Question

    ID<-(c(1,1,1,1,1,1,2,3))   
    type<-(c("A1","A1","A1","A1","A1","A1","A1","B1"))  
    ag_id<-(c("A0001","A0001","A0001","A0001","A0001","A0001","A0001","B0001")) 
    Outcome<-(c("Aggressive","Aggressive","Aggressive","Aggressive","Aggressive","Aggressive","Aggressive","Balanced")) 
    bdate<-c("2012","2012","2012","2012","2012","2012","2012","2012")   
    sd_num<-(c("AIG0001","AIG0001","AIG0001","AIG0001","AIG0001","AIG0001","AIG0001","AIG0001"))  

    buy_pattern<-data.frame(ID,type,ag_id,Outcome,bdate,sd_num)




  #   > buy_pattern
  #     ID type ag_id    Outcome bdate  sd_num
  #   1  1   A1 A0001 Aggressive  2012 AIG0001
  #   2  1   A1 A0001 Aggressive  2012 AIG0001
  #   3  1   A1 A0001 Aggressive  2012 AIG0001
  #   4  1   A1 A0001 Aggressive  2012 AIG0001
  #   5  1   A1 A0001 Aggressive  2012 AIG0001
  #   6  1   A1 A0001 Aggressive  2012 AIG0001
  #   7  2   A1 A0001 Aggressive  2012 AIG0001
  #   8  3   B1 B0001   Balanced  2012 AIG0001

如何为群组中的ID列找到唯一值，我可以使用sqldf列中的distinctID来完成

data<-sqldf("select count(distinct ID) as distinctID,count(type) as rowCount,type,ag_id,Outcome,bdate,sd_num from buy_pattern group by ag_id,Outcome,sd_num,bdate")


 # > data 
 # distinctID rowCount type ag_id    Outcome bdate  sd_num
 # 1          2        7   A1 A0001 Aggressive  2012 AIG0001
 # 2          1        1   B1 B0001   Balanced  2012 AIG0001

尝试使用长度（唯一（ID））时，会计算总行数而不是特定组中的计数

    data<-buy_pattern %>% select(type,ag_id,Outcome,bdate,sd_num) %>% 
    group_by(type,ag_id,Outcome,sd_num,bdate) %>%    
    mutate(rowCount = n(),distinctID=length(unique(ID))) %>% 
    arrange(ag_id,Outcome,sd_num, desc(rowCount))  %>% 
    slice(1)     

 # > data

 #  distinctID rowCount type ag_id    Outcome bdate  sd_num
 #  1          3        7   A1 A0001 Aggressive  2012 AIG0001
 #  2          3        1   B1 B0001   Balanced  2012 AIG0001

Answer 1

主要原因是'ID'作为对象在全局环境中创建为vector，在dplyr链中，select未调用'ID '导致'ID'被从全球环境中取出。整个矢量'ID'将具有3个唯一元素，并且不遵循group_by步骤。基本上，将“ID”保留在select内将解决问题。有n_distinct替换length(unique(

buy_pattern %>% 
      select(ID, type,ag_id,Outcome,bdate,sd_num) %>% # change here
      group_by(type,ag_id,Outcome,sd_num,bdate) %>%
      mutate(rowCount = n(),distinctID=length(unique(ID))) %>% 
      arrange(ag_id,Outcome,sd_num, desc(rowCount))  %>% 
      slice(1) 
# A tibble: 2 x 8
# Groups:   type, ag_id, Outcome, sd_num, bdate [2]
#     ID   type  ag_id    Outcome  bdate  sd_num rowCount distinctID
#   <dbl> <fctr> <fctr>     <fctr> <fctr>  <fctr>    <int>      <int>
#1     1     A1  A0001 Aggressive   2012 AIG0001        7          2
#2     3     B1  B0001   Balanced   2012 AIG0001        1          1

我们可以使用mutate

而不是summarise

buy_pattern %>%
     group_by(type, ag_id, Outcome, sd_num, bdate) %>%
     summarise(rowCount = n(), distinctID = n_distinct(ID))

查找组中特定列的唯一值

1 个答案: