Question

我有一个名为my_list的数据帧列表。以下是my_list中数据框的示例。

> print(df1)    
       A          B         Names
1   0.8262825   0.734412    Baseline
2   1.0100000   0.734412    Sample1
3   0.8262825   0.734412    Sample2
4   1.0100000   0.734412    Sample3
5   0.8262825   0.734412    Sample4
6   1.0100000   0.734412    Sample5
7   0.8262825   0.734412    Sample6
8   1.0100000   0.734412    Sample7
9   0.8262825   0.734412    Sample8
10  1.0100000   0.734412    Sample9
11  0.8262825   0.734412    Sample10
12  1.0100000   NA          AASHTO

我想向my_list中每个包含A和B列平均值的数据帧添加一个新行，但在Names列中包含“ Baseline”和“ AASHTO”的行除外。（因此，只有Sample1到Sample10的行的平均值）

最后，我想将“名称”列设置为my_list中每个数据框的行名称，并从列表中的所有数据框中删除“名称”列。

my_list中每个数据框的预期结果将是

                A          B         
Baseline    0.8262825   0.734412    
Sample1     1.0100000   0.734412    
Sample2     0.8262825   0.734412    
Sample3     1.0100000   0.734412    
Sample4     0.8262825   0.734412    
Sample5     1.0100000   0.734412    
Sample6     0.8262825   0.734412    
Sample7     1.0100000   0.734412    
Sample8     0.8262825   0.734412    
Sample9     1.0100000   0.734412    
Sample10    0.8262825   0.734412
Mean        0.8156500   0.734412
AASHTO      1.0100000   NA

非常感谢您的帮助。

Answer 1

我们可以在list和lapply之间循环，获得列“ A”，“ B”的colMeans，但其中“名称”是“基准”或“ AASHTO”，然后rbind和原始数据集

lst2 <-  lapply(lst1, function(x) {
   means <- colMeans(x[!x$Names %in% c("Baseline", "AASHTO"),
            c('A', 'B')], na.rm = TRUE)
        d1 <- rbind(x, data.frame(Names = "Mean", as.list(means)))
        row.names(d1) <- d1$Names
        d1[setdiff(names(d1), "Names")]
             })

或使用tidyverse

library(dplyr)
library(purrr)
library(tibble)
map(lst1, ~ .x %>%
            add_row(Names = 'Mean', 
              A = mean(.$A[!.$Names %in% c("Baseline", "AASHTO")], 
                     na.rm = TRUE),
              B = mean(.$B[!.$Names %in% c("Baseline", "AASHTO")], na.rm = TRUE)) %>%
         `row.names<-`(., NULL) %>%
             column_to_rownames('Names'))

数据

lst1 <- list(structure(list(A = c(0.8262825, 1.01, 0.8262825, 1.01, 0.8262825, 
1.01, 0.8262825, 1.01, 0.8262825, 1.01, 0.8262825, 1.01), B = c(0.734412, 
0.734412, 0.734412, 0.734412, 0.734412, 0.734412, 0.734412, 0.734412, 
0.734412, 0.734412, 0.734412, NA), Names = c("Baseline", "Sample1", 
"Sample2", "Sample3", "Sample4", "Sample5", "Sample6", "Sample7", 
"Sample8", "Sample9", "Sample10", "AASHTO")), class = "data.frame", row.names = c("1", 
"2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12")), structure(list(
    A = c(0.8262825, 1.01, 0.8262825, 1.01, 0.8262825, 1.01, 
    0.8262825, 1.01, 0.8262825, 1.01, 0.8262825, 1.01), B = c(0.734412, 
    0.734412, 0.734412, 0.734412, 0.734412, 0.734412, 0.734412, 
    0.734412, 0.734412, 0.734412, 0.734412, NA), Names = c("Baseline", 
    "Sample1", "Sample2", "Sample3", "Sample4", "Sample5", "Sample6", 
    "Sample7", "Sample8", "Sample9", "Sample10", "AASHTO")), class = "data.frame", row.names = c("1", 
"2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12")))

在列表的每个数据框中添加一行，其中包含某些行的平均值

1 个答案:

数据