R：使用聚集清理数据集

我有一个来自美国农业部的csv数据集，其中有1970年、1980年、1990年和2000年美国各州成年人的教育水平。 我已使用read_csv函数导入此csv，然后按如下方式清理数据集：

colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "State"] <- "state"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Area name"] <- "area_name"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Less than a high school diploma, 1970"] <- "Less Than Diploma, 1970"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "High school diploma only, 1970"] <- "Diploma, 1970"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Some college (1-3 years), 1970"] <- "AA or more, 1970"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Four years of college or higher, 1970"] <- "BA or more, 1970"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults with less than a high school diploma, 1970"] <- "%Less Than Diploma, 1970"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults with a high school diploma only, 1970"] <- "% Diploma, 1970"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults completing some college (1-3 years), 1970"] <- "% AA or more, 1970"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults completing four years of college or higher, 1970"] <- "% BA or more, 1970"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Less than a high school diploma, 1980"] <- "Less Than Diploma, 1980"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "High school diploma only, 1980"] <- "Diploma, 1980" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Some college (1-3 years), 1980"] <- "AA or more, 1980" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Four years of college or higher, 1980"] <- "BA or more, 1980" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults with less than a high school diploma, 1980"] <- "% Less Than Diploma, 1980" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults with a high school diploma only, 1980"] <- "% Diploma, 1980" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults completing some college (1-3 years), 1980"] <- "% AA or more, 1980" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults completing four years of college or higher, 1980"] <- "% BA or more, 1980"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Less than a high school diploma, 1990"] <- "Less Than Diploma, 1990"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "High school diploma only, 1990"] <- "Diploma, 1990" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Some college or associate's degree, 1990"] <- "AA or more, 1990" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Bachelor's degree or higher, 1990"] <- "BA or more, 1990" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults with less than a high school diploma, 1990"] <- "% Less Than Diploma, 1990" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults with a high school diploma only, 1990"] <- "% Diploma, 1990" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults completing some college or associate's degree, 1990"] <- "% AA or more, 1990" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults with a bachelor's degree or higher, 1990"] <- "% BA or more, 1990"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Less than a high school diploma, 2000"] <- "Less Than Diploma, 2000"
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "High school diploma only, 2000"] <- "Diploma, 2000" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Some college or associate's degree, 2000"] <- "AA or more, 2000" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Bachelor's degree or higher, 2000"] <- "BA or more, 2000" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults with less than a high school diploma, 2000"] <- "% Less Than Diploma, 2000" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults with a high school diploma only, 2000"] <- "% Diploma, 2000" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults completing some college or associate's degree, 2000"] <- "% AA or more, 2000" 
colnames(eduLevelsbyCounty)[colnames(eduLevelsbyCounty) == "Percent of adults with a bachelor's degree or higher, 2000"] <- "% BA or more, 2000"

---

colnames（eduLevelsbyCounty）[colnames（edlevelsbycounty）==“State”]我觉得命名变量的方式使它变得不必要的复杂。否则，
privot\u longer
，一个更新的函数来替换
gather
可能会解决这个问题。我把你原来的名字改了一点：

使用
pivot\u longer
将数据从宽透视到长透视
库（tidyverse）
长长的
#一个tibble:4x11
州地区名称年份低于文凭AA或更高学士学位或更高百分比低于D百分比文凭百分比AA或m百分比学士学位或m百分比~
1     1         2 1970                 71      72         73         74                   75              76               77               78
2     1         2 1980                 81      82         83         84                   85              86               87               88
3     1         2 1990                 91      92         93         94                   95              96               97               98
4     1         2 2000                 21      22         23         24                   25              26               27               28
> 

资料
df请提供一个小的可复制示例和预期结果output@akrun，谢谢你，如果我问了一个愚蠢的问题，我很抱歉，但我该如何提供一个可复制的小例子呢？
library(tidyverse)
long<-pivot_longer(df, -c("state", "area_name"),
            names_to = c(".value", "year"), 
            names_sep = "_", values_drop_na = TRUE) 

> long              
# A tibble: 4 x 11
  state area_name year  Less.Than.Diploma Diploma AA.or.more BA.or.more percent.Less.Than.D~ percent.Diploma percent.AA.or.m~ percent.BA.or.m~
  <dbl>     <dbl> <chr>             <dbl>   <dbl>      <dbl>      <dbl>                <dbl>           <dbl>            <dbl>            <dbl>
1     1         2 1970                 71      72         73         74                   75              76               77               78
2     1         2 1980                 81      82         83         84                   85              86               87               88
3     1         2 1990                 91      92         93         94                   95              96               97               98
4     1         2 2000                 21      22         23         24                   25              26               27               28
> 

df <-data.frame(
  "state" = 1, 
  "area_name" =2,
  "Less Than Diploma_1970" = 71,
  "Diploma_1970" = 72,
  "AA or more_1970"  = 73,
  "BA or more_1970"  = 74,
  "percent Less Than Diploma_1970"  = 75,
  "percent Diploma_1970"  = 76,
  "percent AA or more_1970"  = 77,
  "percent BA or more_1970"  = 78,
  "Less Than Diploma_1980"  = 81,
  "Diploma_1980" = 82,
  "AA or more_1980" = 83, 
  "BA or more_1980" = 84, 
  "percent Less Than Diploma_1980" = 85, 
  "percent Diploma_1980" = 86, 
  "percent AA or more_1980" = 87, 
  "percent BA or more_1980" = 88,
  "Less Than Diploma_1990" = 91,
  "Diploma_1990" = 92, 
  "AA or more_1990" = 93, 
  "BA or more_1990" = 94,
  "percent Less Than Diploma_1990" = 95 ,
  "percent Diploma_1990" = 96, 
  "percent AA or more_1990"= 97, 
  "percent BA or more_1990" = 98,
  "Less Than Diploma_2000" = 21,
  "Diploma_2000"  = 22, 
  "AA or more_2000"  = 23, 
  "BA or more_2000"  = 24, 
  "percent Less Than Diploma_2000"  = 25, 
  "percent Diploma_2000"  = 26, 
  "percent AA or more_2000"  = 27, 
  "percent BA or more_2000"  = 28)