R語言中subset函數同時依據行列進行數據篩選
1、測試數據
manager <- 1:5 date <- c("10/24/08","10/28/08","10/1/08","10/12/08","5/1/09") country <- c("US","US","UK","UK","UK") gender <- c("M","F","F","M","F") age <- c(32,45,25,39,99) q1 <- c(5,3,3,3,2) q2 <- c(4,5,5,3,2) q3 <- c(5,2,5,4,1) q4 <- c(5,5,5,NA,2) q5 <- c(5,5,2,NA,1) leadership <- data.frame(manager,date,country,gender,age,q1,q2,q3,q4,q5, stringsAsFactors = F) leadership$age[leadership$age == 99] <- NA leadership <- within(leadership,{ agecat = NA agecat[age > 75] <- "Elder" agecat[age >= 55 & age <= 75] <- "Middle age" agecat[age < 55] <- "Young" }) leadership
2、測試
new1 <- subset(leadership, country == "UK" & gender == "F", select = c(date, age, q4)) new1
new2 <- subset(leadership, country == "US" | gender == "M", select = 1:3) new2
new3 <- subset(leadership, country == "US" | gender == "M", select = date:q2) new3
—————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————————
R語言中subset函數。用於同時選擇變量和觀測值。
a <- sample(1:20, 20) b <- sample(letters[1:20],20) c <- sample(LETTERS[1:20],20) d <- data.frame(a,b,c) d <- d[order(d$a),] d e <- subset(d, a > 5 & a < 9, select = c(a,b)) e
