r - 如何将列值的下半部分移动到新创建的列中？

Question

我有一列在前 50% 的行中包含三个不同测量值的平均值，在后 50% 的行中包含相关的标准误差。在前一列中是用于每个的名称(meanNativeSR、meanExoticSR、meanTotalSR、seN、seE、seT)。我想创建 2 个新列，在第一列中包含 se_ 名称，在第二列中包含它们的值，然后删除底部 50% 的行。这是我的数据集:

df <- structure(list(Invasion = structure(c(1L, 1L, 1L, 2L, 2L, 2L, 
3L, 3L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 2L, 
2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 
1L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L
), .Label = c("Low", "Medium", "High"), class = "factor"), Growth = structure(c(1L, 
2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 
3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 
1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 
2L, 3L, 1L, 2L, 3L), .Label = c("cover", "herb", "woody"), class = "factor"), 
    mean_se = c("meanNativeSR", "meanNativeSR", "meanNativeSR", 
    "meanNativeSR", "meanNativeSR", "meanNativeSR", "meanNativeSR", 
    "meanNativeSR", "meanNativeSR", "meanExoticSR", "meanExoticSR", 
    "meanExoticSR", "meanExoticSR", "meanExoticSR", "meanExoticSR", 
    "meanExoticSR", "meanExoticSR", "meanExoticSR", "meanTotalSR", 
    "meanTotalSR", "meanTotalSR", "meanTotalSR", "meanTotalSR", 
    "meanTotalSR", "meanTotalSR", "meanTotalSR", "meanTotalSR", 
    "seN", "seN", "seN", "seN", "seN", "seN", "seN", "seN", "seN", 
    "seE", "seE", "seE", "seE", "seE", "seE", "seE", "seE", "seE", 
    "seT", "seT", "seT", "seT", "seT", "seT", "seT", "seT", "seT"
    ), value = c(0.769230769230769, 0.230769230769231, 0.923076923076923, 
    2.46153846153846, 6.84615384615385, 0.538461538461538, 1.69230769230769, 
    1.76923076923077, 1.15384615384615, 0.384615384615385, 0, 
    1.38461538461538, 1.76923076923077, 0, 2.23076923076923, 
    2.07692307692308, 0.769230769230769, 2.46153846153846, 1.15384615384615, 
    0.230769230769231, 2.53846153846154, 4.23076923076923, 6.84615384615385, 
    3.23076923076923, 3.76923076923077, 2.76923076923077, 3.84615384615385, 
    0.280883362823162, 0.12162606385263, 0.329364937914491, 0.312463015562922, 
    0.705710715103738, 0.24325212770526, 0.36487819155789, 0.280883362823162, 
    0.191021338791684, 0.140441681411581, 0, 0.180400606147055, 
    0.201081886427668, 0, 0.230769230769231, 0.329364937914491, 
    0.12162606385263, 0.24325212770526, 0.273771237231572, 0.12162606385263, 
    0.24325212770526, 0.394738572265145, 0.705710715103738, 0.440772139427464, 
    0.532938710021193, 0.257050482766198, 0.336767321450351)), row.names = c(NA, 
-54L), class = c("tbl_df", "tbl", "data.frame"))

我能够弄清楚我想用下面的代码做什么，但肯定有更优雅的方法，因为这种方法需要我创建不必要的中间体。

#create an intermediate data.frame that contains just the means and their values from the first half of original df
df.mean <- head(df, -27)
#rename columns 3 and 4
colnames(df.mean)[3] <- "mean"
colnames(df.mean)[4] <- "mean_value"


#create another intermediate data.frame with standard error values from the bottom half of original df
df.se <- df[28:54,]
#rename columns 3 and 4
colnames(df.se)[3] <- "se"
colnames(df.se)[4] <- "se_value"


#cbind those together to get desired result
df.final <- cbind(df.mean, df.se[,3:4])

#remove intermediates
rm(df.mean); rm(df.se)

是否有更简单的方法来实现这一点，也许使用管道或 tidyverse 中的某些函数，或者甚至使用 base R？

Answer 1

使用 tidyverse，我们可以执行 group_split，更改列名，并执行 inner_join

library(dplyr)
library(purrr)
df %>%
   group_split(grp = row_number() > 27, .keep = FALSE) %>% 
   map2(list(c('mean', 'mean_value'), c('se', 'se_value')),
        ~ {nm1 <- .y
           .x  %>%
             rename_at(3:4, ~ nm1) %>%
             mutate(rn = row_number())} ) %>% 
  reduce(inner_join) %>% 
  select(-rn)

-输出

# A tibble: 27 x 6
#   Invasion Growth mean         mean_value se    se_value
#   <fct>    <fct>  <chr>             <dbl> <chr>    <dbl>
# 1 Low      cover  meanNativeSR      0.769 seN      0.281
# 2 Low      herb   meanNativeSR      0.231 seN      0.122
# 3 Low      woody  meanNativeSR      0.923 seN      0.329
# 4 Medium   cover  meanNativeSR      2.46  seN      0.312
# 5 Medium   herb   meanNativeSR      6.85  seN      0.706
# 6 Medium   woody  meanNativeSR      0.538 seN      0.243
# 7 High     cover  meanNativeSR      1.69  seN      0.365
# 8 High     herb   meanNativeSR      1.77  seN      0.281
# 9 High     woody  meanNativeSR      1.15  seN      0.191
#10 Low      cover  meanExoticSR      0.385 seE      0.140
# … with 17 more rows