R 根据条件以长格式合并2个数据集

我有两个数据帧，我想合并。数据集之间的差异在于观察的数量和收集方式。在DF1中，在两个不同的日期记录观察结果。每个记录都有一个索引，id1个人识别号，id2指的是进行记录的日期，日期必须不同。还有一个日期变量，用于记录进行记录的星期

在df2中，仅根据序列号和id1个人识别号记录观察结果。每个人只有一次观察。同样，这里还有一个日期变量，用于记录录制开始的时间

我想确定与df1在同一天记录的来自df2的观察结果

我试图创建一个新的索引，以组索引和id1转到long并根据天数合并

Df1:-天表示进行观察的时间，如指数12；id1-表示仅1人；id2表示2天-星期三id2 1和星期日id2 2 2

    index id1 id2  Day         obs1 obs2 obs3
     12    1   1   Wednesday    1    11   12
     12    1   2   Sunday       2     0    0
    123    1   1   Tuesday      1     0    1
    123    1   2   Saturday     3     0    3
    123    2   1   Monday       2     2    4
    123    2   2   Saturday     1     0    8

df2:-此处，day-day变量表示进行观察的起始日期，例如id 12 day2和id 123 day1

index   id1  Day       day1 day2 day3 day4 day5 day6  day7   
 12      1    Tuesday     2    1    2    1    1    3    1    
123      1    Friday      0    3    0    3    3    0    3     

结果：

 index id1 id2   obs1 obs2 obs3 
 12      1   1     1   11    12   
 12      1   2     2    0     0
 123     1   2     3    0     3        
 123     2   2     1    0     8

样本数据

df1：

df2：

我们可以得到df2 lin long格式，按索引分组保存观察后出现的行，并根据索引和日期将其与df1连接

然后可以使用select仅保留所需的列

带有melt from data.table的选项

或者使用tidyverse，最好在summary中返回一个列表列，然后在长度与行数不匹配的情况下返回unnest

library(dplyr)
library(tidyr)
df2 %>%
     pivot_longer(cols = day1:day7) %>%
     group_by(index) %>% 
     slice(match(Day, weekday)[1L]:n()) %>%
     summarise(Day = match(Day, weekday)[1]) %>%
     inner_join(df1 %>%
     mutate(Day = match(Day, weekday)), by = 'index') %>%
     filter(Day.y >= Day.x)
# A tibble: 4 x 8
#  index Day.x   id1   id2 Day.y  obs1  obs2  obs3
#  <dbl> <int> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
#1    12     2     1     1     3     1    11    12
#2    12     2     1     2     7     2     0     0
#3   123     5     1     2     6     3     0     3
#4   123     5     2     2     6     1     0     8

---

@user11964604你好，can。请检查我的最新信息tidyverse@user11964604. 看起来你的电脑正在使用a。与中显示的属性不同dput@user11964604我是。没有从评论中得到逻辑。你能不能作为一个新的投递员投递question@user11964604我的意思是，你可以作为一个新的主题/问题发布，因为其他人也已经根据以前的回答了question@user11964604您可以创建一个命名向量，并在指定从第61-da696天开始和第71-day796天开始时进行匹配。这是7天的顺序，对吗？

structure(list(index = c(12, 123), id1 = c(1, 1), Day = structure(2:1, .Label = c("Friday", 
"Tuesday"), class = "factor"), day1 = c(2, 0), day2 = c(1, 3), 
    day3 = c(2, 0), day4 = c(1, 3), day5 = c(1, 3), day6 = c(3, 
    0), day7 = c(1, 3)), class = "data.frame", row.names = c(NA, 
-2L))

library(dplyr)
weekday <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday", 
             "Saturday", "Sunday")


df2 %>%
  mutate_at(vars(matches('day\\d+')), as.numeric) %>%
  tidyr::pivot_longer(cols = matches('day\\d+')) %>%
  group_by(index) %>%
  filter(row_number() >= match(Day, weekday)[1L]) %>%
  summarise(Day = match(Day, weekday)[1]) %>%
  inner_join(df1 %>%mutate(Day = match(Day, weekday)), by = 'index') %>%
  filter(Day.y >= Day.x)


#  index Day.x   id1   id2 Day.y  obs1  obs2  obs3
#  <dbl> <int> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
#1    12     2     1     1     3     1    11    12
#2    12     2     1     2     7     2     0     0
#3   123     5     1     2     6     3     0     3
#4   123     5     2     2     6     1     0     8

library(data.table)
weekday <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday", "Sunday")

library(haven)
df1$Day <- as.character(as_factor(df1$Day))
df2$Day <- as.character(as_factor(df2$Day))
df1$Day <- match(df1$Day, weekday) 
dt2 <- melt(setDT(df2), measure = patterns('^day\\d+$'))[seq_len(.N) >=
    match(Day, weekday)[1L]][, .(Day = match(Day, weekday)[1]), index]
merge(setDT(df1), dt2, by = 'index')[Day.y < Day.x]
#   index id1 id2 Day.x obs1 obs2 obs3 Day.y
#1:    12   1   1     3    1   11   12     2
#2:    12   1   2     7    2    0    0     2
#3:   123   1   2     6    3    0    3     5
#4:   123   2   2     6    1    0    8     5

library(dplyr)
library(tidyr)
df2 %>%
     pivot_longer(cols = day1:day7) %>%
     group_by(index) %>% 
     slice(match(Day, weekday)[1L]:n()) %>%
     summarise(Day = match(Day, weekday)[1]) %>%
     inner_join(df1 %>%
     mutate(Day = match(Day, weekday)), by = 'index') %>%
     filter(Day.y >= Day.x)
# A tibble: 4 x 8
#  index Day.x   id1   id2 Day.y  obs1  obs2  obs3
#  <dbl> <int> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
#1    12     2     1     1     3     1    11    12
#2    12     2     1     2     7     2     0     0
#3   123     5     1     2     6     3     0     3
#4   123     5     2     2     6     1     0     8