Question

我有一个包含每周数据的数据集。一周从星期一开始，到星期日结束。该数据集也按组细分。

我想检测每个组的开始和结束之间是否缺少任何连续的日期。这是一个示例数据集：

Week<- as.Date(c('2015-04-13', '2015-04-20', '2015-05-04', '2015-06-29', '2015-07-27', '2015-08-03'))
Group <- c('A', 'A', 'A','B','B','B','B')
Value<- c(2,3,10,4,11,9,8)

df<-data.frame(Week, Group, Value)

df
      Week    Group     Value
2015-04-13        A         2
2015-04-20        A         3
2015-05-04        A        10
2015-06-29        B         4
2015-07-06        B        11
2015-07-27        B         9
2015-08-03        B         8

对于组B，2015-07-06和2015-07-27之间缺少数据。在2015-04-20和2015-05-04之间的A组中也缺少数据。我想为该组添加一行，其值为NA。我有很多小组，我希望我的预期输出如下：

      Week    Group     Value
2015-04-13        A         2
2015-04-20        A         3
2015-04-27        A        NA
2015-05-04        A        10
2015-06-29        B         4
2015-07-06        B        11
2015-07-13        B        NA
2015-07-20        B        NA
2015-07-27        B         9
2015-08-03        B         8

任何帮助都会很棒，谢谢！

Answer 1

您可以使用complete包中的tidyr，即

library(tidyverse)

df %>% 
 group_by(Group) %>% 
 complete(Week = seq(min(Week), max(Week), by = 'week'))

给出，

# A tibble: 10 x 3
# Groups:   Group [2]
   Group Week       Value
   <fct> <date>     <dbl>
 1 A     2015-04-13     2
 2 A     2015-04-20     3
 3 A     2015-04-27    NA
 4 A     2015-05-04    10
 5 B     2015-06-29     4
 6 B     2015-07-06    NA
 7 B     2015-07-13    NA
 8 B     2015-07-20    NA
 9 B     2015-07-27    11
10 B     2015-08-03     9

Answer 2

我发现这样做的唯一方法是在SQL中使用不等分联接。

library(tidyverse)
library(sqldf)

Week<- as.Date(c('2015-04-13', '2015-04-20', '2015-04-27', '2015-05-04', 
'2015-06-29', '2015-06-07', '2015-07-27', '2015-08-03'))
Group <- c('A', 'A','A', 'A','B','B','B','B')
Value<- c(2,3,2,10,4,11,9,8)

df<-data.frame(Week, Group, Value)

#what are the start and end weeks for each group?
GroupWeeks <- df %>% 
  group_by(Group) %>% 
  summarise(start = min(Week),
            end = max(Week)) 

#What are all the possible weeks?
AllWeeks <- data.frame(Week = seq.Date(min(df$Week), max(df$Week), by = "week"))


#use an inequality join to add rows for every week within the group's range
sqldf("Select AllWeeks.Week, GroupWeeks.[Group], Value
      From AllWeeks inner join GroupWeeks on AllWeeks.Week >= start AND AllWeeks.Week <= end
      left join df on AllWeeks.Week = df.Week and GroupWeeks.[Group] = df.[Group]")

Answer 3

这可以使用seq函数来实现。这是代码段。

代码：

Week<- as.Date(c('2015-04-13', '2015-04-20', '2015-04-27', '2015-05-04', '2015-06-29','2015-07-06', '2015-07-27', '2015-08-03'))
Group <- c('A', 'A','A', 'A','B','B','B','B')
Value<- c(2,3,2,10,4,11,9,8)

df<-data.frame(Week, Group, Value)

#generate all the missing dates
alldates = seq(min(df$Week[df$Group == 'B']), max(df$Week[df$Group == 'B']), 7)

#filter out the dates that are not present in your dataset
dates = alldates[!(alldates %in% df$Week)]

#add these new dates to a new dataframe and rbind with the old dataframe 
new_df = data.frame(Week = dates,Group = 'B', Value = NA)
df = rbind(df, new_df)
df = df[order(df$Week),]

输出：

         Week Group Value
1  2015-04-13     A     2
2  2015-04-20     A     3
3  2015-04-27     A     2
4  2015-05-04     A    10
5  2015-06-29     B     4
6  2015-07-06     B    11
9  2015-07-13     B    NA
10 2015-07-20     B    NA
7  2015-07-27     B     9
8  2015-08-03     B     8

按组插入缺失的连续周

3 个答案: