为什么这个dplyr输入不起作用？

Question

我有一个使用以下管道操作序列获得的数据框:

library(dplyr)
data_agg = data %>%
    group_by(Year,Month) %>%
    summarise( monthly_users = sum(Users))

head(data_agg) 看起来像这样:

  Year Month monthly_users
1 2013    07            22
2 2013    08           221
3 2013    09           252
4 2013    10           313
5 2013    11           322
6 2013    12           339

我现在dput(),获得:

structure(list(Year = c("2013", "2013", "2013", "2013", "2013", 
"2013", "2014", "2014", "2014", "2014", "2014", "2014", "2014"
), Month = c("07", "08", "09", "10", "11", "12", "01", "02", 
"03", "04", "05", "06", "07"), monthly_users = c(22L, 221L, 252L, 
313L, 322L, 339L, 344L, 338L, 301L, 307L, 401L, 383L, 318L)), .Names = c("Year", 
"Month", "monthly_users"), row.names = c(NA, -13L), class = c("grouped_df", 
"tbl_df", "tbl", "data.frame"), vars = list(Year), drop = TRUE)

但是,当我运行上面的输出时,dput()我得到以下错误:

Error in structure(list(Year = c("2013", "2013", "2013", "2013", "2013",  : 

对象'年'未找到

为什么会这样？

Answer 1

解决方法是更改​​:

, vars = list(Year), drop = TRUE

至

, vars = list(quote(Year)), drop = TRUE

这允许您使用结果dput重新创建原始输出.比较以下内容.

mtcars2 <- mtcars %>% group_by(cyl, gear, carb) %>% summarise(mmpg = mean(mpg))
dput(mtcars2)
structure(list(cyl = c(4, 4, 4, 4, 6, 6, 6, 8, 8, 8, 8, 8), gear = c(3,
4, 4, 5, 3, 4, 5, 3, 3, 3, 5, 5), carb = c(1, 1, 2, 2, 1, 4,
6, 2, 3, 4, 4, 8), mmpg = c(21.5, 29.1, 24.75, 28.2, 19.75, 19.75,
19.7, 17.15, 16.3, 12.62, 15.8, 15)), .Names = c("cyl", "gear",
"carb", "mmpg"), row.names = c(NA, -12L), class = c("grouped_df",
"tbl_df", "tbl", "data.frame"), vars = list(cyl, gear), drop = TRUE)

newmtcars <- structure(list(cyl = c(4, 4, 4, 4, 6, 6, 6, 8, 8, 8, 8, 8), gear = c(3,
4, 4, 5, 3, 4, 5, 3, 3, 3, 5, 5), carb = c(1, 1, 2, 2, 1, 4,
6, 2, 3, 4, 4, 8), mmpg = c(21.5, 29.1, 24.75, 28.2, 19.75, 19.75,
19.7, 17.15, 16.3, 12.62, 15.8, 15)), .Names = c("cyl", "gear",
"carb", "mmpg"), row.names = c(NA, -12L), class = c("grouped_df",
"tbl_df", "tbl", "data.frame"), vars = list(quote(cyl), quote(gear)), drop = TRUE)

另一种选择是在您重新读取数据后删除" vars = list(Year),"部分dput并使用regroup.

ungroupedmtcars <- structure(list(cyl = c(4, 4, 4, 4, 6, 6, 6, 8, 8, 8, 8, 8), gear = c(3,
4, 4, 5, 3, 4, 5, 3, 3, 3, 5, 5), carb = c(1, 1, 2, 2, 1, 4,
6, 2, 3, 4, 4, 8), mmpg = c(21.5, 29.1, 24.75, 28.2, 19.75, 19.75,
19.7, 17.15, 16.3, 12.62, 15.8, 15)), .Names = c("cyl", "gear",
"carb", "mmpg"), row.names = c(NA, -12L), class = c("grouped_df",
"tbl_df", "tbl", "data.frame"), drop = TRUE)

ungroupedmtcars <- regroup(ungroupedmtcars, list(quote(cyl), quote(gear)))