R

我使用

dplyr

包的

full\u-join

功能加入了五个数据集。第一个数据集有6165行；第二个数据集有5827行。最终联接的数据集有33503行。 我使用以下代码来连接这五个数据集

n2<-full_join(n96, n01)
    n3<-full_join(n2, n06)
    n4<-full_join(n3, n11)
    nf<-full_join(n4, n16)
    View(nf)

---

n2我不确定
update
函数是如何工作的，但您似乎想更改变量的因子级别。在将数据帧传递给
svydesign
函数之前，可以在
nf
数据帧中执行此操作

library(dplyr)
nf <- nf %>%
  mutate(edu = factor( education, levels = c(0, 1, 2, 3), labels = 
                c("no edu", "primary", "secondary", "higher") ),
        wealth =factor( wealth, levels = c(1, 2, 3, 4, 5) , labels = 
                  c("poorest", "poorer", "middle", "richer", "richest")),
        marital = factor( marital, levels = c(0, 1) , labels = 
                    c( "never married", "married")),
        occu = factor( occu, levels = c(0, 1, 2, 3) , labels =
                 c( "not working" , "professional/technical/manageral/clerial/sale/services" , "agricultural", "skilled/unskilled manual") ),
        age1 = factor(age1, levels = c(1, 2, 3), labels =
                c( "early" , "mid", "late") ),
        obov= factor(obov, levels = c(0, 1, 2), labels= 
               c("normal", "overweight", "obese")),
        over= factor(over, levels = c(0, 1), labels= 
               c("normal", "overweight/obese")),
       working_status= factor (working_status, levels = c(0, 1), labels = c("not working", "working")),
      education1= factor (education1, levels = c(0, 1, 2), labels= 
                      c("no education", "primary", "secondary/secondry+")),
      resi= factor (resi, levels= c(0,1), labels= c("urban", "rural")))

库（dplyr）
nf%
变异（教育程度=因素（教育程度，等级=c（0,1,2,3），标签=
("无教育程度","小学","中学","高级"),，
财富=系数（财富，等级=c（1,2,3,4,5），标签=
c（“最穷”、“较穷”、“中等”、“较富”、“最富有”），
婚姻=因素（婚姻，等级=c（0，1），标签=
c（“未婚”、“已婚”），
占用=系数（占用，级别=c（0,1,2,3），标签=
c（“不工作”、“专业/技术/管理/文书/销售/服务”、“农业”、“熟练/非熟练手册”），
年龄1=系数（年龄1，级别=c（1，2，3），标签=
("早,中,晚),，
obov=系数（obov，级别=c（0,1,2），标签=
c（“正常”、“超重”、“肥胖”），
over=系数（over，levels=c（0，1），标签=
c（“正常”、“超重/肥胖”），
工作状态=系数（工作状态，级别=c（0，1），标签=c（“不工作”，“工作”），
教育1=系数（教育1，级别=c（0，1，2），标签=
c（“无教育”、“小学”、“中学/中学+”），
resi=系数（resi，等级=c（0,1），标签=c（“城市”、“农村”））

svs<-svydesign(id=nf$v021, strata=nf$stra, nest=TRUE, weights=nf$wgtv, data=nf)

svs1 <- 
  update(
    svs, 
    one=1, 
    edu = factor( education, levels = c(0, 1, 2, 3), labels = 
                    c("no edu", "primary", "secondary", "higher") ),
    
    wealth =factor( wealth, levels = c(1, 2, 3, 4, 5) , labels = 
                      c("poorest", "poorer", "middle", "richer", "richest")),
    marital = factor( marital, levels = c(0, 1) , labels = 
                        c( "never married", "married")),
    occu = factor( occu, levels = c(0, 1, 2, 3) , labels =
                           c( "not working" , "professional/technical/manageral/clerial/sale/services" , "agricultural", "skilled/unskilled manual") ),
    age1 = factor(age1, levels = c(1, 2, 3), labels =
                   c( "early" , "mid", "late") ),
    obov= factor(obov, levels = c(0, 1, 2), labels= 
                      c("normal", "overweight", "obese")),
    
    over= factor(over, levels = c(0, 1), labels= 
                   c("normal", "overweight/obese")),
    
    working_status= factor (working_status, levels = c(0, 1), labels = c("not working", "working")),
    education1= factor (education1, levels = c(0, 1, 2), labels= 
                          c("no education", "primary", "secondary/secondry+")),
    resi= factor (resi, levels= c(0,1), labels= c("urban", "rural"))
  )

Error in `[<-.data.frame`(`*tmp*`, , newnames[j], value = c(3L, 3L, 3L,  : 
  replacement has 12674 rows, data has 33503

library(dplyr)
nf <- nf %>%
  mutate(edu = factor( education, levels = c(0, 1, 2, 3), labels = 
                c("no edu", "primary", "secondary", "higher") ),
        wealth =factor( wealth, levels = c(1, 2, 3, 4, 5) , labels = 
                  c("poorest", "poorer", "middle", "richer", "richest")),
        marital = factor( marital, levels = c(0, 1) , labels = 
                    c( "never married", "married")),
        occu = factor( occu, levels = c(0, 1, 2, 3) , labels =
                 c( "not working" , "professional/technical/manageral/clerial/sale/services" , "agricultural", "skilled/unskilled manual") ),
        age1 = factor(age1, levels = c(1, 2, 3), labels =
                c( "early" , "mid", "late") ),
        obov= factor(obov, levels = c(0, 1, 2), labels= 
               c("normal", "overweight", "obese")),
        over= factor(over, levels = c(0, 1), labels= 
               c("normal", "overweight/obese")),
       working_status= factor (working_status, levels = c(0, 1), labels = c("not working", "working")),
      education1= factor (education1, levels = c(0, 1, 2), labels= 
                      c("no education", "primary", "secondary/secondry+")),
      resi= factor (resi, levels= c(0,1), labels= c("urban", "rural")))