R:可变排名模型自动化代码以将其写入函数

Question

如何将下面的命令列表写成一个函数？

例如：variableranking＆lt; - 函数(公式，变量，.....({插入命令........}

#Variable Ranking Model automation
#exclusion of the variables that are not model variables
exclude <- c("~,", "+" ) # exclude target which is bound_count for Property
formula <- toString(formula)
formula
#listing the entire model formula out
variables_pre <- unlist(strsplit(formula, split = " "))
variables_pre
#keeping only the model variables
variables <-  sort(variables_pre[!variables_pre %in% exclude])
variables
#Exclude "," on the target variable 
variables[1] <- substr(variables[1], 1, nchar(variables[1])-1)
variables
#Assigning the variables into a data frame
d <- c(1:length(variables))
d
d= data.frame(d)
d
d= t(d)
d
colnames(d)=variables
d
# exclude target variable on the data frame
allvariables <- colnames(d)[-1]
allvariables
# container for models
listOfModels <- vector("list", length(allvariables))
listOfModels
# loop over variables
for (i in seq_along(allvariables)) {
  # exclude variable i
  currentvariable <- allvariables[-i]
  # programmatically assemble regression formula
  regressionFormula <- as.formula(
    paste(variables[1],"~", paste(currentvariable, collapse="+")))
  # fit model
  currentModel <- glm(formula = regressionFormula, family=binomial(link = "logit"), data=dataL_TT)
  # store model in container
  listOfModels[[i]] <- currentModel
} 
listOfModels
#List of AICs for each model 
lapply(listOfModels,function(xx) xx$aic)
#Assign X as the AIC of the full model
X <- modelTT$aic
X
# Difference of AICs of each model to the AIC of the full model
AICdifference <- lapply(listOfModels,function(xx) xx$aic - X)
AICdifference
# Naming the AIC Difference
AICdifference2 = data.frame(variables=allvariables, AICdiff=unlist(AICdifference))
AICdifference2
#Graph the Barchart of the AIC decrease of each variables and save it to pdf
pdf("Barchart.pdf",width=12,height=10)
par(mar=c(2,18,2,5))
barplot(sort(AICdifference2$AICdiff, decreasing = F), main="Variable Ranking based on AIC decrease", 
        horiz=TRUE, xlab="AIC Increase", names.arg= AICdifference2$variables[order(AICdifference2$AICdiff, decreasing = F)], 
        las=1, col= 'dodgerblue4')
dev.off()

有可能吗？因为它有很多参数。因此，基本上我只需要AICDifference2数据框的输出。和barplot保存为PDF和弹出

Answer 1

尝试以下：

FOO <- function(myformula, data, fullmodel_AIC, plotname){
  exclude <- c("~,", "+" ) # exclude target which is bound_count for Property
  myformula <- toString(myformula)
  variables_pre <- unlist(strsplit(myformula, split = " "))
  variables <-  sort(variables_pre[!variables_pre %in% exclude])
  variables[1] <- substr(variables[1], 1, nchar(variables[1])-1)
  d <- t(data.frame(c(1:length(variables))))
  colnames(d)=variables
  allvariables <- colnames(d)[-1]
  listOfModels <- vector("list", length(allvariables))
  for (i in seq_along(allvariables)) {
    # exclude variable i
    currentvariable <- allvariables[-i]
    # programmatically assemble regression formula
    regressionFormula <- as.formula(
      paste(variables[1],"~", paste(currentvariable, collapse="+")))
    # fit model
    currentModel <- glm(formula = regressionFormula, family=binomial(link = "logit"), data = data)
    # store model in container
    listOfModels[[i]] <- currentModel
  } 
  AICdifference <- lapply(listOfModels,function(xx) xx$aic - fullmodel_AIC)
  AICdifference2 <- data.frame(variables=allvariables, AICdiff=unlist(AICdifference))
  pdf(paste0(plotname, ".pdf"),width=12,height=10)
  par(mar=c(2,18,2,5))
  barplot(sort(AICdifference2$AICdiff, decreasing = F), main="Variable Ranking based on AIC decrease", 
          horiz=TRUE, xlab="AIC Increase", names.arg= AICdifference2$variables[order(AICdifference2$AICdiff, decreasing = F)], 
          las=1, col= 'dodgerblue4')
  dev.off()
  return(AICdifference2)
}

您需要四个参数：myformula，data(代码中的dataL_TT(，fullmodel_AIC(您的代码中的modelTT$aic(和一个字符串来命名图。

尝试使用FOO(myformula, dataL_TT, modelTT$aic, "test")调用它，然后插入myformula的公式对象。

我将formula更改为myformula，因为formula是统计程序包的基本函数，并且使用是基本函数的对象名称通常是不明智的。