R 数据集中的变量可以用作函数中的参数吗？

让数据为：

> dput(df)
structure(list(NAME.x = c("ANNE", "BOB", "CATHY", "DIANNE", "EMILY"
), NAME.y = c(NA, "BOB", "CATHY", "DIANNE", NA), AGE.x = c("81", 
"47", "47", "47", "37"), AGE.y = c(NA, "47", "47", "47", NA), 
    ADMISSIONDATE.x = structure(c(1380751296, 1382088000, 1382088000, 
    1382088000, 1383207720), class = c("POSIXct", "POSIXt"), tzone = "UTC"), 
    ADMISSIONDATE.y = structure(c(NA, 1382088000, 1382088000, 
    1382088000, NA), class = c("POSIXct", "POSIXt"), tzone = "UTC"), 
    DISCHARGEDDATE.x = structure(c(1381172735, 1382189165, 1382189165, 
    1382189165, 1383250549), class = c("POSIXct", "POSIXt"), tzone = "UTC"), 
    DISCHARGEDDATE.y = structure(c(NA, 1382189165, 1382189165, 
    1382189165, NA), class = c("POSIXct", "POSIXt"), tzone = "UTC")), row.names = c(NA, 
-5L), .Names = c("NAME.x", "NAME.y", "AGE.x", "AGE.y", "ADMISSIONDATE.x", 
"ADMISSIONDATE.y", "DISCHARGEDDATE.x", "DISCHARGEDDATE.y"), class = "data.frame")

我想检查这个数据集中常见变量之间的相似性和差异。我试图编写一个函数，其中3个参数是数据集，数据集中的2个变量

  check<-function(data,var1,var2){
    # X1: x and y are equal
    # X2: x and y are not equal
    # Y1: x and y are non-empty
    # Y2: x and y are empty
    # Z1: x is non-empty and y is empty
    # Z2: x is empty and y is non-empty
    cnt_each<-data %>% 
      mutate(X1 = (var1==var2),
             X2 = (var1!=var2),
             Y1 = (!is.na(var1) & !is.na(var2)),
             Y2 = (is.na(var1) & is.na(var2)),
             Z1 = (!is.na(var1) & is.na(var2)),
             Z2 = (is.na(var1) & !is.na(var2))) %>%
      summarise_at("X1:Z2",funs(sum(.))) %>%
      mutate(sum_all=sum(.,na.rm=TRUE))
    return(cnt_each)
  }

mutate_impl（.data，dots）中出错：找不到对象“NAME.x”

---

我们可以利用devel版本的

dplyr

（即将发布的

0.6.0

来实现这一点）。

enquo

接受输入参数并转换为

quosure

。在

mutate/summary/group_by

中，quosures是不带引号的（

！！

或

UQ

）用于评估

check<-function(data,var1,var2){
  var1 <- enquo(var1)
  var2 <- enquo(var2) 
  data %>%
       mutate(X1 = UQ(var1)==UQ(var2),
              X2 = UQ(var1) != UQ(var2),
              Y1 = !is.na(UQ(var1)) &  !is.na(UQ(var2)),
              Y2 = is.na(UQ(var1)) & is.na(UQ(var2)),
              Z1 = !is.na(UQ(var1)) & !is.na(UQ(var2)),
              Z2 = is.na(UQ(var1)) & !is.na(UQ(var2))) %>%
        summarise_at(vars(X1:Z2), funs(sum(., na.rm = TRUE))) %>%
        mutate(sum_all = rowSums(., na.rm = TRUE))

}    


check(df, NAME.x, NAME.y)
#   X1 X2 Y1 Y2 Z1 Z2 sum_all
#1  3  0  3  0  3  0       9

检查%
变异（sum_all=rowSums（，na.rm=TRUE））
}    
检查（df，NAME.x，NAME.y）
#X1 X2 Y1 Y2 Z1 Z2总和
#1  3  0  3  0  3  0       9

请参见

mutate\uu

以将字符串作为列名传递。因此

enquo

和

UQ

都将出现在新版本的

dplyr

？@HNSKD Yes，以及

quo\u name

和其他类似

的东西中

，

quo

或

quos

等。看起来

xxx\uU

类型的函数在下一个版本中将被淘汰？@zx8754，这些函数已被标记为“主要动词的不推荐SE版本”。在开发版本0.5.0.9004中。@zx8754似乎是这样的

check<-function(data,var1,var2){
  var1 <- enquo(var1)
  var2 <- enquo(var2) 
  data %>%
       mutate(X1 = UQ(var1)==UQ(var2),
              X2 = UQ(var1) != UQ(var2),
              Y1 = !is.na(UQ(var1)) &  !is.na(UQ(var2)),
              Y2 = is.na(UQ(var1)) & is.na(UQ(var2)),
              Z1 = !is.na(UQ(var1)) & !is.na(UQ(var2)),
              Z2 = is.na(UQ(var1)) & !is.na(UQ(var2))) %>%
        summarise_at(vars(X1:Z2), funs(sum(., na.rm = TRUE))) %>%
        mutate(sum_all = rowSums(., na.rm = TRUE))

}    


check(df, NAME.x, NAME.y)
#   X1 X2 Y1 Y2 Z1 Z2 sum_all
#1  3  0  3  0  3  0       9