Question

如何按“id”分组，将一些算术函数应用于最后四列（按组），并将新行添加到包含结果的df中。以下是5个样本（id）和8列的说明性示例：

    d1   d2   id  type         treat  v1_gm  v2_pct v3_pct
1   info info 1   leaf         NA     0.2    70     90
2   info info 1   flower       A      0.5    80     80
3   info info 2   leaf         NA     0.4    65     80
4   info info 2   flower       A      0.1    90     90
5   info info 3   leaf         NA     0.6    55     80
6   info info 3   stem         A      0.3    80     30
7   info info 4   leaf         NA     0.6    30     40
8   info info 4   flower       A      0.7    75     75
9   info info 5   leaf/stem    NA     0.8    80     75

可重复示例：

df <- data.frame(matrix(NA, nrow = 9, ncol = 8), row.names=NULL)
colnames(df) <- c("d1","d2","id","type","treat","v1_gm","v2_pct","v3_pct")
df$d1 <- "info"
df$d2 <- "info"
id <- c(1,1,2,2,3,3,4,4,5)
df$id <- c(1,1,2,2,3,3,4,4,5)
df$type <- c("leaf","flower","leaf","flower","leaf","stem","leaf","flower","leaf/stem")
df$treat <- c(NA,"A",NA,"A",NA,"A",NA,"A",NA)
df$v1_gm <- c(0.2,0.5,0.4,0.1,0.6,0.3,0.6,0.7,0.8)
df$v2_pct <- c(70,80,65,90,55,80,30,75,80)
df$v3_pct <- c(90,80,80,90,80,30,40,75,75)

结果表应如下所示。第3,6,9和13行是包含结果的新行。新行可以附加在表的末尾，或者放入tmp df以便稍后使用rbind添加（无论如何都无法弄清楚如何操作）。分组var是列“id”。函数sum用于“v1_gm”。函数“mean”用于多个连续列，此处为“v1_pct”和“v3_pct”，应按名称调用（例如，v1_pct：v3_pct）。新行中“type”的值从组行中的“type”连接起来，“d1”和“d2”只是从处理==“A”的组行中复制，并在新行中“处理”为行分配值“cmb”。

    d1   d2   id type         treat v1_gm  v2_pct  v3_pct
1   info info 1  leaf         NA    0.2    70      90
2   info info 1  flower       A     0.5    80      80
3   info info 1  leaf/flower  cmb   0.7    75      85
4   info info 2  leaf         NA    0.4    65      80
5   info info 2  flower       A     0.1    90      90
6   info info 2  leaf/flower  cmb   0.5    77.5    85
7   info info 3  leaf         NA    0.6    55      80
8   info info 3  stem         A     0.3    80      30
9   info info 3  leaf/stem    cmb   0.9    67.5    55
10  info info 4  leaf         NA    0.6    30      40
11  info info 4  flower       A     0.7    75      75
13  info info 4  leaf/flower  cmb   1.3    52.5    57.5
14  info info 5  leaf/stem    NA    0.8    80      75

Answer 1

我不确定您是否可以将组摘要作为一行添加到数据框中。您应该可以将其作为列。

library("dplyr")
res1 <- df %>% group_by(id) %>% mutate( sumV1 = sum(v1_gm),meanV2 = mean(v2_pct),meanV3 = mean(v3_pct),gr_type = paste(type,collapse="/")) %>% filter(treat == "A") %>% select(d1,d2,id,type,v1_gm=sumV1, v2_pct = meanV2, v3_pct = meanV3,type = gr_type)

这会给你答案，然后使用bind_rows你会得到你想要的结果

final_res <- bind_rows(df,res1)

Answer 2

通过对@Arun的回答进行一些修改，以下脚本完全解决了这个问题。

library("dplyr")
res1 <- df %>%  
  group_by(id) %>%  
  mutate(  
    v1_gm = sum(v1_gm),  
    v2_pct = mean(v2_pct),  
    v3_pct = mean(v3_pct),  
    type = paste(type,collapse="/")) %>%  
  filter(treat == "A") %>%  
  mutate(treat = as.character("calculated"))  
final_res1 <- bind_rows(df,res1)  
final_res1$id <- as.character(final_res1$id)  
final_res1 <- final_res1 [order(final_res1$id, final_res1$treat, na.last=FALSE),  ]

将行结果转换为df，并按组计算多个列的名称结果

2 个答案: