Question

出于速度原因，我正在尝试将数据操作代码从dplyr转换为data.table。我几乎在那里，但错过了最后一步。

我有一些示例数据来复制我的问题。

c_dt = data.table(u_id=rep(c("u1", "u2"),each=5),
                  p_id=c("p1", "p1", "p1", "p2","p2", "p1", "p2", "p2", "p2", "p2" ), 
                  c_dt=c("2015-12-01", "2015-12-02", "2015-12-03", "2015-12-02",
                         "2015-12-05", "2015-12-02", "2015-12-03", "2015-12-04", 
                         "2015-12-05", "2015-12-06"))

我希望确定u_id和p_id重复的行;并且只保留最小c_dt的行（基本上保留第一个实例）。我使用以下dplyr代码：

c_df <- as.data.frame(c_dt)
cdedup_df <- c_df %>% group_by(p_id, u_id) %>% filter(c_dt == min(c_dt))

哪个给出以下输出

> cdedup_df
Source: local data frame [4 x 3]
Groups: p_id, u_id

  u_id p_id       c_dt
1   u1   p1 2015-12-01
2   u1   p2 2015-12-02
3   u2   p1 2015-12-02
4   u2   p2 2015-12-03

我有以下data.table代码，可正确识别所需的行，但我无法弄清楚如何只过滤和行。

cdedup_dt <- c_dt[,c_dt == min(c_dt),by = list(u_id, p_id)]
cdedup_dt
    u_id p_id    V1
 1:   u1   p1  TRUE
 2:   u1   p1 FALSE
 3:   u1   p1 FALSE
 4:   u1   p2  TRUE
 5:   u1   p2 FALSE
 6:   u2   p1  TRUE
 7:   u2   p2  TRUE
 8:   u2   p2 FALSE
 9:   u2   p2 FALSE
10:   u2   p2 FALSE

Answer 1

这样的事情可以解决问题：

c_dt[, list(c_dt=min(c_dt)), by=list(u_id, p_id)]
##    u_id p_id       c_dt
## 1:   u1   p1 2015-12-01
## 2:   u1   p2 2015-12-02
## 3:   u2   p1 2015-12-02
## 4:   u2   p2 2015-12-03

Answer 2

在我的方法之下。我希望它可以更好地扩展到大数据集，因为min没有group，只有单一排序，data.table非常有效，然后首先按组子集。

setorderv(c_dt, "c_dt")[, .SD[1L], .(u_id, p_id)]
# in data.table 1.9.7+ you can also use `head`
setorderv(c_dt, "c_dt")[, head(.SD, 1L), .(u_id, p_id)]

以下代码包括当前其他答案的验证如果OP将提供大数据集，我可以添加基准。

library(data.table)
c_dt = data.table(u_id=rep(c("u1", "u2"),each=5), p_id=c("p1", "p1", "p1", "p2","p2", "p1", "p2", "p2", "p2", "p2" ), c_dt=c("2015-12-01", "2015-12-02", "2015-12-03", "2015-12-02", "2015-12-05", "2015-12-02", "2015-12-03", "2015-12-04", "2015-12-05", "2015-12-06"))

zero = c_dt[, list(c_dt=min(c_dt)), by=list(u_id, p_id)]
ananda = c_dt[, list(c_dt = c_dt[c_dt == min(c_dt)]), by = .(u_id, p_id)]
tal = c_dt[, .SD[rank(c_dt, ties.method = c("first")) == 1],by = .(u_id, p_id)]
all.equal(zero, ananda)
#[1] TRUE
all.equal(ananda, tal)
#[1] TRUE

jan = setorderv(c_dt, "c_dt")[, .SD[1L], .(u_id, p_id)]
all.equal(tal, jan)
#[1] TRUE

Answer 3

所以你确实很亲密。您遗失的只是在 j 列中传递.SD。让我们看看它是如何运作的：

library(data.table)
c_dt = data.table(u_id=rep(c("u1", "u2"),each=5),  
                  p_id=c("p1", "p1", "p1", "p2","p2", "p1", "p2", "p2", "p2", "p2" ), 
                  c_dt=c("2015-12-01", "2015-12-02",  
                   "2015-12-03", "2015-12-02", "2015-12-05", 
                   "2015-12-02", "2015-12-03", "2015-12-04", 
                   "2015-12-05", "2015-12-06"))
c_dt
    u_id p_id       c_dt
 1:   u1   p1 2015-12-01
 2:   u1   p1 2015-12-02
 3:   u1   p1 2015-12-03
 4:   u1   p2 2015-12-02
 5:   u1   p2 2015-12-05
 6:   u2   p1 2015-12-02
 7:   u2   p2 2015-12-03
 8:   u2   p2 2015-12-04
 9:   u2   p2 2015-12-05
10:   u2   p2 2015-12-06

现在，我们将按> u_id 和 p_id 进行分组，并按 c_df 的最小值进行过滤：

cdedup_dt <- c_dt[ , .SD[c_dt == min(c_dt)], by = .(u_id, p_id)] cdedup_dt u_id p_id c_dt 1: u1 p1 2015-12-01 2: u1 p2 2015-12-02 3: u2 p1 2015-12-02 4: u2 p2 2015-12-03

请注意，.(u_id, p_id)等于list(u_id, p_id)，.SD是指每个组的Data.table的子集。你所遗忘的只是.SD 正如@ zero323 min 所提到的那样，将保留重复项（这基本上意味着我们的示例中有一些重复的行）。如果您只希望为每个组保留一条记录，则更安全的选择是使用排名功能：

cdedup_dt <- c_dt[, .SD[rank(c_dt, ties.method = c("first")) == 1],by = .(u_id, p_id)] cdedup_dt u_id p_id c_dt 1: u1 p1 2015-12-01 2: u1 p2 2015-12-02 3: u2 p1 2015-12-02 4: u2 p2 2015-12-03

R dplyr到数据表 - 组和过滤器

3 个答案: