Question

约束：使用dplyr或tidyverse库：

目标：我想使用阈值汇总数据。阈值采用许多值，并附加/整理这些汇总结果。

最小可重复的例子：

df <- data.frame(colA=c(1,2,1,1),
                 colB=c(0,0,3,1),
                 colC=c(0,5,2,3),
                 colD=c(2,4,4,2))
> df
  colA colB colC colD
1    1    0    0    2
2    2    0    1    2
3    1    3    2    2
4    1    1    3    2

当前：单一阈值

df.ans <- df %>%
            group_by(colA) %>%
            summarize(theshold=1,
                      calcB = sum(df$colB[df$colB > theshold] - 1),
                      calcC = sum(df$colC[df$colC > theshold] - 1),
                      calcD = sum(df$colD[df$colD > theshold] - 1))
> df.ans
# A tibble: 2 x 5
   colA theshold calcB calcC calcD
  <dbl>    <dbl> <dbl> <dbl> <dbl>
1     1        1     2     3     4
2     2        1     2     3     4

期望：多个阈值

> df.ans
# A tibble: 6 x 5
   colA theshold calcB calcC calcD
  <dbl>    <dbl> <dbl> <dbl> <dbl>
1     1        1     2     3     4
2     2        1     2     3     4
3     1        2     ....
4     2        2     ....
5     1        3     ....
6     2        3     ....

Answer 1

只需编写一个函数来进行阈值处理

thresh_fun <- function(df, threshold) {
  df %>% 
  group_by(colA) %>%
  summarize(threshold=threshold,
            calcB = sum(colB[colB > threshold] - 1),
            calcC = sum(colC[colC > threshold] - 1),
            calcD = sum(colD[colD > threshold] - 1))
}

然后将每个值的data.frame映射到

# library(purrr) for map_df
map_df(1:3, ~thresh_fun(df, .))
#    colA threshold calcB calcC calcD
#   <dbl>     <int> <dbl> <dbl> <dbl>
# 1     1         1     2     3     5
# 2     2         1     0     4     3
# 3     1         2     2     2     3
# 4     2         2     0     4     3
# 5     1         3     0     0     3
# 6     2         3     0     4     3

dplyr：追加按阈值变量汇总行数

1 个答案: