData <- as.matrix(dt.train[,NULL)])

## Gradient Boosting with hyper parameter tuning: ##
xgb_trcontrol <- caret::trainControl(method = "cv",number = 3,allowParallel = TRUE,verboseIter = TRUE,returnData = FALSE
)

xgbgrid <- base::expand.grid(nrounds = c(15000),# 15000
                             max_depth = c(2),eta = c(0.01),gamma = c(1),colsample_bytree = c(1),min_child_weight = c(2),subsample = c(0.6)
)

## MODEL FITTING: ##
## Gradient Boosting: ##
xgbModel <- caret::train(x = m.trainData,trControl = xgb_trcontrol,tuneGrid = xgbgrid,method = "xgbTree"
)

## Train data PREDICTION with xgbModel: ##
dt.train$prediction <- stats::predict(xgbModel,m.trainData)

## Add DE and date columns to dt.train: ##
dt.train <- data.table(DE = v.trainY,dt.train)
dt.train <- data.table(date = v.trainDate,dt.train)

我如何计算其他三个模型和 LM 的相同？我希望有人可以帮助我。很抱歉问题拖了这么久。

解决方法

您可以将模型定义为作为参数传递给 calcPred 和 varImportance 的函数。

例如带有 LM

model <- function(data) {stats::lm(DE ~ .-1-date,data = data)}

用GAM

model <- function(data) {mgcv::gam(formulaGAM,data = data)}

带有MARS：

model <- function(data) {
  hyper_grid <- expand.grid(degree = 1:3,nprune = seq(2,100,length.out = 10) %>% floor())
  caret::train(x = subset(data,select = -DE),y = data$DE,method = "earth",metric = "RMSE",trControl = trainControl(method = "cv",number = 10),tuneGrid = hyper_grid)
}

我更新了代码以考虑到这个新参数：

library(data.table)
library(caret)
library(magrittr)


days <- 50
## Create random data table: ##
dt.train <- data.table(date = seq(as.Date('2020-01-01'),by = '1 day',length.out = 366),"DE" = rnorm(366,35,1),"Wind" = rnorm(366,5000,2),"Solar" = rnorm(366,3,"Nuclear" = rnorm(366,5),"ResLoad" = rnorm(366,200,3),check.names = FALSE)

dt.importance <- data.table::copy(dt.train)

## Define model & prediction functions ##

model <- function(data) {stats::lm(DE ~ .-1-date,data = data)}

predict <- function(data,model) {stats::predict(model,data)}

calcPred <- function(data,model){
  if (nrow(data)==days) {
  stats::predict(model,data) } else {
  NULL }
}

## Function that calculates the iteratively variable importance: ##
varImportance <- function(data,model){
  cat(nrow(data),'\n')
  if (nrow(data)==days) {
  terms <- attr(model$terms,"term.labels")
  varimp <- caret::varImp(model)
  importance <- data[,.(date,imp = t(varimp))]} else
  { NULL }
}


## Train Data PREDICTION with iteratively xgbModel: ##
dt.train <- dt.train[,c('prediction') := calcPred(.SD,model(.SD)),by = (seq_len(nrow(dt.train))-1) %/% days]

## Iteratively variable importance:##

dt.importance <- dt.importance[,varImportance(.SD,by = (seq_len(nrow(dt.train))-1) %/% days]

要使用其他模型，只需在上面的代码中使用您想要的模型函数。这适用于您提供的数据集上的 LM 或 GAM。

不幸的是，varImp 似乎不适用于带有 MARS 的数据集，尽管这 seems feasible。

如何基于选定的日期迭代训练预测模型GAM、MARS、...并计算该时间段内的变量重要性

如何解决如何基于选定的日期迭代训练预测模型GAM、MARS、...并计算该时间段内的变量重要性

解决方法

相关推荐