根据下面的代码和数据，我如何在新数据帧中仅存储FIPS和County的频率，如所需输出所示:
样本数据:
df = structure(list(Key = c("080012020", "120012020", "120012018",
"120012017", "080012017", "120012016", "120012015", "080012014",
"120012013", "120012012", "080012012", "080012011", "080012016"
), County = c("Adams County", "Alachua County", "Alachua County",
"Alachua County", "Adams County", "Alachua County", "Alachua County",
"Adams County", "Alachua County", "Alachua County", "Adams County",
"Adams County", "Adams County"), State = c("CO", "FL", "FL",
"FL", "CO", "FL", "FL", "CO", "FL", "FL", "CO", "CO", "CO"),
FIPS = c("08001", "12001", "12001", "12001", "08001", "12001",
"12001", "08001", "12001", "12001", "08001", "08001", "08001"
), Inflow = c(38L, 261L, 321L, 339L, 58L, 288L, 254L, 46L,
413L, 433L, 30L, 42L, NA), InAGI = c(1817L, 6287L, 8423L,
8364L, 1865L, 14720L, 5224L, 1074L, 11774L, 10151L, 921L,
500L, NA), FiscalYear = c("2019- 2020", "2019- 2020", "2017 - 2018",
"2016 - 2017", "2016 - 2017", "2015 - 2016", "2014 - 2015",
"2013 - 2014", "2012 - 2013", "2011 - 2012", "2011 - 2012",
"2010 - 2011", "2015 - 2016"), Year = c(2020L, 2020L, 2018L,
2017L, 2017L, 2016L, 2015L, 2014L, 2013L, 2012L, 2012L, 2011L,
2016L), Outflow = c(54L, 447L, 444L, 558L, 44L, 436L, 334L,
49L, 466L, 495L, 39L, 31L, 51L), OutAGI = c(1879L, 13106L,
15409L, 16496L, 2408L, 12675L, 7448L, 733L, 10309L, 11677L,
847L, 605L, 1114L), NetMigration = c(-16L, -186L, -123L,
-219L, 14L, -148L, -80L, -3L, -53L, -62L, -9L, 11L, NA)), row.names = c(NA,
-13L), class = "data.frame")
所需输出:
FIPS County Frequency
12001 Alachua County 7
08001 Adams County 6
Base R解:
aggregate(State ~ FIPS + County, data = df, FUN = length)
#> FIPS County State
#> 1 08001 Adams County 6
#> 2 12001 Alachua County 7