隐式 NA 在 Tidyverse 中制作表格

Question

我在尝试使用 tidyverse 创建表时遇到错误消息。错误消息显示

"Factor Com.Race 包含隐式 NA，考虑使用 forcats::fct_explicit_na"。

说到 tidyverse，我是菜鸟。所以我没能多尝试。

Major_A <- rep("Major A", times=150)
set.seed(1984)
gender <- sample(c("Female","Male"), prob=c(.95,.05),size=150, replace=T)
race.asian <- sample(c("Y","N"),prob= c(.01,.99),size=150, replace=T)
race.black <- sample(c("Y","N"),prob= c(.1,.9),size=150, replace=T)
race.AmInd <- sample(c("Y","N"),prob= c(.01,.99),size=150, replace=T)
race.hawa <- sample(c("Y","N"),prob= c(.01,.99),size=150, replace=T)
race.hisp <- sample(c("Y","N"),prob= c(.02,.98),size=150, replace=T)
race.white <- sample(c("Y","N"),prob=c(.8,.2),size=150,replace=T)
race.NotR <- sample(c("Y","N"),prob=c(.01,.98),size=150,replace=T)
degree <- sample(c("BA","MAT"),prob=c(.9,.1),size=150,replace=T)

enroll <- data.frame(Major_A,gender,race.asian,race.black,race.AmInd,race.hawa,race.hisp,race.white, race.NotR, degree)

multi.race_fun <- function(dat,startr,endr){
  dat$multi <- rowSums(dat[,startr:endr]=="Y")
  return(dat)
}

enroll.multiR <- multi.race_fun(enroll,3,9)

# load comrace function 
com_race.fun <- function(dat){
  dat$Com.Race <- ifelse(dat$race.hisp=="Y","Hispanic",
                         ifelse(dat$race.black=="Y" & dat$multi==1, "African Am",
                                ifelse(dat$race.AmInd=="Y" & dat$multi==1,"Native Am",
                                       ifelse(dat$race.asian=="Y" & dat$multi==1,"Asian",
                                              ifelse(dat$race.hawa=="Y" & dat$multi==1, "Hawaiian",
                                                     ifelse(dat$race.white=="Y" & dat$multi==1,"Caucasian",
                                                            ifelse(dat$multi>=2,"Two or More Races","Not Reported")))))))
  return(dat)
}
# run comrace function
enroll.comR <- com_race.fun(enroll.multiR) 
enroll.comR$gender <- factor(enroll.comR$gender, levels= c("Female", "Male"))
enroll.comR$Com.Race <- factor(enroll.comR$Com.Race, levels=c("African Am","Asian","Caucasian","Hawaiian","Hispancic","Two or More Races", "Not Reported"))

library(tidyverse)
gen_race.tbl<- enroll.comR%>%
  group_by(Com.Race, gender, .drop = FALSE) %>%
  summarise(count = n()) %>%
  ungroup() %>%
  mutate(perc = (count/sum(count)*100)) %>%
  gather(key, value, -gender, -Com.Race) %>%
  unite(Com.Race, Com.Race, key) %>%
  spread(Com.Race, value)

我希望代码生成一个表，其中包含 gender 和 Com.Race 变量的所有级别的计数和百分比。

Answer 1

我建议在开始时使用 dplyr 中的 gather() 来重组您的宽格式数据，然后您可以汇总每个级别的性别和种族变量的计数/百分比。最后使用reshape2::dcast() 会得到你想要的输出，但也可以使用spread()。

# toy data set
df <- data.frame(gender=sample(c('M','F'),100,T,prob=c(0.9,0.1)),
                 ethn.a=sample(c('Y','N'),100,T,prob=c(0.8,0.2)),
                 ethn.b=sample(c('Y','N'),100,T,prob=c(0.7,0.3)),
                 ethn.c=sample(c('Y','N'),100,T,prob=c(0.25,0.75)),
                 ethn.d=sample(c('Y','N'),100,T,prob=c(0.95,0.05)))

# gather wide data, group by gender/ethnicity, summarise, reshape to wide format
df %>% gather(k,v,-gender) %>% group_by(gender,k,v) %>% 
  summarise(n=n()) %>% mutate(perc=round((n/sum(n))*100,2)) %>% 
  mutate(cell=paste0(n,' (',sprintf("%.1f",perc),'%)')) %>% 
  select(-n,-perc) %>% 
  filter(v=='Y') %>% reshape2::dcast(v~k+gender, value.var = 'cell')

  v   ethn.a_F   ethn.a_M   ethn.b_F   ethn.b_M  ethn.c_F   ethn.c_M   ethn.d_F    ethn.d_M
1 Y 11 (84.6%) 69 (79.3%) 10 (76.9%) 66 (75.9%) 3 (23.1%) 28 (32.2%) 12 (92.3%) 87 (100.0%)

# using spread()
df %>% gather(k,v,-gender) %>% group_by(gender,k,v) %>% 
  summarise(n=n()) %>% mutate(perc=round((n/sum(n))*100,2)) %>% 
  mutate(cell=paste0(n,' (',sprintf("%.1f",perc),'%)')) %>% 
  select(-n,-perc) %>% 
  filter(v=='Y') %>% 
  spread(k,cell,fill=0)

# A tibble: 2 x 6
# Groups:   gender [2]
  gender v     ethn.a     ethn.b     ethn.c     ethn.d     
  <fct>  <chr> <chr>      <chr>      <chr>      <chr>      
1 F      Y     11 (84.6%) 10 (76.9%) 3 (23.1%)  12 (92.3%) 
2 M      Y     69 (79.3%) 66 (75.9%) 28 (32.2%) 87 (100.0%)